google ads
Search

Everything you need to know about Computed Tomography (CT) & CT Scanning

September 2020 Imaging Pearls - Educational Tools | CT Scanning | CT Imaging | CT Scan Protocols - CTisus
Imaging Pearls ❯ September 2020

-- OR --

Adrenal

  • “In the retroperitoneum, 20–30% of ganglioneuromas arise from the adrenal medulla. Ganglioneuroma tends to occur in adolescents and young adults. Adrenal ganglioneuromas appear as well-defined masses that are oval, crescentic, or lobulated with a fibrous capsule on cross-sectional imaging. Ganglioneuromas are low-attenuating masses (< 40 HU) on unenhanced CT, and they show homogeneous or heterogeneous attenuation with gradual and delayed enhancement on contrast-enhanced CT. Calcifications are present in 42–60% of cases.”
    Imaging Features of Various Adrenal Neoplastic Lesions on Radiologic and Nuclear Medicine Imaging
    Shin YR, Kim KA
    AJR 2015; 205:554–563
  • “Contemporary ACC predominantly presents as an incidental imaging finding, characterised by HU > 20 on nonenhanced CT but variable tumour size (20–196 mm). Malignancy cannot be ruled out by small tumour size only.”
    Adrenocortical carcinoma: presentation and outcome of a contemporary patient series
    Iiro Kostiainen et al.
    Endocrine (2019) 65:166–174
  • “A nonenhanced CT attenuation value less than or equal to 10 HU can be used to diagnose lipid-rich adrenal adenomas (sensitivity 71%, specificity 98%). An adrenal nodule identified at nonenhanced CT with an attenuation value greater than 10 HU cannot be confirmed as an adenoma without further imaging, which could include washout CT and potentially chemical shift MRI.”
    Technical and Interpretive Pitfalls in Adrenal Imaging
    Nandra G et al.
    RadioGraphics 2020; 40:1041–1060
  • “Ganglioneuroma is a benign tumor arising from the sympathetic nerves or within the adrenals. This lesion is more frequently detected in the mediastinum or retro- peritoneum than in the adrenal medulla. Usually, it is a small round mass (2–3cm) with well-defined smooth margins and an inhomogeneous appearance due to mixoid components.”
    Imaging features of adrenal masses
    Domenico Albano et al.
    Insights into Imaging (2019) 10:1
  • "On CT, it appears as a well-circumscribed solid iso- or hypoattenuating lesion, which may display calcifications, necrosis, and hemorrhagic areas. It remains hypoattenuating on early post-contrastographic phases, while becoming hyperattenuating on delayed phases due to persistent enhancement.”
    Imaging features of adrenal masses
    Domenico Albano et al.
    Insights into Imaging (2019) 10:1
  • “Ganglioneuromas are rare, benign neurogenic tumors that arise from sympathetic ganglia. The tumors are composed of mature Schwann cells, ganglion cells, and nerve fibers. Ganglioneuromas may arise anywhere along the paravertebral sympathetic plexus and occasionally from the adrenal medulla. The retroperitoneum (32%–52% of cases) and posterior mediastinum (39%– 43%) are the two most common locations for a ganglioneuroma, followed by the cervical region (8%– 9%).”
    Neurogenic Tumors in the Abdomen: Tumor Types and Imaging Characteristics
    Sung Eun Rha et al.
    RadioGraphics2003;23:29–43
  • “Adrenal ganglioneuromas do not typically secrete exogenous hormones; thus, systemic manifestation of disease would not be expected. The tumor is commonly identified serendipitously in patients undergoing radiologic study for other reasons. This occult nature often presents a challenge to the radiologist attempting to differentiate adrenal ganglioneuroma from other nonhyperfunctioning adrenal tumors such as adenoma, adrenocortical carcinoma, myelolipoma, and hemangioma.”
    Primary adrenal ganglioneuroma: CT findings in four patients.
    G L Johnson, R H Hruban, F F Marshall ,E K Fishman
    American Journal of Roentgenology. 1997;169: 169-171.
  • Adrenal Ganglioneuroma: Facts
    - Benign tumor arising from neural crest tissue
    - Arise in the adrenal medulla but do not secrete any specific hormone
    - Usually detected as an incidental lesion
  • Adrenal Ganglioneuroma: CT Findings
    - 5-9 cm in size
    - Usually smooth and homogeneous type masses
    - May contain calcification
    - Is not locally invasive
  • “Adrenal ganglioneuroma is an uncommon benign tumor that is a solid adrenal mass on CT.The specific diagnosis requires either biopsy or surgical removal for documentation.”
    Primary Adrenal Ganglioneuroma: CT Findings in Four Patients
    Johnson GL et al.
    AJR 1997;169:169-171
  • "Calculations of washout are based on densitometry measurements on delayed postcontrast images relative to the enhancement at portal venous imaging (portal venous phase minus nonenhanced imaging) for absolute washout or portal venous phase attenuation alone for relative washout cal- culations. An absolute washout value greater than or equal to 60% or a relative washout value greater than or equal to 40% is used to identify adrenal adenomas.”
    Technical and Interpretive Pitfalls in Adrenal Imaging
    Nandra G et al.
    RadioGraphics 2020; 40:1041–1060
  • “Hypervascular metastases, such as those from renal cell carcinoma and hepatocellular carci- noma, are known to demonstrate washout that can satisfy criteria for an adenoma.Therefore, care must be taken in patients with a known primary hypervascular tumor, with consideration of further imaging such as FDG PET/CT, close follow-up, or tissue confirmation.”
    Technical and Interpretive Pitfalls in Adrenal Imaging
    Nandra G et al.
    RadioGraphics 2020; 40:1041–1060
  • “It may be challenging to differentiate hemor- rhage from other incidentally identified adrenal pathologic conditions. In such cases, assessment of temporal change and evaluation of the peri- adrenal fat is of use. Periadrenal infiltration or haziness may be visualized from the extension of hematoma into the surrounding tissues.Temporal resolution with a reduction in attenuation is commonly depicted with adrenal hemorrhage at follow-up imaging. Calcification and pseudocyst formation can also occur in the longer term.”
    Technical and Interpretive Pitfalls in Adrenal Imaging
    Nandra G et al.
    RadioGraphics 2020; 40:1041–1060
  • “Adrenal calcification is commonly observed in benign pathologic conditions, typically the sequelae of prior infection or hemorrhage. Calcification is also rarely appreciated in benign adrenal lesions, including cysts, adenomas, and myelolipomas. The presence of calcification does not invariably determine a benign cause, as adrenal calcification may also be identified in malignant pheochromocytomas and in up to 30% of adrenocortical carcinomas.The morphology of calcification within adrenocortical carcinoma is variable, with punctate, patchy, or nodular calcification.”
    Technical and Interpretive Pitfalls in Adrenal Imaging
    Nandra G et al.
    RadioGraphics 2020; 40:1041–1060
  • "The minority of endogenous Cushing syndrome cases are secondary to a primary adrenal cause (20%), with functioning adenomas and less commonly carcinomas being the major diagnos- tic considerations.There may be radiologic signs of a cortisol-secreting tumor, for example contralateral adrenal gland atrophy as a conse- quence of reduced pituitary ACTH secretion.”
    Technical and Interpretive Pitfalls in Adrenal Imaging
    Nandra G et al.
    RadioGraphics 2020; 40:1041–1060
  • “Primary hyperaldosteronism, due to either aldosterone-producing adenomas (APAs) or bilateral adrenal hyperplasia (BAH), is the most common cause of secondary hypertension. Careful radio- logic evaluation is required to differentiate the two, as a solitary-functioning adenoma is usually treated surgically while bilateral hyperplasia is typically treated medically.The identifica- tion of a nodule must be considered in the con- text of the remainder of the gland morphology, as the removal of a nodule that is actually part of a diffuse hyperplastic process may be futile . Similarly, the presence of numerous nodules can make the distinction between nodular hyperplasia and adenoma difficult.”
    Technical and Interpretive Pitfalls in Adrenal Imaging
    Nandra G et al.
    RadioGraphics 2020; 40:1041–1060
Cardiac

  • "KD is associated with mucocutaneous lymph node syndrome and predominantly affects medium and small arteries in infants and children less than 5 years of age. It is more prevalent in Asian populations and has a male dominance.”
    Radiologic Imaging in Large and Medium Vessel Vasculitis
    Weinrich JM et al.
    Radiol Clin N Am 58 (2020) 765–779
  • “The coronary arteries are often involved in KD and coronary artery aneurysms develop as a result of coronary vasculitis in about 15% to 25% of untreated patients. Coronary artery aneurysms can be classified according to their size (small, <5 mm; medium, 5–8 mm; and large, >8 mm) and shape (saccular or fusiform). Large coronary artery aneurysms are associated with a higher risk of complications such as rupture, thrombosis, and stenosis, which possibly lead to myocardial infarction and death."
    Radiologic Imaging in Large and Medium Vessel Vasculitis
    Weinrich JM et al.
    Radiol Clin N Am 58 (2020) 765–779
Chest

