|
-- OR -- |
|
3D and Workflow
- Cinematic rendering (CR) is a novel post-processing technique similar to volume rendering (VR), which allows for a more photorealistic imaging reconstruction by using a complex light modelling algorithm, incorporating information from multiple light paths and predicted photon scattering patterns. Several recent publications relating to adult imaging have argued that CR gives a better “realism” and “expressiveness” experience over VR techniques. CR has also been shown to improve visualisation of musculoskeletal and vascular anatomy compared with conventional CT viewing, and may help non-radiologists to understand complex patient anatomy. In this review, we provide an overview of how CR could be used in paediatric musculoskeletal imaging, particularly in complex diagnoses, surgical planning, and patient consent processes.We present a direct comparison of VR and CR reconstructions across a range of congenital and acquired musculoskeletal pathologies, highlighting potential advantages and areas for further research.
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282 - “CR uses a Monte Carlo path-tracing method to simulate howphotons have passed through the imaged tissue fromall directions. As there are theoretically an infinite number of directions fromwhich a photon could travel, theMonte Carlo simulation generates a randomnumber of light paths, which are averaged over time to create an image, approximating photon travel from all directions. This complex interaction of light rays better imitates how we visualise objects in real life, resulting in the so-called “photorealistic” image. The path tracing method also takes into account any overlying structures, generating shadows to help improve depth perception of the final digital 3D model.”
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282 - "In addition to musculoskeletal pathology, CR has been shown to provide improved visualisation of underlying vascular anatomy (over 2D CT images) for undergraduate medical education and several studies have published examples of CR use in depicting cerebrovascular, mesenteric, and aortic vascular pathology. In relation to trauma, we have found that traumatic pseudoaneurysms can be well depicted in relation to surrounding bony anatomy and may help in explaining treatment plans during patient consent for interventional procedures.”
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282 - “Despite the improved aesthetic appearances of CR, there are clear potential drawbacks in relying on this technique alone, some of which are similar to the VR technique. These include the potential to “mask” important findings, either by incorrect windowing or the superimposition of overlying structures. Furthermore, where the pathology is subtle or injuries (e.g., fractures) are present without significant displacement or angulation, they may be easily overlooked and “smoothened out” by the reconstruction algorithm. As such, any 3D reconstruction (CR and VR) should thus always be reviewed with the original source material (e.g., axial CT sections), as is conventional radiology practice. Care should also be taken in these circumstances to determine whether the 3D model should be shown at all, as it could provide false reassurance if the findings are too subtle to demonstrate.”
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282 - “As with all post-processing software, the quality of the CR reconstruction also depends on the original CT image quality. Image reconstructions require thin, isovolumetric sections in order to create accurate, non-pixelated, and aesthetically pleasing 3D models. This can result in a longer post-processing times and the higher computational demand is one main drawbacks of CR (compared to VR). Realtime display of a rotating CR image is at present limited by the need for repetitive recalculation of complex light paths, which can take the reconstruction software anywhere from 5-30 seconds per rotation.”
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282
Chest
- “Artificial intelligence (AI) is becoming more widespread within radiology. Capabilities that AI algorithms currently provide include detection, segmentation, classification, and quantification of pathological findings. Artificial intelligence software have created challenges for the traditional United States Food and Drug Administration (FDA) approval process for medical devices given their abilities to evolve over time with incremental data input. Currently, there are 190 FDA-approved radiology AI-based software devices, 42 of which pertain specifically to thoracic radiology. The majority of these algorithms are approved for the detection and/or analysis of pulmonary nodules, for monitoring placement of endotracheal tubes and indwelling catheters, for detection of emergent findings, and for assessment of pulmonary parenchyma; however, as technology evolves, there are many other potential applications that can be explored. For example, evaluation of non-idiopathic pulmonary fibrosis interstitial lung diseases, synthesis of imaging, clinical and/or laboratory data to yield comprehensive diagnoses, and survival or prognosis prediction of certain pathologies. With increasing physician and developer engagement, transparency and frequent communication between developers and regulatory agencies, such as the FDA, AI medical devices will be able to provide a critical supplement to patient management and ultimately enhance physicians’ ability to improve patient care.”
The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States
M.E. Milam, C.W. Koo
Clinical Radiology 2022 (in press) - “Rib fractures are commonly seen in the setting of thoracic trauma with an estimated 350,000 cases in the United States yearly. Presently, the only FDA-approved AI SaMD for rib fracture detection on CT is the uAI EasyTriage- Rib by Shanghai United Imaging Intelligence Co., Ltd. The tool consists of automatic vertebra localisation, rib segmentation and labelling, and rib fracture detection. There are currently no FDA-approved AI SaMD algorithms to detect rib fractures on chest radiographs.”