  • “In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symp- toms, exposure history and laboratory testing to rapidly diagnose patients who are positive for COVID-19. Among a total of 905 patients tested by real-time RT–PCR assay and next-generation sequencing RT–PCR, 419 (46.3%) tested positive for SARS-CoV-2. In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of patients who were positive for COVID-19 via RT–PCR who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • “In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of patients who were positive for COVID-19 via RT–PCR who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • "We believe implementation of the joint algorithm discussed above could aid in both issues. First, the AI algorithm could evaluate the CT immediately after completion. Second, the algorithm outperformed radiologists in identifying patients positive for COVID-19, demonstrating normal CT results in the early stage. Third, the algorithm performed equally well in sensitivity (P = 0.05) in the diagnosis of COVID-19 as compared to a senior thoracic radiologist. Specifically, the joint algorithm achieved a statistically significant 6% (P = 0.00146) and 12% (P < 1 × 10−4) improvement in AUC as compared to the CNN model using only CT images and the MLP model using only clinical information respectively.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • "In conclusion, these results illustrate the potential role for a highly accurate AI algorithm for the rapid identification of COVID-19 patients, which could be helpful in combating the current disease outbreak. We believe the AI model proposed, which combines CT imaging and clinical information and shows equivalent accuracy to a senior chest radiologist, could be a useful screening tool to quickly diagnose infectious diseases such as COVID-19 that does not require radiologist input or physical tests.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • Primary Ciliary Dyskinesia
    - Primary ciliary dyskinesia (PCD) is usually an autosomal recessive genetic condition in which the microscopic organelles (cilia) in the respiratory system have defective function. Ciliary dysfunction prevents the clearance of mucous from the lungs, paranasal sinuses and middle ears. Bacteria and other irritants in the mucous lead to frequent respiratory infections. Kartagener syndrome is a type of PCD associated with a mirror-image orientation of the heart and other internal organs (situs inversus). Rare cases of X-linked and autosomal dominant inheritance have been observed.
  • “Rosai-Dorfman disease represents a wide-spectrum disease not limited to lymph nodes. Radiologically, RDD has diverse imaging findings. However, most lesions were hypermetabolic on 18F-fluorodeoxyglucose positron-emission tomography/computed tomography and isointense on T1-weighted imaging. Patients with RDD have a high rate of comorbid diseases including autoimmune disease, viral infections, and cancer.”
    Disease Characteristics, Radiologic Patterns, Comorbid Diseases, and Ethnic Differences in 32 Patients With Rosai-Dorfman Disease
    Mohamed Elshikh et al.
    J Comput Assist Tomogr 2020;44: 450–461
  • “Rosai-Dorfman disease (RDD) or sinus histocytosis with mas- sive lymphadenopathy is a rare, classically nonmalignant, and proliferative disorder of histiocytes that was first described in 1969 by Rosai and Dorfman. The usual presentation is a young patient in his first or second decade of life with cervical and submandibular lymphadenopathy. Rarely, RDD may be associatedwith systemic symptoms such as fever, malaise, and weight loss. A high erythrocyte sedimentation rate, neutrophilic leukocytosis, anemia, and polyclonal gammopathy frequently present in RDD patients. No etiology has been established for RDD, but in ectious, neoplastic, autoimmune, and immunodeficiency-related causes have been hypothesized.”
    Disease Characteristics, Radiologic Patterns, Comorbid Diseases, and Ethnic Differences in 32 Patients With Rosai-Dorfman Disease
    Mohamed Elshikh et al.
    J Comput Assist Tomogr 2020;44: 450–461
  • “Radiographically, RDD has nonspecific image findings, and presentation varies according to the affected organ. Nodal disease presents as a pathological lymph node enlargement, with the cervical chain being the most commonly affected. Axillary, inguinal, hilar, mediastinal, and retroperitoneal lymph nodes are less frequently affected and usually smaller than the cervical chain.”
    Disease Characteristics, Radiologic Patterns, Comorbid Diseases, and Ethnic Differences in 32 Patients With Rosai-Dorfman Disease
    Mohamed Elshikh et al.
    J Comput Assist Tomogr 2020;44: 450–461
  • “Anatomically, the head and neck including cervical lymph nodes are the most commonly affected locations by RDD. The predilection of RDD to affect the head and neck is well documented.Among 423 RDD patients, head and neck RDD represented 38% of extranodal disease. However, Goyal et al reported subcutaneous tissue as the most common affected anatomical location by RDD.”
    Disease Characteristics, Radiologic Patterns, Comorbid Diseases, and Ethnic Differences in 32 Patients With Rosai-Dorfman Disease
    Mohamed Elshikh et al.
    J Comput Assist Tomogr 2020;44: 450–461
  • "Rosai-Dorfman disease represents a wide-spectrum disease not limited to the lymph nodes, with extranodal disease being possibly more common than nodal disease. Radiologically, RDD had diverse imaging findings. However, most lesions are hypermetabolic on PET/CT and isointense on T1-WI. In addition, we found a high rate of comorbid diseases in RDD patients, in- cluding autoimmune disease, viral infections, and cancer. Rosai- Dorfman disease may have a difference in organ involvement among ethnic groups.”
    Disease Characteristics, Radiologic Patterns, Comorbid Diseases, and Ethnic Differences in 32 Patients With Rosai-Dorfman Disease
    Mohamed Elshikh et al.
    J Comput Assist Tomogr 2020;44: 450–461
  • Main Points
    Rosai-Dorfman disease is more likely to affect extranodal tis- sues, especially the head and neck. More than half (62.5%) of our population had a pure extranodal disease. Absence of nodal disease does not exclude RDD from the differential. Most RDD lesions are hypermetabolic on PET/CT and isointense on T1-WI MRI.
    Thirty-two percent of our patients had comorbid diseases. The most common comorbid diseases in patients with RDD were autoimmune diseases, viral infections, and cancers.
    Rosai-Dorfman disease organ affection is slightly different be- tween ethnic groups. Central nervous system RDD is more common in white ethnicity.
    Disease Characteristics, Radiologic Patterns, Comorbid Diseases, and Ethnic Differences in 32 Patients With Rosai-Dorfman Disease
    Mohamed Elshikh et al.
    J Comput Assist Tomogr 2020;44: 450–461
  • Background: IBM Watson for Oncology (WFO) is a cognitive computing system helping physicians quickly identify key information in a patient’s medical record, surface relevant evidence, and explore treatment options. This study assessed the possibility of using WFO for clinical treatment in lung cancer patients.
    Methods: We evaluated the level of agreement between WFO and multidisciplinary team (MDT) for lung cancer. From January to December 2018, newly diagnosed lung cancer cases in Chonnam National University Hwasun Hospital were retrospectively examined using WFO version 18.4 according to four treatment categories (surgery, radiotherapy, chemoradiotherapy, and palliative care). Treatment recommendations were considered concordant if the MDT recommendations were designated ‘recommended’ by WFO. Concordance between MDT and WFO was analyzed by Cohen’s kappa value.
    Artificial intelligence and lung cancer treatment decision: agreement with recommendation of multidisciplinary tumor board
    Min-Seok Kim et al.
    Transl Lung Cancer Res 2020;9(3):507-514
  • Results: In total, 405 (male 340, female 65) cases with different histology (adenocarcinoma 157, squamous cell carcinoma 132, small cell carcinoma 94, others 22 cases) were enrolled. Concordance between MDT and WFO occurred in 92.4% (k=0.881, P<0.001) of all cases, and concordance differed according to clinical stages. The strength of agreement was very good in stage IV non-small cell lung carcinoma (NSCLC) (100%, k=1.000) and extensive disease small cell lung carcinoma (SCLC) (100%, k=1.000). In stage I NSCLC, the agreement strength was good (92.4%, k=0.855). The concordance was moderate in stage III NSCLC (80.8%, k=0.622) and relatively low in stage II NSCLC (83.3%, k=0.556) and limited disease SCLC (84.6%, k=0.435). There were discordant cases in surgery (7/57, 12.3%), radiotherapy (2/12, 16.7%), and chemoradiotherapy (15/129, 11.6%), but no discordance in metastatic disease patients.
    Conclusions: Treatment recommendations made by WFO and MDT were highly concordant for lung cancer cases especially in metastatic stage. However, WFO was just an assisting tool in stage I–III NSCLC and limited disease SCLC; so, patient-doctor relationship and shared decision making may be more important in this stage..
    Artificial intelligence and lung cancer treatment decision: agreement with recommendation of multidisciplinary tumor board
    Min-Seok Kim et al.
    Transl Lung Cancer Res 2020;9(3):507-514
  • Methods: We evaluated the level of agreement between WFO and multidisciplinary team (MDT) for lung cancer. From January to December 2018, newly diagnosed lung cancer cases in Chonnam National University Hwasun Hospital were retrospectively examined using WFO version 18.4 according to four treatment categories (surgery, radiotherapy, chemoradiotherapy, and palliative care). Treatment recommendations were considered concordant if the MDT recommendations were designated ‘recommended’ by WFO. Concordance between MDT and WFO was analyzed by Cohen’s kappa value.
    Conclusions: Treatment recommendations made by WFO and MDT were highly concordant for lung cancer cases especially in metastatic stage. However, WFO was just an assisting tool in stage I–III NSCLC and limited disease SCLC; so, patient-doctor relationship and shared decision making may be more important in this stage..
    Artificial intelligence and lung cancer treatment decision: agreement with recommendation of multidisciplinary tumor board
    Min-Seok Kim et al.
    Transl Lung Cancer Res 2020;9(3):507-514
  • “In conclusion, treatment decisions made by WFO exhibited a high degree of agreement with those of the MDT tumor board, and the concordance varied by stage. AI-based CDSS is expected to play an assistive role, particularly in the metastatic lung cancer stage with less complex treatment options. However, patient-doctor relationships and shared decision making may be more important in non-metastatic lung cancer because of the complexity to reach at an appropriate decision. Further study is warranted to overcome this gray area for current machine learning algorithms.”
    Artificial intelligence and lung cancer treatment decision: agreement with recommendation of multidisciplinary tumor board
    Min-Seok Kim et al.
    Transl Lung Cancer Res 2020;9(3):507-514
  • “In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symp- toms, exposure history and laboratory testing to rapidly diagnose patients who are positive for COVID-19. Among a total of 905 patients tested by real-time RT–PCR assay and next-generation sequencing RT–PCR, 419 (46.3%) tested positive for SARS-CoV-2. In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of patients who were positive for COVID-19 via RT–PCR who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • “In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of patients who were positive for COVID-19 via RT–PCR who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • "We believe implementation of the joint algorithm discussed above could aid in both issues. First, the AI algorithm could evaluate the CT immediately after completion. Second, the algorithm outperformed radiologists in identifying patients positive for COVID-19, demonstrating normal CT results in the early stage. Third, the algorithm performed equally well in sensitivity (P = 0.05) in the diagnosis of COVID-19 as compared to a senior thoracic radiologist. Specifically, the joint algorithm achieved a statistically significant 6% (P = 0.00146) and 12% (P < 1 × 10−4) improvement in AUC as compared to the CNN model using only CT images and the MLP model using only clinical information respectively.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • "In conclusion, these results illustrate the potential role for a highly accurate AI algorithm for the rapid identification of COVID-19 patients, which could be helpful in combating the current disease outbreak. We believe the AI model proposed, which combines CT imaging and clinical information and shows equivalent accuracy to a senior chest radiologist, could be a useful screening tool to quickly diagnose infectious diseases such as COVID-19 that does not require radiologist input or physical tests.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3 
Deep Learning

  • “To prevent patient privacy compromise while promoting scientific research on large datasets that aims to improve patient care, the implementation of technical solutions to simultaneously address the demands for data protection and utilization is mandatory. Here we present an overview of current and next-generation methods for federated, secure and privacy-preserving artificial intelligence with a focus on medical imaging applications, alongside potential attack vectors and future prospects in medical imaging and beyond.”
    Secure, privacy-preserving and federated machine learning in medical imaging
    Georgios A. Kaissis et al.
    Nat Mach Intell 2, 305–311 (2020)

  • Secure, privacy-preserving and federated machine learning in medical imaging
    Georgios A. Kaissis et al.
    Nat Mach Intell 2, 305–311 (2020)
  • Key Points
    • Successful implementation of AI in radiology requires collaboration between radiologists and referring clinicians.
    • Implementation of AI in radiology is facilitated by the presence of a local champion.
    • Evidence on the clinical added value of AI in radiology is needed for successful implementation.
    Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors
    Lea Strohm et al.
    Eur Radiol (2020). https://doi.org/10.1007/s00330-020-06946-y
  • “Considering the great attention AI applications are receiving in radiology and other medical disciplines like pathology, un- derstanding the barriers of and facilitators for the implemen- tation of AI is important. One of the important facilitating factors is the presence of a “local champion,” an individual with a strong personal interest in AI applications who most often initiates and actively advances AI implementation in the organization.”
    Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors
    Lea Strohm et al.
    Eur Radiol (2020). https://doi.org/10.1007/s00330-020-06946-y
  • "Among the most prominent hindering factors is the uncertain added value for clinical practice, which causes low acceptance of AI applications among adopters and complicates the mobilization of funds to acquire AI applications. Furthermore, the failure to include all relevant stakeholders in the planning, execution, and monitoring phase of the implementation of AI applications was found to be a major hindering factor.”
    Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors
    Lea Strohm et al.
    Eur Radiol (2020). https://doi.org/10.1007/s00330-020-06946-y
  • “To increase the acceptance among adopters, more evidence of the added benefit of their AI applications in the clinical setting is needed. Also, all involved stakeholders (most notably radiologists and referring clinicians) should be included in the decisions for and the design of implementation processes of AI applications.”
    Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors
    Lea Strohm et al.
    Eur Radiol (2020). https://doi.org/10.1007/s00330-020-06946-y
  • “In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symp- toms, exposure history and laboratory testing to rapidly diagnose patients who are positive for COVID-19. Among a total of 905 patients tested by real-time RT–PCR assay and next-generation sequencing RT–PCR, 419 (46.3%) tested positive for SARS-CoV-2. In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of patients who were positive for COVID-19 via RT–PCR who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3 
  • “In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of patients who were positive for COVID-19 via RT–PCR who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • "We believe implementation of the joint algorithm discussed above could aid in both issues. First, the AI algorithm could evaluate the CT immediately after completion. Second, the algorithm outperformed radiologists in identifying patients positive for COVID-19, demonstrating normal CT results in the early stage. Third, the algorithm performed equally well in sensitivity (P = 0.05) in the diagnosis of COVID-19 as compared to a senior thoracic radiologist. Specifically, the joint algorithm achieved a statistically significant 6% (P = 0.00146) and 12% (P < 1 × 10−4) improvement in AUC as compared to the CNN model using only CT images and the MLP model using only clinical information respectively.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3
  • "In conclusion, these results illustrate the potential role for a highly accurate AI algorithm for the rapid identification of COVID-19 patients, which could be helpful in combating the current disease outbreak. We believe the AI model proposed, which combines CT imaging and clinical information and shows equivalent accuracy to a senior chest radiologist, could be a useful screening tool to quickly diagnose infectious diseases such as COVID-19 that does not require radiologist input or physical tests.”
    Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
    Xueyan Mei et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0931-3 
  • Background: Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images.
    Methods: A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN.
    Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images
    Toshiaki Hirasawa et al.
    Gastric Cancer (2018) 21:653–660
  • Results: The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface.
    Conclusion: The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.
    Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images
    Toshiaki Hirasawa et al.
    Gastric Cancer (2018) 21:653–660
  • “In conclusion, we developed a CNN system for detecting gastric cancer using stored endoscopic images, which processed extensive independent images in a very short time. The clinically relevant diagnostic ability of the CNN offers a promising applicability to daily clinical practice for reducing the burden of endoscopists as well as telemedicine in remote and rural areas as well as in developing countries where the number of endoscopists is limited.”
    Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images
    Toshiaki Hirasawa et al.
    Gastric Cancer (2018) 21:653–660
  • AI and Medicine: Changing the Workflow
    - GI Endoscopy
    - Acute findings in CT (pneumothorax, intracranial bleed, PE)
    - Goal is to increase physician accuracy and perhaps increase workflow/through-put
  • "KD is associated with mucocutaneous lymph node syndrome and predominantly affects medium and small arteries in infants and children less than 5 years of age. It is more prevalent in Asian populations and has a male dominance.”
    Radiologic Imaging in Large and Medium Vessel Vasculitis
    Weinrich JM et al.
    Radiol Clin N Am 58 (2020) 765–779
  • “The coronary arteries are often involved in KD and coronary artery aneurysms develop as a result of coronary vasculitis in about 15% to 25% of untreated patients. Coronary artery aneurysms can be classified according to their size (small, <5 mm; medium, 5–8 mm; and large, >8 mm) and shape (saccular or fusiform). Large coronary artery aneurysms are associated with a higher risk of complications such as rupture, thrombosis, and stenosis, which possibly lead to myocardial infarction and death."
    Radiologic Imaging in Large and Medium Vessel Vasculitis
    Weinrich JM et al.
    Radiol Clin N Am 58 (2020) 765–779
  • “The decision of what imaging test is most appropriate in each situation is influenced by many factors, some of which are highly subjective. The issue of over- and under-utilization of imaging resources is something that every clinician and radiologist struggles with. The desire to not miss acute pathology is balanced with the potential detriment of excessive radiation dose to susceptible populations. There likely exists a combination of historical and objective factors which can predict outcomes with sufficient sensitivity and specificity to guide the ordering pattern of most physicians.”
    Applications of artificial intelligence in the emergency department
    Supratik K. Moulik, Nina Kotter, Elliot K. Fishman
    Emergency Radiology (2020) 27:355–358
  • "In the future, predictive models will be trained on clinical, treatment, laboratory, and genetic data of individuals to facilitate personalized treatments. Machine learning systems are uniquely equipped for finding groups and subgroups that require more aggressive management. The goal of incorporating viral and host genetic data will require significant advances in computing and genetic sequencing.”
    Applications of artificial intelligence in the emergency department
    Supratik K. Moulik, Nina Kotter, Elliot K. Fishman
    Emergency Radiology (2020) 27:355–358
  • "It is important to keep the evolution of the AI/ML technology in context so as not to become overly enthusiastic about the current capabilities and simultaneously not to become overly pessimistic about future developments. Though the promised delivery date of fully self-driving cars has continuously been pushed back for the past decade, it is undeniable that drivers in semiautonomous vehicles are safer than unassisted drivers. Similarly, there are tangible patient care and cost benefits to be obtained through staged development of AL/ML systems even if fully autonomous MD systems are not on the horizon.”
    Applications of artificial intelligence in the emergency department
    Supratik K. Moulik, Nina Kotter, Elliot K. Fishman
    Emergency Radiology (2020) 27:355–358
  • “The FDA approval process to date has focused on applications (apps) that affect patient triage and not necessarily apps that have the computer serve as the only or final reader. We have chosen a select group of apps to provide the reader with a sense of the current state of AI use in the ER setting. Because adoption of new technology and FDA approval are always works in progress, it is not our intention here to be comprehensive. For a more thorough review of approved AI applications, please see the American College of Radiology record available here (https:// www.acrdsi.org/DSI-Services/FDA-Cleared-AI-Algorithms).”
    The first use of artificial intelligence (AI) in the ER: triage not diagnosis
    Edmund M. Weisberg, Linda C. Chu, Elliot K. Fishman
    Emergency Radiology (2020) 27:361–366
  • “Digital technology, including its omnipresent connectedness and its powerful artificial intelligence, is the most recent long wave of humanity’s socioeconomic evolution. The first technological revolutions go all the way back to the Stone, Bronze, and Iron Ages, when the transformation of material was the driving force in the Schumpeterian process of creative destruction. A second metaparadigm of societal modernization was dedicated to the transformation of energy (aka the “industrial revolutions”), including water, steam, electric, and combustion power. The current metaparadigm focuses on the transformation of information. Less than 1% of the world's technologically stored information was in digital format in the late 1980s, surpassing more than 99% by 2012. Every 2.5 to 3 years, humanity is able to store more information than since the beginning of civilization. The current age focuses on algorithms that automate the conversion of data into actionable knowledge.”
    Digital technology and social change: the digital transformation of society from a historical perspective
    Martin Hilbert
    DIALOGUES IN CLINICAL NEUROSCIENCE • Vol 22 • No. 2 • 2020
  • “The current metaparadigm focuses on the transformation of information. Less than 1% of the world's technologically stored information was in digital format in the late 1980s, surpassing more than 99% by 2012. Every 2.5 to 3 years, humanity is able to store more information than since the beginning of civilization. The current age focuses on algorithms that automate the conversion of data into actionable knowledge.”
    Digital technology and social change: the digital transformation of society from a historical perspective
    Martin Hilbert
    DIALOGUES IN CLINICAL NEUROSCIENCE • Vol 22 • No. 2 • 2020
  • “Each technological revolution, originally received as a bright new set of opportunities, is soon recognized as a threat to the established way of doing things in firms, institutions, and society at large. The new techno-economic paradigm gradually takes shape as a different “common sense” for effective action in any area of endeavor. But while competitive forces, profit seeking, and survival pressures help diffuse the changes in the economy, the wider social and institutional spheres — where change is also needed — are held back by strong inertia stemming from routine, ideology, and vested interests. It is this difference in rhythm of change, between the techno-economic and the socio-institutional spheres, that would explain the turbulent period.”
    Digital technology and social change: the digital transformation of society from a historical perspective
    Martin Hilbert
    DIALOGUES IN CLINICAL NEUROSCIENCE • Vol 22 • No. 2 • 2020
  • “The first focused on the transformation of material, including stone, bronze, and iron. The second, often referred to as industrial revolutions, was dedicated to the transformation of energy, including water, steam, electric, and combustion power. Finally, the most recent metaparadigm aims at transforming information. It started out with the proliferation of communication and stored data and has now entered the age of algorithms, which aims at creating automated processes to convert the existing information into actionable knowledge.”
    Digital technology and social change: the digital transformation of society from a historical perspective
    Martin Hilbert
    DIALOGUES IN CLINICAL NEUROSCIENCE • Vol 22 • No. 2 • 2020
  • “PDAC is the most common pancreatic malig- nancy, accounting for more than 85% of pancreatic tumors. It is typically a disease of elderly patients, with a mean age at presentation of 68 years and a male-to-female ratio of 1.6:1. After colorectal cancer, it is the second most common cancer of the digestive system in the United States, and its incidence is rising sharply.The development of pancreatic cancer is strongly related to smoking, family history, obesity, long-standing diabetes, and chronic pancreatitis. Early stages of PDAC are clinically silent. Abdominal pain is the most frequently reported clinical symptom, even when the tumor is small (<2 cm).”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "With the development of AI and all its potential wonders in terms of increasing the accuracy of our diagnostic capabilities and potentially improving patient care, we must also be concerned about the potential dark side by bad actors. The sooner organized radiology and organized medicine address these issues with clarity, the more stable and protected the health care system and our patients will be from those intent on creating harm and havoc by abusing AI. The acceleration of data sharing during the current pandemic exposes critical vulnerabilities in data security. It reminds us of the pervasive threat that bad actors can and will exploit any technology for their selfish gains. Doing nothing is not a viable strategy, but acting in a concerted effort will lead us to the protection we need and is important as we push AI development over the next several years.”
    The Potential Dangers of Artificial Intelligence for Radiology and Radiologists
    Linda C. Chu, MD, Anima Anandkumar, PhD, Hoo Chang Shin, PhD, Elliot K. Fishman, MD
    JACR (in press)
  • “Pancreatic cancer continues to be one of the deadliest malignancies and is the third leading cause of cancer-related mortality in the United States. Based on several models, it is projected to become the second leading cause of cancer-related deaths by 2030. Although the overall survival rate for patients diagnosed with pancreatic cancer is less than 10%, survival rates are increasing in those whose cancers are detected at an early stage, when intervention is possible. There are, however, no reli- able biomarkers or imaging technology that can detect early-stage pancreatic cancer or accurately identify precursors that are likely to progress to malignancy.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • "The challenge now is to develop imaging biomarkers and models that can further improve sensitivity for the detection of early-stage PDACs and aggressive neoplasms while mitigating diagnostic uncertainty in evaluation of premalignant abnormalities. Augmented reality, artificial intelligence (AI), and related computa- tional techniques can uncover these subtle patterns, improve image interpretation, and streamline diagnostic workflows.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • "Currently, identification of localized pancreatic cancer is mostly incidental as localized pancreatic cancer is asymptomatic. What is urgently needed are minimally invasive screening strategies with a high clinical sensitivity and specificity to identity early-stage cancer and improve these grim statistics. To this end, it is particularly important to develop tests that have high specificity because a false-positive test may trigger unnecessary invasive procedures, which add their own risk of morbidity and mortality.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • There are many challenges that need to be mitigated in the development of an image repository to enable AI system development. These include the following:
    (1) What are the requirements for defining image annotation? 
    (2) What are the main concerns with depositing patient imaging data?
    (3) What are the definitions of an AI-specific clinical use cases?
    (4) What are the benefits and drawbacks of alternative data sharing in facilitating AI development? 

  • Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886

  • Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • “The AI-driven diagnostic software has the potential to trans- form early detection of pancreatic cancer by improving accuracy and consistency of interpretation of radiologic imaging scans and related patient data. The development of reproducible AI systems requires access to current, large, diverse, and multisite data sets, which are subject to numerous data sharing limitations. Future efforts are likely to involve alternative data sharing solutions to enable the development of both public and private AI-ready data resources. Early detection of pancreatic cancer represents an attractive AI use case, well matched to benefit from the MTD challenge approach. This approach will significantly expand the use of sensitive data to improve early detection of pancreatic cancer and lay the foundation for the development of federated architectures for real-world medical data in general.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • Purpose: The purpose of this study is to evaluate diagnostic performance of a commercially available radiomics research prototype vs. an in-house radiomics software in the binary classification of CT images from patients with pancreatic ductal adenocarcinoma (PDAC) vs. healthy controls.
    Results: When 40 radiomics features were used in the random forest classification, in-house software achieved superior sensitivity (1.00) and accuracy (0.992) compared to the commercially available research prototype (sensitivity = 0.950, accuracy = 0.968). When the number of features was reduced to five features, diagnostic performance of the in-house soft- ware decreased to sensitivity (0.950), specificity (0.923), and accuracy (0.936). Diagnostic performance of the commercially available research prototype was unchanged.
    Conclusion: Commercially available and in-house radiomics software achieve similar diagnostic performance, which may lower the barrier of entry for radiomics research and allow more clinician-scientists to perform radiomics research.
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology (2020) 45:2469–2475
  • “This study showed that a commercially available radiomics software may be able to achieve similar diagnostic performance as an in-house radiomics software. The results obtained from one radiomics software may be transferrable to another system. Availability of commercial radiomics software may lower the barrier of entry for radiomics research and allow more researchers to engage in this exciting area of research.”
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology (2020) 45:2469–2475
  • “However, there is also the potential for harm if these artificial images infiltrate our health care system by hackers with malicious intent. As proof of principle, Mirsky et al [3] showed that they were able to tamper with CT scans and artificially inject or remove lung cancers on the images. When the radiologists were blinded to the attack, this hack had a 99.2% success rate for cancer injection and a 95.8% success rate for cancer removal. Even when the radiologists were warned about the attack, the success of cancer injection decreased to 70%, but the cancer removal success rate remained high at 90%. This illustrates the sophistication and realistic appearance of such artificial images. These hacks can be targeted against specific patients or can be used as a more general attack on our radiologic data.”
    The Potential Dangers of Artificial Intelligence for Radiology and Radiologists
    Linda C. Chu, MD, Anima Anandkumar, PhD, Hoo Chang Shin, PhD, Elliot K. Fishman, MD
    JACR (in press)
  • “A generative adversarial network (GAN) is a recently developed deep- learning model aimed at creating new images. It simultaneously trains a generator and a discriminator network, which serves to generate artificial images and to discriminate real from artificial images, respectively. We have recently described how GANs can produce artificial images of people and audio content that fool the recipient into believing that they are authentic. As applied to medical imaging, GANs can generate synthetic images that can alter lesion size, location, and transpose abnormalities onto normal examinations. GANs have the potential to improve image quality, reduce radiation dose, augment data for training algorithms, and perform automated image segmentation.”
    The Potential Dangers of Artificial Intelligence for Radiology and Radiologists
    Linda C. Chu, MD, Anima Anandkumar, PhD, Hoo Chang Shin, PhD, Elliot K. Fishman, MD
    JACR (in press)
  • "However, there are several ways to mitigate potential AI-based hacks and attacks. These include clear security guide- lines and protocols that are uniform across the globe. As deep-fake technology gets more sophisticated, there is emerging research on AI-driven defense strategies. One example features the training of an AI to detect artificial images by image artifacts induced by GAN. However, AI-driven defense mechanisms have a long way to catch up, as seen in the related problem of defense against adversarial attacks. Recognizing these challenges, the Defense Advanced Research Projects Agency has launched the Media Forensics program to research against deep fakes. Hence, for now, the best defense against deep fakes is based on traditional cybersecurity best practices: secure all stages in the pipeline and enable strong encryption and monitoring tools.”
    The Potential Dangers of Artificial Intelligence for Radiology and Radiologists
    Linda C. Chu, MD, Anima Anandkumar, PhD, Hoo Chang Shin, PhD, Elliot K. Fishman, MD
    JACR (in press)
  • “We find that good quality AI-based support of clinical decision-making improves diagnostic accuracy over that of either AI or physicians alone, and that the least experienced clinicians gain the most from AI-based support. We further find that AI-based multiclass probabilities outperformed content-based image retrieval (CBIR) representations of AI in the mobile technology environment, and AI-based support had utility in simulations of second opinions and of telemedicine triage.”
    Human–computer collaboration for skin cancer recognition
    Philipp Tschandl et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0942-0
  • "We find that good quality AI-based support of clinical decision-making improves diagnostic accuracy over that of either AI or physicians alone, and that the least experienced clinicians gain the most from AI-based support."
    Human–computer collaboration for skin cancer recognition
    Philipp Tschandl et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0942-0
  • “In addition to demonstrating the potential benefits associated with good quality AI in the hands of non-expert clinicians, we find that faulty AI can mislead the entire spectrum of clinicians, includ- ing experts. Lastly, we show that insights derived from AI class-activation maps can inform improvements in human diagnosis. Together, our approach and findings offer a frame- work for future studies across the spectrum of image-based diagnostics to improve human–computer collaboration in clinical practice.”
    Human–computer collaboration for skin cancer recognition
    Philipp Tschandl et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0942-0
  • "This study examines human–computer collaboration from multiple angles and under varying conditions. We used the domain of skin cancer recognition for simplicity, but our study could serve as a framework for similar research in image-based diagnostic medicine. In contrast to the current narrative, our findings sug- gest that the primary focus should shift from human–computer competition to human–computer collaboration. From a regulatory perspective, the performance of AI-based systems should be tested under real-world conditions in the hands of the intended users and not as stand-alone devices. Only then can we expect to rationally adopt and improve AI-based decision support and to accelerate its evolution.”
    Human–computer collaboration for skin cancer recognition
    Philipp Tschandl et al.
    Nat Med (2020). https://doi.org/10.1038/s41591-020-0942-0