The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States
M.E. Milam, C.W. Koo
Clinical Radiology 2022 (in press) - “Although medical AI holds great promise, several barriers must be overcome before widespread clinical implementation. The process through which a model renders a decision remains unclear to human end-users, preventing trust-building. Although explainability methods, such as saliency maps, feature visualisation, and Shapley plots exist, it is increasingly apparent that these methods may be insufficient and more intuitive methods will need to be developed. In order to obtain buy-in from physicians, a change in physician point of view is needed, from perceiving AI as a rival threatening job security to seeing AI as a beneficial assistant. Physician engagement through training sessions that promote user understanding of software capability and limitations and having physicians as drivers of product development instead of just passive users may be key in turning such challenge into an opportunity. It cannot be emphasised enough that physician acceptance is one of the most important determinants in the successful initial institutional rollout of a medical AI product.”
The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States
M.E. Milam, C.W. Koo
Clinical Radiology 2022 (in press) - “AI is becoming ever increasingly more integrated within radiology. It has required the FDA to adapt their regulatory and approval process. Currently, there are 42 commercially available FDA-approved AI SaMD that have applications within chest radiology and as technologies continue to progress, more devices with different and enhanced capabilities currently under development will become available. Although several challenges remain for widespread adoption of AI SaMD, with increasing physician buy in, developer engagement, transparency, and frequent communication between developers and regulatory agencies such as the FDA, it will not be long before AI becomes an integral part of patient management and ultimately enhances patient care.”
The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States
M.E. Milam, C.W. Koo
Clinical Radiology 2022 (in press)
Colon
- “Intussusception is defined as the invagination of one segment of the bowel into an immediately adjacent segment of the bowel. Idiopathic ileocolic intussusception is the most common form in children and is typically managed with nonoperative reduction via pneumatic and/or hydrostatic enemas. In the adult population, intussusception is uncommon and occurs more often in the small intestine than in the colon. It is associated with lead point pathology in most symptomatic cases presenting as bowel obstruction. When lead point pathology is present in adult small bowel intussusception, it is usually benign, though when malignant it is most frequently due to diffuse metastatic disease, for example, melanoma. In contrast, adult ileocolic and colonic intussusception lead point pathology is most frequently primary adenocarcinoma when malignant.”
Intestinal Intussusception: Etiology, Diagnosis, and Treatment.
Marsicovetere P, Ivatury SJ, White B, Holubar SD.
Clin Colon Rectal Surg. 2017 Feb;30(1):30-39. - “The mean age of intussusception in adults is 50 years with no gender predominance. In direct contrast to pediatric etiologies, adult intussusception is associated with an identifiable cause in 90% of symptomatic cases with an idiopathic cause in 10% of cases.Benign or malignant neoplasms cause two-thirds of cases with a lead point; the remaining cases are caused by infections, postoperative adhesions, Crohn granulomas, intestinal ulcers (Yersinia), and congenital abnormalities such as Meckel diverticulum. Of the cases caused by neoplasms, 50% of them are malignant. Independent predictors of malignancy include colonic intussusception and anemia.”
Intestinal Intussusception: Etiology, Diagnosis, and Treatment.
Marsicovetere P, Ivatury SJ, White B, Holubar SD.
Clin Colon Rectal Surg. 2017 Feb;30(1):30-39. - “Most adult intussusceptions arise from the small bowel, and most lesions are benign with a rate of 50 to 75% in most series. The most common lesions are Meckel diverticulum and adhesions. Benign tumors include lymphoid hyperplasia, lipomas, leiomyomas, hemangiomas, and polyps. Other conditions that predispose to small bowel intussusception include anorexia, nervosa, and malabsorption syndromes, as increased flaccidity of the bowel wall facilitates invagination. Supratherapeutic anticoagulation therapy may cause submucosal hemorrhages that can lead to intussusception. Less commonly, malignant tumors may act as lead points with metastatic disease (i.e., carcinomatosis) being the most common. In several reports, approximately 50% of malignant lesions causing small bowel intussusception were metastatic (miliary) melanomas.Malignant intraluminal causes of small bowel intussusception include primary leiomyosarcomas, adenocarcinoma, GIST tumors, carcinoid tumors, neuroendocrine tumors, and lymphomas.”
Intestinal Intussusception: Etiology, Diagnosis, and Treatment.
Marsicovetere P, Ivatury SJ, White B, Holubar SD.
Clin Colon Rectal Surg. 2017 Feb;30(1):30-39. - “Adult intussusception less commonly occurs in the colon than in the small bowel and accounts for only 20 to 25% of all intussusceptions in most reported case series. The most common malignant cause of colonic intussusception is primary colonic adenocarcinoma and the most common benign cause is colonic lipoma. Contrary to the small intestine, several reports indicate that colonic intussusception is more likely to have a malignant lead point due to the increased prevalence of malignancies in the colon versus the small bowel. However, other studies conflict with this and suggest the proportion of benign and malignant lesions causing colonic intussusception is similar to that of small bowel intussusception. Ileocolic intussusception in adults is a unique variant in which nearly 100% of cases have a malignant lead point, namely, cecal adenocarcinoma involving the ileocecal valve.”
Intestinal Intussusception: Etiology, Diagnosis, and Treatment.
Marsicovetere P, Ivatury SJ, White B, Holubar SD.
Clin Colon Rectal Surg. 2017 Feb;30(1):30-39. - “In adults, the clinical presentation of intussusception can be nonspecific, rarely presenting with the classic triad of abdominal pain, palpable mass, and bloody stool. Instead, it presents with symptoms of small or large bowel obstruction. The most common presenting symptom is abdominal pain, with associated symptoms consistent with partial obstruction: nausea, vomiting, obstipation, gastrointestinal bleeding, change in bowel habits, constipation, or bloating. Wang et al found abdominal cramping pain in nearly 80% of patients as a leading symptom; a palpable abdominal mass, however, was found in less than 9%.”
Intestinal Intussusception: Etiology, Diagnosis, and Treatment.
Marsicovetere P, Ivatury SJ, White B, Holubar SD.
Clin Colon Rectal Surg. 2017 Feb;30(1):30-39. 
- “In adults, the clinical presentation of intussusception can be nonspecific, rarely presenting with the classic triad of abdominal pain, palpable mass, and bloody stool. Instead, it presents with symptoms of small or large bowel obstruction. The most common presenting symptom is abdominal pain, with associated symptoms consistent with partial obstruction: nausea, vomiting, obstipation, gastrointestinal bleeding, change in bowel habits, constipation, or bloating. Wang et al found abdominal cramping pain in nearly 80% of patients as a leading symptom; a palpable abdominal mass, however, was found in less than 9%.”
Colonic Intussusception: Clinical and Radiographic Features
Gollub MJ
AJR 2011; 196:W580–W585 - Colonic intussusception is caused by a malignancy more frequently than is smallbowel intussusception, because of the greater prevalence of malignant tumors in the colon (e.g., primary adenocarcinoma, lymphoma, and metastatic disease to the colon) than in the small bowel. Benign colonic lesions constitute about 30% of colonic intussusceptions and include lipoma, benign stromal tumors, adenomatous polyps, endometriosis, and previous anastomoses. Ileocecal intussusception can occur from a lead point in the colon, ileum, or appendix. Causes may include lipoma, inflammatory fibroid polyp, hamartomatous polyp, lymphoma, adenocarcinoma of the ileum or cecum, or even Meckel diverticulum. Inflammatory appendiceal conditions can also cause intussusception, but the most commonly reported entity is a mucocele.
Colonic Intussusception: Clinical and Radiographic Features
Gollub MJ
AJR 2011; 196:W580–W585 - “Among my patients, only one with colonic intussusception ultimately presented emergently with severe cramping abdominal pain, vomiting, and diarrhea. Most cases required surgery but not usually emergently. Other malignant intussusceptions spontaneously resolved after chemotherapy. As in other series, most cases at my institution occurred in the proximal colon, either right or transverse. Possible explanations include a greater tendency in the proximal colon for polypoid neoplasms and a longer colonic mesentery, which allows greater colonic mobility. Obstruction was a rare feature in this series."
Colonic Intussusception: Clinical and Radiographic Features
Gollub MJ
AJR 2011; 196:W580–W585 - “Intussusception is the invagination of a bowel loop with its mesenteric fold (intussusceptum) into the lumen of a contiguous portion of bowel (intussuscipiens) as a result of peristalsis. Intraluminal polypoid lesions have a greater tendency to cause invagination of the bowel as peristalsis drags the lesion forward. Although the exact mechanism precipitating intussusception, especially intussusception without a lead point, is not well understood, this condition has been ascribed to dysrhythmic contractions.”
Adult Intestinal Intussusception: CT Appearances and Identification of a Causative Lead Point
Young H. Kim, et al.
RadioGraphics 2006; 26:733–744 - Adenocarcinoma of the colon is the most common malignant neoplasm associated with colonic intussusception .Typical signs and symptoms of adenocarcinoma of the colon include bleeding, obstruction, a palpable abdominal mass, and abdominal pain. The individual layers of the intussuscepted bowel wall are more easily distinguished from the lead mass in this intussusception. Differentiation of the lead mass from bowel wall edema at CT is generally easier in large bowel intussusception than in small bowel intussusception due to the greater caliber of the colon.
Adult Intestinal Intussusception: CT Appearances and Identification of a Causative Lead Point
Young H. Kim, et al.
RadioGraphics 2006; 26:733–744 - “Lipomas are the most common benign cause of colocolic intussusception in adults. Next to adenomatous polyps, these mesenchymal tumors are the most common benign tumors of the colon. Lipomas of the colon are within the submucosa in 90% of cases, are usually solitary, and may be sessile or pedunculated . Lipomas are often discovered incidentally at endoscopic or radiologic examination and can easily be diagnosed with CT due to their typical fat attenuation. Close observation of consecutive axial images can help avoid misinterpreting entrapped mesentery and subserosal fat as a lipoma. Multiplanar reformation may be used to confirm the diagnosis of intussusception when axial views raise suspicion for such a diagnosis. Lipomas are almost always asymptomatic until they cause abdominal pain, sometimes due to intussusception.”