  • Human–computer collaboration for skin cancer recognition
    Philipp Tschandl et al.
    Nat Med (2020).  https://doi.org/10.1038/s41591-020-0942-0
  • Background: IBM Watson for Oncology (WFO) is a cognitive computing system helping physicians quickly identify key information in a patient’s medical record, surface relevant evidence, and explore treatment options. This study assessed the possibility of using WFO for clinical treatment in lung cancer patients.
    Methods: We evaluated the level of agreement between WFO and multidisciplinary team (MDT) for lung cancer. From January to December 2018, newly diagnosed lung cancer cases in Chonnam National University Hwasun Hospital were retrospectively examined using WFO version 18.4 according to four treatment categories (surgery, radiotherapy, chemoradiotherapy, and palliative care). Treatment recommendations were considered concordant if the MDT recommendations were designated ‘recommended’ by WFO. Concordance between MDT and WFO was analyzed by Cohen’s kappa value.
    Artificial intelligence and lung cancer treatment decision: agreement with recommendation of multidisciplinary tumor board
    Min-Seok Kim et al.
    Transl Lung Cancer Res 2020;9(3):507-514
  • Results: In total, 405 (male 340, female 65) cases with different histology (adenocarcinoma 157, squamous cell carcinoma 132, small cell carcinoma 94, others 22 cases) were enrolled. Concordance between MDT and WFO occurred in 92.4% (k=0.881, P<0.001) of all cases, and concordance differed according to clinical stages. The strength of agreement was very good in stage IV non-small cell lung carcinoma (NSCLC) (100%, k=1.000) and extensive disease small cell lung carcinoma (SCLC) (100%, k=1.000). In stage I NSCLC, the agreement strength was good (92.4%, k=0.855). The concordance was moderate in stage III NSCLC (80.8%, k=0.622) and relatively low in stage II NSCLC (83.3%, k=0.556) and limited disease SCLC (84.6%, k=0.435). There were discordant cases in surgery (7/57, 12.3%), radiotherapy (2/12, 16.7%), and chemoradiotherapy (15/129, 11.6%), but no discordance in metastatic disease patients.
    Conclusions: Treatment recommendations made by WFO and MDT were highly concordant for lung cancer cases especially in metastatic stage. However, WFO was just an assisting tool in stage I–III NSCLC and limited disease SCLC; so, patient-doctor relationship and shared decision making may be more important in this stage..
    Artificial intelligence and lung cancer treatment decision: agreement with recommendation of multidisciplinary tumor board
    Min-Seok Kim et al.
    Transl Lung Cancer Res 2020;9(3):507-514
  • Methods: We evaluated the level of agreement between WFO and multidisciplinary team (MDT) for lung cancer. From January to December 2018, newly diagnosed lung cancer cases in Chonnam National University Hwasun Hospital were retrospectively examined using WFO version 18.4 according to four treatment categories (surgery, radiotherapy, chemoradiotherapy, and palliative care). Treatment recommendations were considered concordant if the MDT recommendations were designated ‘recommended’ by WFO. Concordance between MDT and WFO was analyzed by Cohen’s kappa value.
    Conclusions: Treatment recommendations made by WFO and MDT were highly concordant for lung cancer cases especially in metastatic stage. However, WFO was just an assisting tool in stage I–III NSCLC and limited disease SCLC; so, patient-doctor relationship and shared decision making may be more important in this stage..
    Artificial intelligence and lung cancer treatment decision: agreement with recommendation of multidisciplinary tumor board
    Min-Seok Kim et al.
    Transl Lung Cancer Res 2020;9(3):507-514
  • “In conclusion, treatment decisions made by WFO exhibited a high degree of agreement with those of the MDT tumor board, and the concordance varied by stage. AI-based CDSS is expected to play an assistive role, particularly in the metastatic lung cancer stage with less complex treatment options. However, patient-doctor relationships and shared decision making may be more important in non-metastatic lung cancer because of the complexity to reach at an appropriate decision. Further study is warranted to overcome this gray area for current machine learning algorithms.”
    Artificial intelligence and lung cancer treatment decision: agreement with recommendation of multidisciplinary tumor board
    Min-Seok Kim et al.
    Transl Lung Cancer Res 2020;9(3):507-514
  • Purpose: The purpose of this study is to evaluate diagnostic performance of a commercially available radiomics research prototype vs. an in-house radiomics software in the binary classification of CT images from patients with pancreatic ductal adenocarcinoma (PDAC) vs. healthy controls.
    Results: When 40 radiomics features were used in the random forest classification, in-house software achieved superior sensitivity (1.00) and accuracy (0.992) compared to the commercially available research prototype (sensitivity = 0.950, accuracy = 0.968). When the number of features was reduced to five features, diagnostic performance of the in-house soft- ware decreased to sensitivity (0.950), specificity (0.923), and accuracy (0.936). Diagnostic performance of the commercially available research prototype was unchanged.
    Conclusion: Commercially available and in-house radiomics software achieve similar diagnostic performance, which may lower the barrier of entry for radiomics research and allow more clinician-scientists to perform radiomics research.
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology (2020) 45:2469–2475
  • “This study showed that a commercially available radiomics software may be able to achieve similar diagnostic performance as an in-house radiomics software. The results obtained from one radiomics software may be transferrable to another system. Availability of commercial radiomics software may lower the barrier of entry for radiomics research and allow more researchers to engage in this exciting area of research.”
    Diagnostic performance of commercially available vs. in‐house radiomics software in classification of CT images from patients with pancreatic ductal adenocarcinoma vs. healthy controls
    Linda C. Chu · Berkan Solmaz · Seyoun Park · Satomi Kawamoto · Alan L. Yuille · Ralph H. Hruban · Elliot K. Fishman
    Abdominal Radiology (2020) 45:2469–2475
Incidentaloma

  • Revised in 2020 (from 2013)
  • “Incidental adnexal findings are commonly identified in women on CT and MR studies that include the pelvis. Normal physiologic changes in premenopausal women include monthly development of a dominant follicle and subsequent corpus luteum, resulting in a potential incidental CT or MR finding in many premenopausal women. Nonneoplastic cysts that may wax and wane in size are also common in postmenopausal women; in a large series of postmenopausal women, 14% had cysts on an initial ultrasound examination, with 32% resolving but 8% developing a new cyst at 1-year follow-up.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “An extensive body of ultrasound-based imaging literature in surgical and clinically followed cohorts shows that the risk of malignancy in simple cysts identified sonographically is negligible in both premenopausal and postmenopausal women, a conclusion confirmed by recent large studies showing no increased risk of malignancy in women with sonographically identified simple adnexal cysts irrespective of cyst size.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “The revised SRU consensus recommendations have increased some size thresholds for surveillance, now stating that simple cysts characterized with standard ultrasound quality do not require ultrasound follow-up when 5 cm in premenopausal women and 3 cm in postmenopausal women. When there is exceptional quality and documentation that the cyst is simple, the SRU panel opines that these thresholds are justifiably increased to 7 cm in premenopausal women and 5 cm in postmenopausal women, because the risk of mischaracterization is reduced.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • The following four elements should be reported when an incidental adnexal mass is detected on CT or MRI:
    1. Mass characteristics (ie, simple-appearing cyst, features indicating a specific diagnosis, indeterminate features)
    2. Size (largest diameter)
    3. Technical considerations
    4. Known or presumed menopausal status
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “It is important that radiologists who report CT or MR studies of the pelvis be familiar with the features of adnexal masses that enable confident benign or malignant diagnosis, so that those features can be described in the reporting of these masses the risk of mischaracterization is reduced.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.

  • Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.

  • Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.

  • Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “The algorithm does not apply to any CT or MR adnexal finding that is unchanged in appearance over 2 or more years, because malignancy is effectively excluded by this stability. The algorithm is not intended for use in women at high genetic risk for ovarian cancer, in whom lower size thresholds for sonographic characterization of adnexal cysts may be justified. The algorithm is aborted when a patient develops symptoms potentially related to a mass being followed; an asymptomatic cyst may become painful because of internal hemorrhage, rupture, or torsion, with symptoms justifying immediate imaging attention.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “Baheti et al evaluated the agreement between contrast-enhanced CT and ultrasound in characterizing adnexal masses and showed that simple appearing cysts on CT correspond to simple cysts on ultrasound . A subsequent investigation also showed that simple-appearing cysts on CT had no risk of malignancy. Thus, although there is far more evidence confirming the absence of increased malignancy risk in sonographically characterized simple adnexal cysts, based on the available current evidence, it is reasonable to assume that simpleappearing cysts on CT or MR are similarly benign.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “Small, incidental, simple-appearing adnexal cysts on CT or MR do not justify sonographic characterization even when assessment is limited. Paralleling the revised SRU consensus recommendations for incidental simple cysts on ultrasound, our committee consensus uses 3 cm (postmenopausal) and 5 cm (premenopausal) as the default threshold for not pursuing follow-up of incidental simple-appearing cysts on CT or MR [7]. Because many adnexal cysts are 5 cm in premenopausal women and 3 cm in postmenopausal women, the mere existence of a small (ie, below size threshold) simple-appearing cyst with limited assessment is not enough to justify sonographic recharacterization or follow-up when it is an incidental finding. O cysts on CT or MR are similarly benign.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “When an incidental simple-appearing cyst is adequately characterized by CT or MR but justifies sonographic follow-up because of its size, the sonographic evaluation is reasonably delayed by 6 to 12 months to provide evidence regarding the cyst growth rate. By delaying the sonographic follow-up by 6 to 12 months instead of immediately recharacterizing the cyst with ultrasound, the cyst has a chance to resolve or involute, allowing for diagnosis as a nonneoplastic cyst that requires no further follow-up, or to grow, favoring a benign cystic neoplasm.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • • Incidental adnexal findings on CT and MR examinations of the female pelvis are common; we provide an algorithm to guide management of the incidental adnexal mass based on whether the mass is (1) a simple-appearing cyst; (2) has reasonably diagnostic imaging features; or (3) has an uncertain diagnosis.
    • Simple-appearing cysts on CT or MR have very low risk of malignancy. Imaging follow-up is justified only when the cyst is relatively large for the patient’s menopausal status. The primary goals of imaging follow-up are to limit the risk of cyst mischaracterization and to understand the rate of cyst growth, which may inform subsequent clinical decision making.
    • Recommendations regarding the optimal timing of sonographic follow-up for a large simple-appearing cyst balances the small potential risk of CT or MR mischaracterization against the desire to gain information about cyst growth using as few imaging studies as possible.
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • Purpose: The frequency of computed tomography (CT) imaging of trauma patients has given rise to an increase in the discovery of incidental findings. The purpose of this study was to evaluate the frequency and documentation of follow-up recommendations of incidental findings during the initial trauma evaluation. Secondarily, trauma patients with and without incidental findings were compared. We hypothesized that there would be a high rate of incidental findings in trauma patients and that these findings would be poorly documented.
    Results: Of the 1573 CT scans performed, 478 (30.4%) revealed incidental findings. The abdomen/pelvis had the highest rate of incidental findings (61.7%). Of the 416 patients, 295 (70.9%) had a total of 858 incidental findings, with an average of 3 findings per patient. Follow-up was required for 24 (2.8%) incidental findings, and admission/immediate intervention was required for 6 (0.7%) findings. Only 12 (1.4%) incidental findings were documented in the discharge note. Increasing age (p < 0.001), a higher body mass index (BMI) (p = 0.015), and receiving a pan-CT (p < 0.001) increased the odds of having an incidental finding.
    Incidental findings in blunt trauma patients: prevalence, follow-up documentation, and risk factors. 
    James MK et al.
    Emerg Radiol. 2017;24(4):347-353
  • Aim: Whole-body computed tomography (CT) for trauma occasionally reveals significant incidental findings not related to trauma, which require an adequate response. In this study, we examined the current state of incidental findings in trauma patients on whole-body CT and the effects of the feedback system.
    Results: During the study period, whole-body CT revealed incidental findings in 79 of 199 trauma patients (40.1%). The mean age of the 79 patients with incidental findings was 62.8 ± 19.5 years, and the mean injury severity score was 16.6 ± 10.0. No difference was observed in the severity of trauma, age, or length of hospital stay. The incidental findings were related to the liver/gallbladder in 22 patients, kidneys in 17, lungs in 14, and the intracranial area in 13. The recognition rate of incidental findings after the implementation of the feedback system increased from 23.3% to 32.6%.
    Incidental findings on whole-body computed tomography in trauma patients: the current state of incidental findings and the effect of implementation of a feedback system. 
    Kumada K et al.
    Acute Med Surg. 2019;6(3):274-278.
  • “Although CT is not considered the examination of choice for the detection and characterisation of adnexal diseases, adnexal masses may be incidentally detected during CT examination performed for other clinical indications. Most adnexal incidentalomas are benign, and therefore may not require further investigation, follow-up or intervention; however, few of them may prove malignant. Multidetector CT has improved the diagnostic performance of the technique in the detection and differentiation of adnexal mass lesions. Radiologists should be able to recognise the normal CT appearance of the ovaries and the CT characteristics of various adnexal incidentalomas. This may obviate unnecessary imaging evaluation and allow optimal treatment planning. Regarding the management of adnexal lesions incidentally found on CT, recommendations based on the collective experience of the members of the American College of Radiology Incidental Findings Committee II have recently been presented.”
    Adnexal incidentalomas on multidetector CT: how to manage and characterise.
    Tsili AC, Argyropoulou MI.
    Obstet Gynaecol. 2019;1-8.
Kidney

  • “Bilaterality (p < 0.0001), an extramural growth pattern (p < 0.0001), a great- er number of affected segments (p = 0.04), and a gradual dynamic enhancement pattern (p < 0.001) were significantly more frequent in patients with IgG4-related disease. With regard to extraurinary findings, paraaortic fat stranding (p = 0.03), presacral fat stranding (p < 0.001), fat stranding of the pelvic walls (p < 0.001), and aortic involvement (p < 0.001) were seen more frequently in patients with IgG4-related disease; on the other hand, there was no statistically significant difference in terms of frequency of pancreatic involvement. Hydronephrosis and renal involvement were seen more frequently in patients with urothelial carcinoma, although the difference was not statistically significant.”
    CT Findings of Upper Urinary Tract Lesions in IgG4-Related Disease: Comparison With Urothelial Carcinoma
    Kamo M et al.
    AJR 2020; 215:406–412
  • "CT findings suggestive of IgG4-related upper urinary tract lesions in comparison with urothelial carcinoma are bilateral and have a longer urinary tract involve- ment and exhibit an extramural growth pattern, ill-defined margins, a gradual enhancement pattern, aortic involvement, and fat stranding in the paraaortic, presacral, or pelvic wall areas.”
    CT Findings of Upper Urinary Tract Lesions in IgG4-Related Disease: Comparison With Urothelial Carcinoma
    Kamo M et al.
    AJR 2020; 215:406–412
  • "In this study, findings of bilateral involvement and longer urinary tract involvement, extramural growth pattern, ill-defined margins, and gradual enhancement pattern in the dynamic CT study were more suggestive of IgG4-related upper urinary tract lesions than they were of urothelial carcinoma. Furthermore, extraurinary findings such as fat stranding in the paraaortic space, presacral space, and pelvic wall were identified as CT findings suggestive of IgG4-related disease.”
    CT Findings of Upper Urinary Tract Lesions in IgG4-Related Disease: Comparison With Urothelial Carcinoma
    Kamo M et al.
    AJR 2020; 215:406–412
  • “CT findings suggestive of IgG4-related upper urinary tract lesions in comparison with urothelial carcinoma are bilateral and have longer urinary tract involvement; extramural growth pattern; ill-defined margins; a grad- ual enhancement pattern in the dynamic CT study; aortic involvement; and fat stranding in the paraaortic space, presacral space, or pelvic wall areas. IgG4-related disease can also manifest as unilateral lesions, which could appear similar to those of urothelial carcinoma and be difficult to differentiate."
    CT Findings of Upper Urinary Tract Lesions in IgG4-Related Disease: Comparison With Urothelial Carcinoma
    Kamo M et al.
    AJR 2020; 215:406–412
OB GYN

  • “Although CT is not considered the examination of choice for the detection and characterisation of adnexal diseases, adnexal masses may be incidentally detected during CT examination performed for other clinical indications. Most adnexal incidentalomas are benign, and therefore may not require further investigation, follow-up or intervention; however, few of them may prove malignant. Multidetector CT has improved the diagnostic performance of the technique in the detection and differentiation of adnexal mass lesions. Radiologists should be able to recognise the normal CT appearance of the ovaries and the CT characteristics of various adnexal incidentalomas. This may obviate unnecessary imaging evaluation and allow optimal treatment planning. Regarding the management of adnexal lesions incidentally found on CT, recommendations based on the collective experience of the members of the American College of Radiology Incidental Findings Committee II have recently been presented.”
    Adnexal incidentalomas on multidetector CT: how to manage and characterise.
    Tsili AC, Argyropoulou MI.
    Obstet Gynaecol. 2019;1-8.
  • Revised in 2020 (from 2013)
  • “Incidental adnexal findings are commonly identified in women on CT and MR studies that include the pelvis. Normal physiologic changes in premenopausal women include monthly development of a dominant follicle and subsequent corpus luteum, resulting in a potential incidental CT or MR finding in many premenopausal women. Nonneoplastic cysts that may wax and wane in size are also common in postmenopausal women; in a large series of postmenopausal women, 14% had cysts on an initial ultrasound examination, with 32% resolving but 8% developing a new cyst at 1-year follow-up.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “An extensive body of ultrasound-based imaging literature in surgical and clinically followed cohorts shows that the risk of malignancy in simple cysts identified sonographically is negligible in both premenopausal and postmenopausal women, a conclusion confirmed by recent large studies showing no increased risk of malignancy in women with sonographically identified simple adnexal cysts irrespective of cyst size.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “The revised SRU consensus recommendations have increased some size thresholds for surveillance, now stating that simple cysts characterized with standard ultrasound quality do not require ultrasound follow-up when 5 cm in premenopausal women and 3 cm in postmenopausal women [7]. When there is exceptional quality and documentation that the cyst is simple, the SRU panel opines that these thresholds are justifiably increased to 7 cm in premenopausal women and 5 cm in postmenopausal women, because the risk of mischaracterization is reduced.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • The following four elements should be reported when an incidental adnexal mass is detected on CT or MRI:
    1. Mass characteristics (ie, simple-appearing cyst, features indicating a specific diagnosis, indeterminate features)
    2. Size (largest diameter)
    3. Technical considerations
    4. Known or presumed menopausal status
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “It is important that radiologists who report CT or MR studies of the pelvis be familiar with the features of adnexal masses that enable confident benign or malignant diagnosis, so that those features can be described in the reporting of these masses the risk of mischaracterization is reduced.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.

  • Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.

  • Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.

  • Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “The algorithm does not apply to any CT or MR adnexal finding that is unchanged in appearance over 2 or more years, because malignancy is effectively excluded by this stability. The algorithm is not intended for use in women at high genetic risk for ovarian cancer, in whom lower size thresholds for sonographic characterization of adnexal cysts may be justified. The algorithm is aborted when a patient develops symptoms potentially related to a mass being followed; an asymptomatic cyst may become painful because of internal hemorrhage, rupture, or torsion, with symptoms justifying immediate imaging attention.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “Baheti et al evaluated the agreement between contrast-enhanced CT and ultrasound in characterizing adnexal masses and showed that simple appearing cysts on CT correspond to simple cysts on ultrasound . A subsequent investigation also showed that simple-appearing cysts on CT had no risk of malignancy. Thus, although there is far more evidence confirming the absence of increased malignancy risk in sonographically characterized simple adnexal cysts, based on the available current evidence, it is reasonable to assume that simpleappearing cysts on CT or MR are similarly benign.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “Small, incidental, simple-appearing adnexal cysts on CT or MR do not justify sonographic characterization even when assessment is limited. Paralleling the revised SRU consensus recommendations for incidental simple cysts on ultrasound, our committee consensus uses 3 cm (postmenopausal) and 5 cm (premenopausal) as the default threshold for not pursuing follow-up of incidental simple-appearing cysts on CT or MR [7]. Because many adnexal cysts are 5 cm in premenopausal women and 3 cm in postmenopausal women, the mere existence of a small (ie, below size threshold) simple-appearing cyst with limited assessment is not enough to justify sonographic recharacterization or follow-up when it is an incidental finding. O cysts on CT or MR are similarly benign.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • “When an incidental simple-appearing cyst is adequately characterized by CT or MR but justifies sonographic follow-up because of its size, the sonographic evaluation is reasonably delayed by 6 to 12 months to provide evidence regarding the cyst growth rate. By delaying the sonographic follow-up by 6 to 12 months instead of immediately recharacterizing the cyst with ultrasound, the cyst has a chance to resolve or involute, allowing for diagnosis as a nonneoplastic cyst that requires no further follow-up, or to grow, favoring a benign cystic neoplasm.”
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
  • • Incidental adnexal findings on CT and MR examinations of the female pelvis are common; we provide an algorithm to guide management of the incidental adnexal mass based on whether the mass is (1) a simple-appearing cyst; (2) has reasonably diagnostic imaging features; or (3) has an uncertain diagnosis.
    • Simple-appearing cysts on CT or MR have very low risk of malignancy. Imaging follow-up is justified only when the cyst is relatively large for the patient’s menopausal status. The primary goals of imaging follow-up are to limit the risk of cyst mischaracterization and to understand the rate of cyst growth, which may inform subsequent clinical decision making.
    • Recommendations regarding the optimal timing of sonographic follow-up for a large simple-appearing cyst balances the small potential risk of CT or MR mischaracterization against the desire to gain information about cyst growth using as few imaging studies as possible.
    Management of Incidental Adnexal Findings on CT and MRI: A White Paper of the ACR Incidental Findings Committee
    Patel MD et al.
    J Am Coll Radiol 2020;17:248-254.
Pancreas