Adult Intestinal Intussusception: CT Appearances and Identification of a Causative Lead Point
Young H. Kim, et al.
RadioGraphics 2006; 26:733–744 - Causes of Adult Intestinal Lead Point Intussusception (Colon)
Benign
- Lipoma
- adenomatous polyp
Malignant
- Adenocarcinoma
- lymphoma,
- metastasis
Idiopathic
- Postoperative adhesion,
- motility disorder
- “Originally described in 1957 by Bauer et al., colonic lipomas are the most common non-epithelial (mesenchymal) tumor of the colon and the second most common benign colonic lesion after polyps. They are asymptomatic except when large and therefore, usually have no clinical signifcance. However, approximately 75% of patients with colonic lipomas larger than 4 cm in size may be symptomatic. Non-specifc symptoms such as abdominal pain or altered bowel habits are typical with gastrointestinal bleeding, perforation, obstruction, and intussusception rare.”
Colonic lipomas revisited on CT colonography
Shima Roknsharif et al.
Abdominal Radiology (2022) 47:1788–1797 - "The majority of the colonic lipomas are asymptomatic and discovered incidentally. In up to 25% of patients, however, lipomas may cause symptoms, including abdominal pain, weight loss, and alteration in bowel habits. Lipomas have been reported to cause spontaneous expulsion, GI bleeding from surface ulceration, intussusception, and rarely bowel obstruction In rare circumstances, large colonic lipomas mimic colonic malignancy on OC with the diagnosis only made after colonic surgery . The most common symptoms reported with colonic lipomas are abdominal pain, GI bleeding, and altered bowel habits.”
Colonic lipomas revisited on CT colonography
Shima Roknsharif et al.
Abdominal Radiology (2022) 47:1788–1797 - “The most commonsite of symptomatic lipomas is the transverse colon (25%), with the sigmoid colon and cecum the second most common locations (20%).”
Colonic lipomas revisited on CT colonography
Shima Roknsharif et al.
Abdominal Radiology (2022) 47:1788–1797 - “A large fatty ileocecal valve is an occasional mimicker of a lipoma of the ileocecal valve but unlike a lipoma has a central depression unique to the ileocecal valve best appreciated on 3D images aiding its recognition. Primary colonic liposarcoma, an exceedingly rare entity reported in older patients in the proximal colon, should not be confused with colonic lipomas. A fatty mass with septations or nodular soft tissue component is suggestive of liposarcoma.”
Colonic lipomas revisited on CT colonography
Shima Roknsharif et al.
Abdominal Radiology (2022) 47:1788–1797 - “The 2021 USPSTF recommendations state that screening adults’ age 45 to 75 years with CTC every 5 years is an efective alternative to screening every 10 years with colonoscopy. Given the USPSTF recommendations and the non-invasiveness of CTC compared to optical colonoscopy (OC), the utilization of CTC is expected to increase substantially."
Colonic lipomas revisited on CT colonography
Shima Roknsharif et al.
Abdominal Radiology (2022) 47:1788–1797
- Introduction: Colitis is one of the most common immune-related adverse events in patients receiving immune checkpoint inhibitors. Although radiographic changes on computed tomography (CT), such as mild diffuse bowel thickening, mesenteric fat stranding, and mucosal enhancement, have been reported, the utility of CT in diagnosis of patients with suspected immune-related colitis is not well documented. The aim of this retrospective study was to determine the value of CT scans in diagnosis of immunotherapy-induced colitis.
Conclusions: We found that CT had a low sensitivity, specificity, and negative predictive value for the diagnosis of immunotherapy-induced colitis. We therefore conclude that CT has a limited role in the diagnosis of patients with suspected uncomplicated immune-related colitis.
Role of Abdominal and Pelvic CT Scans in Diagnosis of Patients with Immunotherapy-Induced Colitis.
Ibarra Rovira J, et al.
J Immunother Precis Oncol. 2022 May 19;5(2):32-36. - “ICI-induced colitis is a frequent adverse event and is seen in 15–25% of patients on CTLA-4 inhibitors and in up to 10% of patients treated with PD-1 and PD-L1 inhibitors. Colitis typically appears between 5 and 10 weeks after initiating treatment; however, the timing can range from immediately after the first dose to more than 6 months after the last dose.”
Role of Abdominal and Pelvic CT Scans in Diagnosis of Patients with Immunotherapy-Induced Colitis.
Ibarra Rovira J, et al.
J Immunother Precis Oncol. 2022 May 19;5(2):32-36. - Our study demonstrates that CT is not a useful tool for diagnosing colitis in patients receiving ICIs with grades 1–3 colitis. Routine use of CT scans to diagnose colitis in such patients should be discouraged. Use of CT scans should be reserved for patients with signs of complicated colitis, such as perforation, obstruction, and abscesses.
Role of Abdominal and Pelvic CT Scans in Diagnosis of Patients with Immunotherapy-Induced Colitis.
Ibarra Rovira J, et al.
J Immunother Precis Oncol. 2022 May 19;5(2):32-36. - “Thus, myriad gastrointestinal (GI) symptoms are common in immunocompromised patients and may be due to inflammatory conditions (graft versus host disease, neutropenic enterocolitis, or HIV-related proctocolitis), opportunistic infections (viral, bacterial, fungal, or protozoal), or malignancies (Kaposi sarcoma, lymphoma, posttransplant lymphoproliferative disorder, or anal cancer). GI tract involvement in immunodeficient patients contributes to significant morbidity and mortality. Along with endoscopy and histopathologic evaluation, imaging plays an integral role in detection, localization, characterization, and distinction of GI tract manifestations of various immunodeficiency syndromes and their complications.”
Gastrointestinal Manifestations of Immunodeficiency: Imaging Spectrum
Malak Itani et al.
RadioGraphics 2022; 42:759–777 - “Typical imaging findings of acute GVHD include fluid-filled dilated bowel loops with wall thickening and marked mucosal enhancement, with mural stratification, producing a targetoid appearance owing to hyperattenuating mucosa and serosa and hypoattenuating edematous submucosa. Extraintestinal manifestations include mesenteric fat stranding, vasa recta engorgement, and ascites, with absence of mesenteric lymphadenopathy.”
Gastrointestinal Manifestations of Immunodeficiency: Imaging Spectrum
Malak Itani et al.
RadioGraphics 2022; 42:759–777 - “The early posttransplant period is 30–100 days after transplant, whereas beyond 100 days is the late posttransplant period. Acute GVHD classically develops 10–40 days after transplant. However, late-onset acute GVHD may be seen more than 100 days after transplant and involves the GI tract in 54% of patients, most commonly the small intestine followed by the colon.”
Gastrointestinal Manifestations of Immunodeficiency: Imaging Spectrum
Malak Itani et al.
RadioGraphics 2022; 42:759–777 - “Typical imaging findings of acute GVHD include fluid-filled dilated bowel loops with wall thickening and marked mucosal enhancement, with mural stratification, producing a targetoid appearance owing to hyperattenuating mucosa and serosa and hypoattenuating edematous submucosa . Extraintestinal manifestations include mesenteric fat stranding, vasa recta engorgement, and ascites, with absence of mesenteric lymphadenopathy. The degree of small-bowel involvement has been shown to be related to disease severity, diffuse small bowel involvement being associated with severe clinical manifestation, less chance of response to therapy, and poor prognosis .”
Gastrointestinal Manifestations of Immunodeficiency: Imaging Spectrum
Malak Itani et al.
RadioGraphics 2022; 42:759–777 - “Opportunistic MAI enteritis is typically characterized by irregularly thickened small-bowel folds at fluoroscopy and small-bowel segmental or diffuse wall thickening with mucosal hyperenhancement at CT and MRI. Mesenteric lymph nodes are often smaller and more uniform than in cases of M tuberculosis infection, although they commonly demonstrate central necrosis.”
Gastrointestinal Manifestations of Immunodeficiency: Imaging Spectrum
Malak Itani et al.
RadioGraphics 2022; 42:759–777 - “Candida is the most common cause of esophageal infection in AIDS patients in the United States. The fluoroscopic appearance of esophageal candidiasis varies in AIDS versus non-AIDS immunosuppressed patients. In AIDS patients, diffuse ulceration of the esophageal mucosa with coalescent plaques and pseudomembranes result in a grossly irregular “shaggy” esophagus appearance. In non-AIDS patients, candidiasis manifests as longitudinally oriented plaquelike growths etched out by barium along the longitudinal folds of the esophagus.”
Gastrointestinal Manifestations of Immunodeficiency: Imaging Spectrum
Malak Itani et al.
RadioGraphics 2022; 42:759–777 - “Lymphomas in immunodeficient individuals include both Hodgkin lymphoma and non-Hodgkin lymphoma (NHL), with the most common subtypes of HIV-related NHL being diffuse large B-cell lymphoma (DLBCL) and Burkitt lymphoma,mwhich are associated with Epstein-Barrmvirus (EBV). Primary effusion lymphoma (PEL) is a less common variant of HIV-related lymphoma that arises in body cavities such as the pleura, pericardium, or peritoneum; it occurs more specifically in HIV-positive patients and is associated with HHV8. GI lymphoma may manifest with B symptoms and GI symptoms.”
Gastrointestinal Manifestations of Immunodeficiency: Imaging Spectrum
Malak Itani et al.