  • Purpose: The imaging features of serous cystadenomas (SCAs) overlap with those of mucinous cystic neoplasms (MCNs) and branch duct intraductal papillary mucinous neoplasms (BD-IPMNs), and an accurate preoperative diagnosis is important for clinical treatment due to their different biological behaviors. The aim of this study was to provide a computed tomographic (CT) feature for the diagnosis of SCAs and estimate whether the “circumvascular sign” can contribute to the discrimination of SCAs from MCNs and BD-IPMNs.
    Conclusion: Pancreatic cystic neoplasms that show central scarring, central calcification or the circumvascular sign on CT could be diagnosed as SCAs. When either of the first two features is combined with the circumvascular sign, the diagnostic sensitivity could be increased.
    Discrimination of serous cystadenoma from mucinous cystic neoplasm and branch duct intraductal papillary mucinous neoplasm in the pancreas with CT
    Guang‐xian Wang et al.
    Abdominal Radiology (2020) 45:2772–2778
  • “The “circumvascular sign” was defined as the presence of some abnormal arteries surrounding the lesion on arterial phase CT. In addition, tumor size, tumor patterns, and degree of enhancement were also recorded.”
    Discrimination of serous cystadenoma from mucinous cystic neoplasm and branch duct intraductal papillary mucinous neoplasm in the pancreas with CT
    Guang‐xian Wang et al.
    Abdominal Radiology (2020) 45:2772–2778
  • “The central scarring, central calcification and circumvas- cular sign had high specificities, 97.7%, 100% and 100%, respectively. However, the sensitivities of central scarring and central calcification were low, 36.7% and 23.3%, respec- tively. Only the circumvascular sign had moderate sensitivity (76.7%). Combining the circumvascular sign with either of the other features increased the sensitivity for the diagnosis of SCAs to 83.3%.”
    Discrimination of serous cystadenoma from mucinous cystic neoplasm and branch duct intraductal papillary mucinous neoplasm in the pancreas with CT
    Guang‐xian Wang et al.
    Abdominal Radiology (2020) 45:2772–2778
  • "In conclusion, this study showed that central scarring, central calcification and the circumvascular sign were able to distinguish SCAs from MCNs and BP-IPMNs. When either central scarring or central calcification was combined with the circumvascular sign, the sensitivity for the diagnosis of SCAs increased. The circumvascular sign may be a novel diagnostic and differential diagnostic sign for SCAs.”
    Discrimination of serous cystadenoma from mucinous cystic neoplasm and branch duct intraductal papillary mucinous neoplasm in the pancreas with CT
    Guang‐xian Wang et al.
    Abdominal Radiology (2020) 45:2772–2778
  • Errors in the Diagnosis of Pancreatic Cancer
    - Small tumor size
    - Tumor is isodense to the pancreas
    - Missed pancreatic duct cutoff sign
    - Underlying chronic pancreatitis
  • Errors in the Diagnosis of Pancreatic Cancer
    - Confusion of duodenal mass as pancreatic mass (GIST, Adenocarcinoma, Carcinoid)
    - Adenopathy especially portocaval nodes (lymphoma)
    - Adrenal or retroperitoneal mass near pancreas
    - Metastases to the pancreas (kidney, lung, breast primary)
    - Autoimmune pancreatitis (false positive)
  • “Missed imaging diagnosis of PDAC can be minimized by increasing awareness of the secondary signs identified in subtle or isoattenuating tumors, prompting further diagnostic workup rather than follow-up imaging. Uncinate process PDAC can be easily missed at its early stage due to the lack of pancreatic and bile duct dilatation. By using different imaging modalities the radiologists can play a pivotal role in determining tumor resectability, aiding proper surgical planning and evaluating tumor response to treatment. It is also important for the radiologist to know the mimics of PDAC to avoid unnecessary surgery for benign entities such as focal fat infiltration, autoimmune, and groove pancreatitis, and to arrange for proper treatments in malignant tumors such as PNET, lymphoma, and metastasis.”
    Imaging diagnosis and staging of pancreatic ductal adenocarcinoma: a comprehensive review
    Khaled Y. Elbanna , Hyun-Jung Jang and Tae Kyoung Kim
    Insights into Imaging (2020) 11:58
  • Key Points
    Question:  Is there an association of diabetes duration and recent weight loss with subsequent risk of pancreatic cancer?
    Findings:  In this cohort study of 112 818 women and 46 207 men enrolled in 2 US cohort studies, participants with recent-onset diabetes accompanied by weight loss of 1 to 8 lb or more than 8 lb had a substantially increased risk for pancreatic cancer compared with participants with no such exposure.
    Meaning:  The findings from this study suggest that individuals with recent-onset diabetes accompanied by weight loss have a high risk for developing pancreatic cancer and may be a group for whom early detection strategies would be advantageous.
    Diabetes, Weight Change, and Pancreatic Cancer Risk.
    Yuan C, Babic A, Khalaf N, et al.
    JAMA Oncol. Published online August 13, 2020. doi:10.1001/jamaoncol.2020.2948
  • "Metastases to the pancreas are most commonly from cancers of the kidney, lung, breast and colorectal, and from melanoma. Overall, 15–44% of pancreatic metastases have a diffuse morphological pattern. The appearance of pancreatic metastases can be similar to primary PDAC on MDCT. Pancreatic metastases often show peripheral or homogeneous (less common) enhancement; while PDACs are generally hypoattenuating lesions.”
    Pitfalls in the MDCT of pancreatic cancer: strategies for minimizing errors.
    Abdom Radiol 45, 457–478 (2020).
    Haj-Mirzaian A, Kawamoto S, Zaheer A, Hruban RH, Fishman EK, Chu LC.
  • Errors in the Diagnosis of Pancreatic Cancer
    - Poor CT scan acquisition protocol (poor injection, non-contrast CT, poor timing of acquisition)
    - Poor CT scan parameters (thick sections, single phase acquisition, poor timing of acquisition)
  • "In pancreatic lymphoma, mild common bile duct dilatation is more common than is main pancreatic duct dilatation. Enlarged lymph nodes, infiltration to retroperitoneal or abdominal organs, and invasive tumor growth with loss of anatomic boundaries are also more commonly seen in lymphoma. Also, vascular invasion, tumor calcification, and necrosis are less common in pancreatic lymphoma than in PDAC. Considering the better prognosis of pancreatic lymphoma and availability of chemotherapy as an effective treatment, the accurate diagnosis of lymphoma and distinguishing it from PDAC is critical.”
    Pitfalls in the MDCT of pancreatic cancer: strategies for minimizing errors.
    Abdom Radiol 45, 457–478 (2020).
    Haj-Mirzaian A, Kawamoto S, Zaheer A, Hruban RH, Fishman EK, Chu LC.
  • “Recent improvements in multimodality care have substantially improved overall survival, local control, and metastasis-free survival for patients who have localized tumors that are amenable to surgical resection. The widening gap in prognosis between patients with resectable and unresectable or metastatic disease reinforces the importance of detecting pancreatic cancer sooner to improve outcomes. Furthermore, the developing use of therapies that target tumor-specific molecular vulnerabilities may offer improved disease control for patients with advanced disease.”
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.
  • “Although most patients are symptomatic at presentation, symptoms of PDAC are often nonspecific,leading to a median delay between presentation and diagnosis of >2 months. The most commonly reported symptoms are fatigue (86%), weight loss (85%), anorexia (83%), jaundice (56%), nausea (51%), abdominal pain (79%), diarrhea (44%), pruritis (32%), and steatorrhea (25%). Clinical signs of PDAC, including jaundice (55%), hepatomegaly (29%), cachexia (13%), epigastric mass (9%), or ascites (5%), are much less common.”
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.
  • “Approximately 10% of patients with PDAC harbor a pathogenic germline mutation in a cancer-predisposing gene, of which BRCA2 and ATM are the 2 most common candidates, followed by BRCA1, PALB2, CDKN2A/p16, and LKB1/STK11; the mismatch repair genes (hMLH1, hMSH2, and hPMS6); and other rarer variants (Table 1). Of note, only one-half of patients with a deleterious germline mu- tation report an overt family history of PDAC, in light of which the American Society of Clinical Oncology (ASCO) and the National Comprehensive Cancer Network (NCCN) recently updated their guidelines to recommend universal germline mutation testing for all patients diagnosed with PDAC (instead of only those with a suspicious family history).”
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.

  • Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.

  • Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.
  • “Approximately 10% of patients with PDAC harbor a pathogenic germline mutation in a cancer-predisposing gene, of which BRCA2 and ATM are the 2 most common candidates, followed by BRCA1, PALB2, CDKN2A/p16, and LKB1/STK11; the mismatch repair genes (hMLH1, hMSH2, and hPMS6); and other rarer variants (Table 1). Of note, only one-half of patients with a deleterious germline mu- tation report an overt family history of PDAC, in light of which the American Society of Clinical Oncology (ASCO) and the National Comprehensive Cancer Network (NCCN) recently updated their guidelines to recommend universal germline mutation testing for all patients diagnosed with PDAC (instead of only those with a suspicious family history).”
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.
  • “Serum CA 19-9 levels are closely related to tumor size, and the degree of elevation in CA 19-9 is associated with prognosis.87 In a study of patients with apparently localized disease, values >130 units/mL predicted occult, unresectable disease and were prognos-tic for survival among >1500 patients with resectable cancers.90,91 Although patients with apparently localized PDAC and high levels of CA 19-9 are commonly recommended for staging laparoscopy and neoadjuvant therapy, ASCO guidelines do not specify a cutoff value of CA 19-9 to be used in this manner.92 Because elevations in serum CA 19-9 can be induced by either tumor production or cholestasis, CA 19-9 should be remeasured after stent placement in patients with biliary obstruction to estimate true tumor burden, accounting for its 4-day to 8-day half-life.”
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.
  • “A failure in CA 19-9 normalization after surgery is associ- ated with poor survival and is thought to represent occult metastatic disease. Similarly, declining CA 19-9 during systemic therapy correlates with improved patient survival, although it is unclear what magnitude of decline is most prognostic. Rises in CA 19-9 after a nadir can represent treatment failure and often precede imaging evidence of re- current or progressive cancer.99 Serum CA 19-9 changes are not considered to be a substitute for imaging evidence of treatment response or recurrence. In some tumors, additional cancer-specific biomarkers. "
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.
  • "The reported accuracy in determining tumor resectability ranges from 73% to 87% for CT and from 70% to 79% for MRI.103 CT offers superior spatial resolution and is less sus- ceptible to respiratory motion artifacts than MRI, which is essential in demonstrating the critical relationship between the tumor and adjacent vasculature. The accuracy of PDAC detection and staging critically depends on the appropriate imaging protocol, postprocessing technique, and experience of radiologists.”
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.

  • Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.

  • Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.

  • Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886

  • Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • “The AI-driven diagnostic software has the potential to trans- form early detection of pancreatic cancer by improving accuracy and consistency of interpretation of radiologic imaging scans and related patient data. The development of reproducible AI systems requires access to current, large, diverse, and multisite data sets, which are subject to numerous data sharing limitations. Fu- ture efforts are likely to involve alternative data sharing solutions to enable the development of both public and private AI-ready data resources. Early detection of pancreatic cancer represents an attractive AI use case, well matched to benefit from the MTD challenge approach. This approach will significantly expand the use of sensitive data to improve early detection of pancreatic cancer and lay the foundation for the development of federated architectures for real-world medical data in general.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • “PDAC is the most common pancreatic malig- nancy, accounting for more than 85% of pancreatic tumors. It is typically a disease of elderly patients, with a mean age at presentation of 68 years and a male-to-female ratio of 1.6:1. After colorectal cancer, it is the second most common cancer of the digestive system in the United States, and its incidence is rising sharply.The development of pancreatic cancer is strongly related to smoking, family history, obesity, long-standing diabetes, and chronic pancreatitis. Early stages of PDAC are clinically silent. Abdominal pain is the most frequently reported clinical symptom, even when the tumor is small (<2 cm).”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • “Pancreatic cancer continues to be one of the deadliest malignancies and is the third leading cause of cancer-related mortality in the United States. Based on several models, it is projected to become the second leading cause of cancer-related deaths by 2030. Although the overall survival rate for patients diagnosed with pancreatic cancer is less than 10%, survival rates are increasing in those whose cancers are detected at an early stage, when intervention is possible. There are, however, no reli- able biomarkers or imaging technology that can detect early-stage pancreatic cancer or accurately identify precursors that are likely to progress to malignancy.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • "The challenge now is to develop imaging biomarkers and models that can further improve sensitivity for the detection of early-stage PDACs and aggressive neoplasms while mitigating diagnostic uncertainty in evaluation of premalignant abnormalities. Augmented reality, artificial intelligence (AI), and related computa- tional techniques can uncover these subtle patterns, improve image interpretation, and streamline diagnostic workflows.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • "Currently, identification of localized pancreatic cancer is mostly incidental as localized pancreatic cancer is asymptomatic. What is urgently needed are minimally invasive screening strategies with a high clinical sensitivity and specificity to identity early-stage cancer and improve these grim statistics. To this end, it is particularly important to develop tests that have high specificity because a false-positive test may trigger unnecessary invasive procedures, which add their own risk of morbidity and mortality.”
    Prediagnostic Image Data, Artificial Intelligence, and Pancreatic Cancer A Tell-Tale Sign to Early Detection
    Matthew R. Young et al.
    Pancreas 2020;49: 882–886
  • There are many challenges that need to be mitigated in the development of an image repository to enable AI system development. These include the following:
    (1) What are the requirements for defining image annotation? 
    (2) What are the main concerns with depositing patient imaging data?
    (3) What are the definitions of an AI-specific clinical use cases?
    (4) What are the benefits and drawbacks of alternative data sharing in facilitating AI development?
  • "Little is known about the other histologic subtypes of PDAC, mainly because of their rarity and lack of specific patterns of disease manifestation. According to the World Health Organization, these variants include adenosquamous carcinoma, colloid carcinoma, hepatoid carcinoma, medullary carcinoma, signet ring cell carcinoma, undifferentiated carcinoma with osteoclast-like giant cells, and undifferentiated carcinoma. Depending on the subtype, they can confer a better or even worse prognosis than that of conventional PDAC.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "The pathogenesis of PDAC follows a series of stepwise mutations from normal pancreatic tissue that first forms a precursor lesion and eventually mutates to an invasive malignancy (15).The most common neoplastic precursor lesions of PDAC are pancreatic intraepithelial neoplasms, which are microscopic tumors (<5 mm) that are not directly visible at pancreatic imaging (16). Less frequently, PDAC can evolve from intraductal papillary mucinous neoplasms (IPMNs) and mucinous cystic neoplasms.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • “Adenosquamous carcinoma (ASqC) of the pancreas is a malignant epithelial neoplasm, which is defined at pathologic examination as a mixed tumor with ductal and squamous differentiation, with at least a 30% squamous component. ASqC is a rare and still poorly understood variant of PDAC that accounts for only 1%–4% of exocrine pancreatic malignancies.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "The imaging features of ASqC tumors correlate with the pathologic features and are usually seen as large round lobulated masses with extensive central necrosis and progressive enhancement of the fibrous capsule. The presence of extensive central tumor necrosis was suggested by several reports to be a characteristic imaging feature.The pronounced peripheral enhancement, mostly described as ring enhancement, is gradual progressive enhancement, presumably reflective of progressive accumulation of contrast material in the interstitial space of the fibrous tissue.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "Colloid carcinoma of the pancreas is characterized by mucin-producing neoplastic ductal epithelial cells dispersed in an accumulation of extracellular mucin. According to the definition by the WHO, the mucinous component should comprise at least 50% of the tumor. Colloid carcinoma accounts for only 1%–3% of all exocrine pancreatic malignancies and has a patient age and sex distribution similar to those of PDAC.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "Although colloid carcinomas are not true cystic tumors, the abundant mucin production leads to a cystic appearance at imaging.There- fore, these tumors can be confused with mainly cystic tumors, such as IPMNs or mucinous cystic adenocarcinomas. At imaging, colloid carcinomas manifest with a lobulated contour and indiscrete margins.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "Hepatoid carcinoma (HC) of the pancreas is a primary extrahepatic epithelial malignancy that re- sembles hepatocellular carcinoma (HCC) in terms of morphologic and immunohistochemical properties. On histological specimens, HC is heterogeneous, showing either pure hepatoid differentiation or areas more common to pancreatic neoplasms such as PDAC or neuroendocrine tumors.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "Medullary carcinoma of the pancreas (MCP) is characterized by a syncytial growth pattern of poorly differentiated highly pleomorphic cells that are accompanied by extensive necrosis. The tumor displays a lymphocytic reaction and clearly defined borders. Microsatellite instability (MSI+) is apparent with polymerase chain reaction. On the basis of our experience, MCP manifests at imaging as a well-circumscribed mass with central hypoenhancement at contrast-enhanced CT, corresponding to hyperintensity with a hypointense rim at T2-weighted MRI.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • "Undifferentiated carcinoma with osteoclast-like giant cells (UCOGC) of the pancreas is a malignant epithelial neoplasm of the pancreas and a histologic variant of PDAC. Histopathologic evaluation reveals at least two distinct but intermixed cell populations: pleomorphic neoplastic mononuclear cells and large nonneoplastic multinucleated osteoclast- like giant cells. Focal intratumoral osteoid formation may be associated.”
    Pancreatic Ductal Adenocarcinoma and Its Variants: Pearls and Perils
    Schawkat K et al.
    RadioGraphics 2020; 40:0000–0000
  • “NCCN guidelines classify the resectability of localized PDAC based on preoperative imaging findings into resect- able, borderline resectable, and locally advanced disease and are summarized in Table 3. Arterial abutment (<180 degrees) is considered borderline resectable, whereas arterial encasement (≥180 degrees) is usually considered locally advanced (exception noted below) . Venous abutment, encasement, or thrombosis are considered borderline resectable, as long as the venous segment is reconstructable. Unreconstructable venous involvement is considered locally advanced.102 NCCN guidelines share many common fea- tures with other guidelines (Table 4), with the no- table exception of celiac artery encasement (>180 degrees).”
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.
  • "Despite being relatively uncommon, PDAC is expected to become the second leading cause of cancer death by the end of the decade.The vast majority of patients diagnosed with PDAC in 2020 will die of the disease. On the other hand, 5-year survival among all patients has eclipsed double digits for the first time. Led by improvements in the effectiveness of systemic therapy, an increase in the proportion of patients with early-stage disease, and stage-specific treatment paradigms, a true separation in expected survival is widening between patients with resectable cancer and those with locally advanced or metastatic disease.”
    Multidisciplinary Standards of Care and Recent Progress in Pancreatic Ductal Adenocarcinoma
    Aaron J. Grossberg, Linda C. Chu, Christopher R. Deig, Elliot K. Fishman, et al.
    CA Cancer J Clin. 2020 Jul 19. doi: 10.3322/caac.21626.
  • "Interpretation of images can be challenging due to intrinsic tumor features (including small and isoenhancing masses, exophytic masses, subtle pancreatic duct irregularities, and diffuse tumor infiltration), presence of coexisting pathology (including chronic pancreatitis and intraductal papillary mucinous neoplasm), mimickers of PDAC (including focal fatty infiltration and focal pancreatitis), distracting findings, and satisfaction of search. Awareness of pitfalls associated with the diagnosis of PDAC along with the strategies to avoid them will help radiologists to minimize technical and interpretation errors. Cognizance and mitigation of these errors can lead to earlier PDAC diagnosis and ultimately improve patient prognosis.”
    Pitfalls in the MDCT of pancreatic cancer: strategies for minimizing errors.
    Abdom Radiol 45, 457–478 (2020).
    Haj-Mirzaian A, Kawamoto S, Zaheer A, Hruban RH, Fishman EK, Chu LC.
  • “Pancreatic cancer has been associated with the development of diabetes within 4 years before the cancer diagnosis in up to 20% of patients.In the present study, recent-onset diabetes was associated with a 3-fold higher adjusted risk of pancreatic cancer and a 0.29% pancreatic cancer risk at 4 years, which was consistent with findings in previous studies evaluating physician-diagnosed diabetes.”
    Diabetes, Weight Change, and Pancreatic Cancer Risk. 
    Yuan C, Babic A, Khalaf N, et al.
    JAMA Oncol. Published online August 13, 2020. doi:10.1001/jamaoncol.2020.2948
  • "In this study, recent-onset diabetes accompanied by weight loss was associated with a substantial increase in risk for pancreatic cancer and may represent a high-risk group in the general population for whom early detection strategies would be advantageous. Further elevation of risk was seen in individuals with older age, previous healthy weight, and no intentional weight loss.”
    Diabetes, Weight Change, and Pancreatic Cancer Risk.
    Yuan C, Babic A, Khalaf N, et al.
    JAMA Oncol. Published online August 13, 2020. doi:10.1001/jamaoncol.2020.2948 
Practice Management