RadioGraphics 2022; 42:759–777
Deep Learning
- Purpose: A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist.
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print. - Results: 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist.
Conclusion: Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdominal Radiology (2022) 47:4139–4150 
- “A total of 488 radiomics features from the segmented volume were extracted to define cystic lesion and pancreas phenotypes based on venous phase images. Radiomics features used in this study included 14 first-order statistics of the volumetric CT intensities, 8 shape features of the target structure, 33 texture features from a gray-level co-occurrence matrix and a gray-level run-length matrix, 376 texture features from the 8 filtered volumes by wavelets, and an additional 47 texture features form the filtered volume by Laplacian of Gaussian (LoG). Ten image features were extracted from the whole pancreatic region. Table 2 represents the whole feature set used for cyst classification in this study. Two demographic features, age and gender, were also incorporated into the final model.”
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdominal Radiology (2022) 47:4139–4150 
- AI and Pancreatic Adenocarcinoma
- Early (earlier) detection
- Improved staging of disease
- Pre-operative planning
- Selection of chemotherapy
- Selection of radiation therapy
- Prediction of outcome/survival - Early Detection
- Pre-Operative Planning
- Pre-Operative Planning
- “Radiomics is a rapidly growing field that quantitatively extracts image features in a high-throughput manner from medical imaging. In this study, we analyzed the radiomics features of the whole pancreas between healthy individuals and pancreatic cancer patients, and we established a predictive model that can distinguish cancer patients from healthy individuals based on these radiomics features.”
Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
Shuo Wang et al.
Technology in Cancer Research & Treatment Volume 21: 1-14 2022 - Results: We identified that 91 radiomics features are stable against various uncertainty sources, including bin width, resampling, image transformation, image noise, and segmentation uncertainty. Eight of the 91 features are nonredundant. Our final predictive model, using these 8 features, has achieved a mean area under the receiver operating characteristic curve (AUC) of 0.99±0.01 on the training dataset (189 subjects) by cross-validation. The model achieved an AUC of 0.910 on the independent test set (77 subjects) and an accuracy of 0.935.
Conclusion: CT-based radiomics analysis based on the whole pancreas can distinguish cancer patients from healthy individuals, and it could potentially become an early detection tool for pancreatic cancer.
Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
Shuo Wang et al.
Technology in Cancer Research & Treatment Volume 21: 1-14 2022 - “Second, our study is a single-institution study without any external validation, which is one of the essential metrics for assessing the robustness of a study. Although we sought to improve the robustness of our study by randomizing the TCIA public dataset into our radiomic analysis and predictive analytics, the generalizability of our results remains to be further validated on new datasets. Third, although all the CT images we collected are the venous phases of the contrast CT, it is difficult to evaluate contrast enhancement variation since it depends on patient-specific physiology (eg, blood flow rate). Therefore, we did not study the feature stability against contrast enhancement variation among various patients.”
Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
Shuo Wang et al.
Technology in Cancer Research & Treatment Volume 21: 1-14 2022 - Conclusion: Our study proved that CT-based radiomics analysis and modeling can distinguish healthy individuals from pancreatic cancer patients, and potentially can become an effective tool to detect cancerous pancreatic tissue at an early stage.
Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
Shuo Wang et al.
Technology in Cancer Research & Treatment Volume 21: 1-14 2022
- “Artificial intelligence (AI) is becoming more widespread within radiology. Capabilities that AI algorithms currently provide include detection, segmentation, classification, and quantification of pathological findings. Artificial intelligence software have created challenges for the traditional United States Food and Drug Administration (FDA) approval process for medical devices given their abilities to evolve over time with incremental data input. Currently, there are 190 FDA-approved radiology AI-based software devices, 42 of which pertain specifically to thoracic radiology. The majority of these algorithms are approved for the detection and/or analysis of pulmonary nodules, for monitoring placement of endotracheal tubes and indwelling catheters, for detection of emergent findings, and for assessment of pulmonary parenchyma; however, as technology evolves, there are many other potential applications that can be explored. For example, evaluation of non-idiopathic pulmonary fibrosis interstitial lung diseases, synthesis of imaging, clinical and/or laboratory data to yield comprehensive diagnoses, and survival or prognosis prediction of certain pathologies. With increasing physician and developer engagement, transparency and frequent communication between developers and regulatory agencies, such as the FDA, AI medical devices will be able to provide a critical supplement to patient management and ultimately enhance physicians’ ability to improve patient care.”
The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States
M.E. Milam, C.W. Koo
Clinical Radiology 2022 (in press) - “Rib fractures are commonly seen in the setting of thoracic trauma with an estimated 350,000 cases in the United States yearly. Presently, the only FDA-approved AI SaMD for rib fracture detection on CT is the uAI EasyTriage- Rib by Shanghai United Imaging Intelligence Co., Ltd. The tool consists of automatic vertebra localisation, rib segmentation and labelling, and rib fracture detection. There are currently no FDA-approved AI SaMD algorithms to detect rib fractures on chest radiographs.”