  • “So what is on the forefront of technological advancement for the home consumer? Health and wellness. The current paradigm of health care delivery is akin to driving a car on a given day and looking at the dash- board information, which is then blacked out for the rest of the year. A once-a-year physical examination with parameters from a single time point is very similar and leaves you with only a brief snapshot of a person’s health. In the future, your smart home will serve as a 24-hour health monitor. The home thermostat will sense changes in your temperature, lights will monitor your movement, and toilets will test for early cancers via urine or stool samples.”
    The Next Topic for Digital Tech Publishing—Your Health and Wellness
    Mark Larkin, Elliot K. Fishman, Pamela T. Johnson
    J Am Coll Radiol 2020 Aug;17(8):1071-1072
  • “As 5G networks facilitate streaming of large volumes of data without latency, home health and wellness monitors will create a paradigm shift in disease diagnosis and management. The relative effectiveness of early disease diagnosis and monitoring made possible by annual visits or even more frequent regular visits to a physician’s office pales in comparison with the potential to improve health and wellness that constant monitoring by smart devices will provide. Determining how to accurately and efficiently analyze these massive data represents the next big implementation hurdle.”
    The Next Topic for Digital Tech Publishing—Your Health and Wellness
    Mark Larkin, Elliot K. Fishman, Pamela T. Johnson
    J Am Coll Radiol 2020 Aug;17(8):1071-1072
  • "The advantage of constant monitoring is the ability to detect early changes, be they blood values, cardiac function including arrhythmia, or even just heart rate. Of course, these new developments must meet our standards by being transparent, intuitive, intimate, and con- stant. With the development of these changes, the entire health care system will undergo nothing short of a revo- lution. When one observes the health care environment and thinks about the classic companies involved, it is clear why newer players such as Amazon, Apple, Google, and Berkshire Hathaway are being looked at for developing new technology and methods of care.”
    The Next Topic for Digital Tech Publishing—Your Health and Wellness
    Mark Larkin, Elliot K. Fishman, Pamela T. Johnson
    J Am Coll Radiol 2020 Aug;17(8):1071-1072
  • "Nevertheless, technological changes—particularly 5G networks, natural language processing, and artificial intelligence—provide what may be new opportunities for seamless integration of data and the improvement of care without disturbing or interrupting the patient’s daily life. When we are able to match the needs of patients with technology, then we can truly change the face of medicine for the better. Simply acquiring data or being intrusive will not be of value. And of course, successful solutions will need to be transparent, intuitive, intimate, and constant.”
    The Next Topic for Digital Tech Publishing—Your Health and Wellness
    Mark Larkin, Elliot K. Fishman, Pamela T. Johnson
    J Am Coll Radiol 2020 Aug;17(8):1071-1072
  • “The evolving role of the patient as the primary mover in health care will be a change for radiology. A typical model was that physicians usually refer patients to specific imaging practices, but as patients become more involved as the primary mover of their health care, they will be seeking high quality at an acceptable cost. This trend was recently catalyzed by Walmart in collaboration with Covera Health. Covera has created a Radiology Centers of Excellence program, and large corporations like Walmart encourage their patients to undergo imaging in high-quality centers. The impetus for this was the recognition that low-quality imaging was precipi- tating unnecessary surgery for some patients.”
    The Next Topic for Digital Tech Publishing—Your Health and Wellness
    Mark Larkin, Elliot K. Fishman, Pamela T. Johnson
    J Am Coll Radiol 2020 Aug;17(8):1071-1072
  • “It is 2020 now, and I’m still sitting in lectures with endless slide presentations and endless bul- let points. I have a tablet sitting in front of me, and before the faculty member goes through all 10 bullet points on the slide, I have already looked at multiple imaging examples of the diagnosis being discussed on STATdx (Elsevier, Atlanta, Ga) and read about the entity in Radio- Graphics. Technology has revolutionized the way we learn, but our style of classroom teaching has not evolved to embrace it appropriately.”
    Back to the Future: Shortcomings of an Archaic Model for Radiology Lectures
    Durga Sivacharan Gaddam, Omer A. Awan
    RadioGraphics 2020; 40:1196–1197
  • "The real challenge for educators is to engage this new breed of learners who are extremely versatile at accessing the enormous amounts of information available to them instantaneously. Although it presents a challenge, this versatility can certainly be advantageous for the lecturer,as teaching material could be curated to address more complex aspects of a topic. Trainees could be relied on to be more proactive with self-learning regarding the basics. One example that comes to mind is imaging of a cholangiocarcinoma. Searching through various primary sources online would give me a plethora of images of classic-appearing cholangiocarcinomas within a few minutes. During lecture, an attending physician could address the atypical appearances of a cholangiocarcinoma from a case file that I would otherwise not have access to. This would allow the trainee to develop a deeper, complex, more practical understanding of this particular topic.”
    Back to the Future: Shortcomings of an Archaic Model for Radiology Lectures
    Durga Sivacharan Gaddam, Omer A. Awan
    RadioGraphics 2020; 40:1196–1197
  • "These are just some of the techniques that can be used to transition radiology education from passive instruction to more active learning. Iam sure that there are many additional methods being implemented that are more effective than the current slide-after-slide monotony. Perhaps a starting point could be to implement a hybrid method of teaching that involves both workstation simulation and brief slide presentations.The point is that if the purpose of a lecture is to transmit useful and practical knowledge to a learner, why do faculty continue to teach in styles that are not conducive to this fundamental goal?”
    Back to the Future: Shortcomings of an Archaic Model for Radiology Lectures
    Durga Sivacharan Gaddam, Omer A. Awan
    RadioGraphics 2020; 40:1196–1197
  • “With the ongoing fear of the pandemic, and the conflicting data regarding possible spread from surfaces, being able to have voice commands decrease risk and provides the ability to bypass common danger points from elevator buttons to door knobs to credit card processing machines. Outside of the individual, the increasing presence of voice-enabled devices affects the data-gathering and research approaches to this pandemic as well as to future public health crises. These devices can facilitate the sharing and gathering of information, provide near instantaneous updated information, and facilitate the pooling of data for use by public health experts and artificial intelligence algorithms.”
    Connecting With Patients: The Rapid Rise of Voice Right Now
    Isbitski D, Fishman EK, Rowe SP
    J Am Coll Radiol. 2020;S1546-1440(20)30666-9. [published online ahead of print, 2020 July 17].
  • "The combination of rapidly advancing voice-enabled technology and the social changes we have seen because of the coronavirus have driven the adoption of voice as a potential transformative way that patients can obtain information and communicate with their health care providers. Because of the changes that have already occurred, we can expect that we will never go back entirely to how things were and that voice will be an increasingly important influence on health care.”
    Connecting With Patients: The Rapid Rise of Voice Right Now
    Isbitski D, Fishman EK, Rowe SP
    J Am Coll Radiol. 2020;S1546-1440(20)30666-9. [published online ahead of print, 2020 July 17].  
  • "The focus on artificial intelligence in radiology has been on the use of algorithms to enhance image interpretation and uncover imaging bio- markers. However, artificial intelligence will have profound impacts across radiology practices, and the rise of voice-enabled devices indicates that. We can expect that patient preparation, explanations of studies, and the consenting process will be well handled by voice-enabled devices with artificial intelligence algorithms.”
    Connecting With Patients: The Rapid Rise of Voice Right Now
    Isbitski D, Fishman EK, Rowe SP
    J Am Coll Radiol. 2020;S1546-1440(20)30666-9. [published online ahead of print, 2020 July 17]. 
  • "Successful practices that emerge from the coronavirus pandemic in strong positions will find ways to leverage artificial intelligence, and voice-enabled technologies can play a large role in that. Our day-to-day work in our offices will also change. Voice-enabled technologies can finally help us to realize the “paperless” office. Our phone calls, dictations, and communications with colleagues can all be done in a contactless way using voice.”
    Connecting With Patients: The Rapid Rise of Voice Right Now
    Isbitski D, Fishman EK, Rowe SP
    J Am Coll Radiol. 2020;S1546-1440(20)30666-9. [published online ahead of print, 2020 July 17]. 
  • Results: Implementation of the checklist led to further actions in 25.9% of cases. The most common actions were calls to referring providers to modify or clarify an order (24.3%), followed by verification of proper pre- medication in patients with allergy to iodinated contrast (12.7%) and contacting the radiologist for protocolling (12.7%).
    Conclusions: Implementation of a pre-CT checklist that can be tailored to individual practices has potential to improve patients' safety and experience as well as providing a more efficient clinical operation.
    Summary sentence: We present an easy-to-implement checklist to maximize CT throughput in an outpatient setting that can be customized to the needs of individual institutions and has the potential to improve patients' safety and experience.
    The pre-CT checklist: A simple tool to improve workflow and patient safety T in an outpatient CT setting
    Sheila Sheth, Beatrice Mudge, Elliot K. Fishman
    Clinical Imaging 66 (2020) 101–105
  • Summary sentence: We present an easy-to-implement checklist to maximize CT throughput in an outpatient setting that can be customized to the needs of individual institutions and has the potential to improve patients' safety and experience.
    The pre-CT checklist: A simple tool to improve workflow and patient safety T in an outpatient CT setting
    Sheila Sheth, Beatrice Mudge, Elliot K. Fishman
    Clinical Imaging 66 (2020) 101–105