The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States
M.E. Milam, C.W. Koo
Clinical Radiology 2022 (in press) - “Although medical AI holds great promise, several barriers must be overcome before widespread clinical implementation. The process through which a model renders a decision remains unclear to human end-users, preventing trust-building. Although explainability methods, such as saliency maps, feature visualisation, and Shapley plots exist, it is increasingly apparent that these methods may be insufficient and more intuitive methods will need to be developed. In order to obtain buy-in from physicians, a change in physician point of view is needed, from perceiving AI as a rival threatening job security to seeing AI as a beneficial assistant. Physician engagement through training sessions that promote user understanding of software capability and limitations and having physicians as drivers of product development instead of just passive users may be key in turning such challenge into an opportunity. It cannot be emphasised enough that physician acceptance is one of the most important determinants in the successful initial institutional rollout of a medical AI product.”
The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States
M.E. Milam, C.W. Koo
Clinical Radiology 2022 (in press) - “AI is becoming ever increasingly more integrated within radiology. It has required the FDA to adapt their regulatory and approval process. Currently, there are 42 commercially available FDA-approved AI SaMD that have applications within chest radiology and as technologies continue to progress, more devices with different and enhanced capabilities currently under development will become available. Although several challenges remain for widespread adoption of AI SaMD, with increasing physician buy in, developer engagement, transparency, and frequent communication between developers and regulatory agencies such as the FDA, it will not be long before AI becomes an integral part of patient management and ultimately enhances patient care.”
The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States
M.E. Milam, C.W. Koo
Clinical Radiology 2022 (in press)
Musculoskeletal
- Cinematic rendering (CR) is a novel post-processing technique similar to volume rendering (VR), which allows for a more photorealistic imaging reconstruction by using a complex light modelling algorithm, incorporating information from multiple light paths and predicted photon scattering patterns. Several recent publications relating to adult imaging have argued that CR gives a better “realism” and “expressiveness” experience over VR techniques. CR has also been shown to improve visualisation of musculoskeletal and vascular anatomy compared with conventional CT viewing, and may help non-radiologists to understand complex patient anatomy. In this review, we provide an overview of how CR could be used in paediatric musculoskeletal imaging, particularly in complex diagnoses, surgical planning, and patient consent processes.We present a direct comparison of VR and CR reconstructions across a range of congenital and acquired musculoskeletal pathologies, highlighting potential advantages and areas for further research.
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282 - “CR uses a Monte Carlo path-tracing method to simulate howphotons have passed through the imaged tissue fromall directions. As there are theoretically an infinite number of directions fromwhich a photon could travel, theMonte Carlo simulation generates a randomnumber of light paths, which are averaged over time to create an image, approximating photon travel from all directions. This complex interaction of light rays better imitates how we visualise objects in real life, resulting in the so-called “photorealistic” image. The path tracing method also takes into account any overlying structures, generating shadows to help improve depth perception of the final digital 3D model.”
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282 - "In addition to musculoskeletal pathology, CR has been shown to provide improved visualisation of underlying vascular anatomy (over 2D CT images) for undergraduate medical education and several studies have published examples of CR use in depicting cerebrovascular, mesenteric, and aortic vascular pathology. In relation to trauma, we have found that traumatic pseudoaneurysms can be well depicted in relation to surrounding bony anatomy and may help in explaining treatment plans during patient consent for interventional procedures.”
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282 - “Despite the improved aesthetic appearances of CR, there are clear potential drawbacks in relying on this technique alone, some of which are similar to the VR technique. These include the potential to “mask” important findings, either by incorrect windowing or the superimposition of overlying structures. Furthermore, where the pathology is subtle or injuries (e.g., fractures) are present without significant displacement or angulation, they may be easily overlooked and “smoothened out” by the reconstruction algorithm. As such, any 3D reconstruction (CR and VR) should thus always be reviewed with the original source material (e.g., axial CT sections), as is conventional radiology practice. Care should also be taken in these circumstances to determine whether the 3D model should be shown at all, as it could provide false reassurance if the findings are too subtle to demonstrate.”
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282 - “As with all post-processing software, the quality of the CR reconstruction also depends on the original CT image quality. Image reconstructions require thin, isovolumetric sections in order to create accurate, non-pixelated, and aesthetically pleasing 3D models. This can result in a longer post-processing times and the higher computational demand is one main drawbacks of CR (compared to VR). Realtime display of a rotating CR image is at present limited by the need for repetitive recalculation of complex light paths, which can take the reconstruction software anywhere from 5-30 seconds per rotation.”
Cinematic rendering of paediatric musculoskeletal pathologies: initial experiences with CT
A. Fagan et al.
Clinical Radiology 77 (2022) 274-282
- Myxopapillary ependymoma (MPE) is a rare variant of conventional ependymoma which arises from the ependymal cells lining the subarachnoid space. It most commonly affects young adults and children. The male-female ratio of this tumor is 2.2:1.2.