  • The pre-CT checklist: A simple tool to improve workflow and patient safety T in an outpatient CT setting
    Sheila Sheth, Beatrice Mudge, Elliot K. Fishman
    Clinical Imaging 66 (2020) 101–105
  • IV Contrast Agent Selection
    - Volume of contrast
    - Type of contrast (non-ionic vs iso-osmolar)
    - Concentration of contrast (300 vs 350 vs 370)
    - Injection rate (cc/sec)
    - Phases of acquisition(s)
  • Adult and Pediatric Patients
  • Adult Patients
  • Pediatric Patients
  • Renal Function and Intravascular Iodinated Contrast Administration
  • Renal Function and Intravascular Iodinated Contrast Administration
    - Dialysis Patients: Additional labs will not be needed as dialysis patients are already recognized to have an eGFR <30 mL/min/1.73m2
  • Renal Function and Intravascular Iodinated Contrast Administration
    - If the patient has any of the following risk factors and there is no eGFR value on record within 90 days, a serum creatinine/eGFR will be performed:
    --- Renal transplantation
    --- Total nephrectomy
    --- Documentation of any stage of CKD in the EHR
    --- Documentation of any eGFR value in the EHR within 90 days that is <30 mL/min/1.73m2 in patients who have no documented history of CKD or of currently being on dialysis
  • Renal Function and Intravascular Iodinated Contrast Administration
    - If the patient has any of the following risk factors and there is no eGFR value on record within 90 days, a POCT creatinine/eGFR will be performed:
    --- ≥ 60 years of age
    --- Diabetes mellitus
    --- Born with one kidney, partial nephrectomy, or renal ablation procedure
  • Renal Function and Intravascular Iodinated Contrast Administration
    - If the patient is taking a metformin-containing medication:
    --- Creatinine/eGFR values must be obtained within 30 days instead of 90 days.
    --- POCT can be performed unless the patient has one of the risk factors identified requiring serum creatinine/eGFR.
  • Renal Function and Intravascular Iodinated Contrast Administration
    - POCT creatinine/eGFR additional information:
    --- If eGFR POCT is not available, serum eGFR will be obtained.
    --- eGFR calculations should not be performed on the Nova StatSensor on patients under 18 years of age.  Use approved eGFR calculator using the creatinine value obtained from the POCT meter.
    --- POCT eGFR values will be documented in the electronic medical record.
Quotes

Small Bowel

  • “The small bowel is frequently the site of metastasis. Metastasis may reach the small bowel by the hematogenous route or by direct invasion or contiguous spread.The most common sources of hematogenous metastasis to the small bowel include lung cancer, breast cancer, and melanoma. These lesions tend to arise in the submucosa and may have a target or ulcerative appearance. The most common tumors to directly invade the small bowel include ovarian cancer and colon cancer. Tumor implants from carcinomatosis may be seen along the small bowel serosal surface and can cause obstruction.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "Small bowel neoplasms overall are rare. Small bowel lesions may be identified or evaluated with cross-sectional imaging such as CT or MRI.The differential diagnosis of focal small bowel masses found at cross-sectional imaging includes a variety of benign and malignant neoplasms and other masslike processes. Cross-sectional imaging is useful for evaluating the location, characteristics, and extent of disease. CT enterography and MR enterography are the best noninvasive imaging techniques for diagnosing, evaluating, and staging small bowel neoplasms. Imaging features of the small bowel lesion and associated findings at CT or MRI help limit the diagnostic possibilities. A high index of suspicion coupled with optimal imaging technique is often necessary for detection and accurate diagnosis.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • “Metastases to the small bowel often occur many years after the initial diagnosis of the primary malignancy or entering remission and may be symptomatic. Attention to the small bowel is particularly important in melanoma patients, who may have multiple small bowel metastases, even after many years of being disease free. As oncology patients undergo numerous surveillance scans and improved therapies allow for longer survival, detection of these masses at a small size can facilitate elective resection to avert urgent surgical intervention.”
    Clinical time course and CT detection of metastatic disease to the small bowel. 
    Lee MH, Zaheer A, Voltaggio L, Johnson PT, Fishman EK.
    Abdom Radiol (NY). 2019;44(6):2104-2110
  • “Adenomas are benign tumors that arise from glandular epithelium. Adenomatous polyp and villous adenoma are terms related to the growth pattern and morphology of adenomas.They are characterized histologically as tubular, villous, or tubulo-villous. Adenomas are most commonly found in the duodenum, particularly in the vicinity of the ampulla of Vater, where they tend to be of the villous subtype.They are least common in the ileum, where they are usually of the tubular subtype.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "Important polyposis syndromes that involve the small bowel and are reviewed in this article include familial adenomatous polyposis and Peutz-Jeghers syndrome. Polyposis syndromes are a group of disorders characterized by multiple polyps affecting part or all of the gastrointestinal tract. Lesions in these conditions are usually diagnosed relatively early, in a screening setting as compared with small bowel lesions overall. Also, patients tend to have multiple small bowel lesions and may present because of symptoms due to intermittent intussusception.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "Approximately 40% of GISTs arise in the small bowel, most often in the duodenum or jejunum. GISTs are unique mesenchymal tumors that arise from the interstitial cells of Cajal. They are defined by their expression of KIT (CD117), a tyrosine kinase growth factor receptor. Immu- noreactivity for KIT distinguishes GISTs from other mesenchymal tumors such as leiomyoma, neurofibroma, and schwannoma and determines the appropriateness of KIT inhibitor therapy.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "Benign GISTs are much more common than malignant GISTs and may be indistinguishable from other mesenchymal tumors at imaging. At CT and MRI, benign GISTs are seen as well-circumscribed variably enhancing soft-tissue masses that often show poor enhancement. GISTs often extend exophytically from the bowel lumen and may contain calcification.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "Some estimation of tumor activity may be inferred from lesion size and degree of contrast material uptake. Imaging also helps identify areas of necrosis and hemorrhage. Malignant tumors are larger than benign lesions andtend to have larger areas of necrosis as well as greater enhancement. Tumor diameter greater than 10 cm is a strong predictor of malignancy. Local invasion is an unequivocal indicator of malignancy. GISTs are considered to have malignant potential irrespective of their imaging features, and surgical resection is warranted irrespective of their size.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • “Malignant GIST tends to appear as a large, bulky, predominantly exophytic mass. At CT and MRI, it can be seen as a heterogeneous, enhancing, lobulated mass with areas of hypo- or hyperenhancement, necrosis, ulceration, cavitation, or hemorrhage. There may be associated metastases to the liver, omen- tum, or peritoneum. However, bulky lymphadenopathy is uncommon and would favor other neoplasms, including lymphoma or metastatic disease.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "Carcinoid tumor arises from the chromaffin cells at the base of the crypts of Lieberkühn. It most frequently arises in the distal ileum, Meckel diverticulum, or appendix and can be multifocal. Carcinoid tumor represents 25% of primary tumors of the small bowel, and 90% of small bowel carcinoid tumors arise in the distal ileum. Detection of primary carcinoid tumor in the small bowel is difficult with conventional imaging owing to the small size of the primary tumor (often less than a centimeter) and its location in the submucosa. More often, a spiculated mesenteric mass from metastatic disease is detected with imaging.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • “The endoexoenteric (cavitary) form appears as a large soft-tissue mass that communicates with the bowel lumen and appears cavitary. It represents a sealed-off localized perforation of bowel into the soft-tissue mass in the mesenteric space. Contrast material or gas can be seen in the soft-tissue mass, and this should not be mistaken for an abscess. Associated lymphadenopathy may help distinguish this form of intestinal lymphoma from a malignant GIST.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • “Diagnosis is a challenge owing to nonspecific clinical manifestation, rare occurrence, and low index of clinical suspicion. Yet, various small bowel neoplasms have characteristic imaging features at CT and MRI when optimal distention of the small bowel is achieved, correlating well with features seen in gross specimens. Understanding the imaging features of small bowel neoplasms is important to improve the radiologist’s ability to diagnose and characterize small bowel neoplasms. Most small bowel tumors are clinically silent for long periods, and nearly half of the benign tumors are found incidentally during surgery or at cross-sectional imaging performed for other reasons.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • * Small bowel neoplasms are rare, accounting for 0.5% of all cancers and approximately 3% of all gastrointestinal tumors in the United States, and their incidence is rising—in particular, there is a rising incidence of small bowel carcinoid tumor.  CT enterography and MR enterography are optimal imaging studies for assessing for small bowel tumors.
    * Adenoma and gastrointestinal stromal tumor (GIST) are the most common benign small bowel tumors and the only two with malignant predisposition.
    * GIST may be indistinguishable from other mesenchymal tumors (eg, leiomyoma) at imaging. All GISTs are now con- sidered potentially malignant; therefore, surgical resection should be considered regardless of size.
    * The most frequent site of small bowel involvement with lym- phoma is the ileum owing to the presence of abundant lymphoid tissue.
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "Peutz-Jeghers syndrome is a rare autosomal dominant inherited condition, although sporadic cases have been reported. It is less common than familial ad- enomatous polyposis and is characterized by multiple hamartomatous small bowel polyps, which are composed of smooth muscle and covered by normal mucosa. Peutz-Jeghers polyps are most often found in the jejunum followed by the ileum and duodenum.The condition is also characterized by mucocutaneous perioral and genital melanin pigmentation and increased risk of intestinal adenocarcinoma and nongastroin- testinal tumors.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "The mean age of diagnosis is 65 years. Small bowel neoplasms demonstrate a higher prevalence in black patients than in white patients . Metastatic lesions of the small bowel from tumors such as melanoma, lung cancer, and breast cancer are more common than primary small bowel malignancy. Among all symptomatic small bowel tumors, malignant lesions are more prevalent than benign lesions. Malignant lesions have a poor prognosis and usually manifest late with subocclusive crisis when at least two-thirds of the bowel lumen is occluded. This is due to the tolerance of the small bowel to obstructive phenomena.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • “More common risk factors for malignant small bowel tumors include chronic inflammation; inherited conditions such as familial adenomatous polyposis, hereditary nonpolyposis colorectal cancer (HNPCC), and Peutz-Jeghers syndrome; and infections such as human immunodeficiency virus (HIV). Small bowel malignant lesions metastasize frequently owing to the rich portal drainage. Curative surgical resection is the goal of treatment of most small bowel tumors with the exception of early localized lymphoma, for which other nonsurgical treatments have become more refined. Radiation therapy and chemotherapy are usually retained for more advanced stage III or IV disease.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
  • "Small bowel adenocarcinoma represents 25%– 40% of primary malignant small bowel tumors. It arises from the glandular epithelium. Predisposing conditions include polyposis syn- dromes, celiac disease, and Crohn disease. The median age of onset is 50–70 years. Primary adenocarcinoma most commonly occurs in the proximal jejunum or distal duodenum. Patients can present with vague symptoms including abdominal pain, nausea, vomiting, weight loss, gastrointestinal bleeding, anemia, and jaundice.”
    Small Bowel Neoplasms: A Pictorial Review
    Jasti R, Carucci LR
    RadioGraphics 2020;40:1020-1038
Stomach

  • Background: Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images.
    Methods: A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN.
    Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images
    Toshiaki Hirasawa et al.
    Gastric Cancer (2018) 21:653–660
  • Results: The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface.
    Conclusion: The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.
    Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images
    Toshiaki Hirasawa et al.
    Gastric Cancer (2018) 21:653–660
  • “In conclusion, we developed a CNN system for detecting gastric cancer using stored endoscopic images, which processed extensive independent images in a very short time. The clinically relevant diagnostic ability of the CNN offers a promising applicability to daily clinical practice for reducing the burden of endoscopists as well as telemedicine in remote and rural areas as well as in developing countries where the number of endoscopists is limited.”
    Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images
    Toshiaki Hirasawa et al.
    Gastric Cancer (2018) 21:653–660
© 1999-2020 Elliot K. Fishman, MD, FACR. All rights reserved.