It is categorized by the World Health Organization as a Grade 1 lesion and is found predominantly in the sacrococcygeal region most often near the filum terminale or conus medullaris.
The tumor is usually slow growing, is often intradural although local extension into paravertebral soft tissue and adjacent bone is occasionally seen.
Myxopapillary ependymoma: Lesser known cytomorphologic features.
Choudhury M, Rautela A, Nain M.J Cytol. 2015 Jan-Mar;32(1):42-5. - Plain radiograph and CT scan can reveal scalloping of the vertebral bodies secondary to the expansion of the spinal canal caused by the presence of a large myxopapillary ependymoma.
The differential diagnosis of a large myxopapillary ependymoma that is responsible for sacral destruction includes:
Aneurysmal bone cyst
Chondrosarcoma
Chordoma
Giant cell tumor
Metastatic carcinoma
Pancreas
- “This study showed that a radiomics-based model can achieve equivalent performance as an experienced academic radiologist in the classification of a wide array of pancreatic cysts with variable malignant potential. This model has the potential to refine pancreatic cyst management by improving diagnostic accuracy of cystic lesions, which can minimize healthcare utilization while maximizing detection of malignant lesions. This study confirms the ability of a radiomic based model to accurately classify pancreatic cystic neoplasms. Further validation and clinical integration of this model could help optimize management of pancreatic cysts by maximizing the rate of detection of malignant lesions while reducing healthcare utilization.”
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdominal Radiology (2022) 47:4139–4150 - “Among the whole 490 features (488 radiomics features plus age and gender), thirty features were found to reduce redundancy by the minimum-redundancy maximum-relevancy feature selection based on mutual information, which showed the best classification performance, with AUC of 0.940. Age and gender were included in the model due to the known gender and gender associations for pancreatic cysts. These demographic features would be available to the radiologist at the time of exam, and this would simulate the real-world application. Age, median and mean intensities of the original images and wavelets, and fractal dimension were highly ranked for the classifications. Gender was ranked as 29th feature for the classification."
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdominal Radiology (2022) 47:4139–4150 - “In this study, the performance of the radiomics featurebased classification achieved AUC of 0.940 in distinguishing among five types of pancreatic cystic neoplasms. The performance was similar to previous studies with multi-class pancreatic cyst classifications that included three or four cyst types, with accuracy of 79.6–83.6%. Previous studies on radiomics-based pancreatic cyst classification did not include a direct comparison with a radiologist, therefore, it was difficult to assess if the radiomics-based classification reported provided any added value relative to the standard of care. The current study showed that the radiomics- based pancreatic cyst classification achieved equivalent performance as an academic radiologist with more than 25 years of experience.”
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdominal Radiology (2022) 47:4139–4150 - "Secondly, the performance of the radiomics-based model was compared to the performance of a single-academic radiologist. The experienced academic radiologist in this study may be more accurate at pancreatic cyst classification than an average radiologist in the community, which may underestimate the incremental value of the radiomics-based model. Future reader studies should also recruit multiple readers with a wide range of experience to measure the real-world impact of these radiomics tools. Thirdly, the current radiomics model only used CT-based features plus patient age and demographics. Other important clinical features such as symptoms, family history, laboratory values, and cyst fluid molecular markers were not included in the current model, which should be incorporated into future models. Our prior experience has demonstrated that the predictive power offered by multiple features is often additive.”
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdominal Radiology (2022) 47:4139–4150
- Purpose: A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist.
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdom Radiol (NY). 2022 Sep 13. doi: 10.1007/s00261-022-03663-6. Online ahead of print. - Results: 214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist.
Conclusion: Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdominal Radiology (2022) 47:4139–4150 - “A total of 488 radiomics features from the segmented volume were extracted to define cystic lesion and pancreas phenotypes based on venous phase images. Radiomics features used in this study included 14 first-order statistics of the volumetric CT intensities, 8 shape features of the target structure, 33 texture features from a gray-level co-occurrence matrix and a gray-level run-length matrix, 376 texture features from the 8 filtered volumes by wavelets, and an additional 47 texture features form the filtered volume by Laplacian of Gaussian (LoG). Ten image features were extracted from the whole pancreatic region. Table 2 represents the whole feature set used for cyst classification in this study. Two demographic features, age and gender, were also incorporated into the final model.”
Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer‑augmented diagnostics for radiologists
Linda C. Chu et al.
Abdominal Radiology (2022) 47:4139–4150
- Purpose: To characterize the prevalence of missed pancreatic masses and pancreatic ductal adenocarcinoma (PDAC)-related findings on CT and MRI between pre-diagnostic patients and healthy individuals.
Materials and methods: Patients diagnosed with PDAC (2010–2016) were retrospectively reviewed for abdominal CT- or MRI-examinations 1 month—3 years prior to their diagnosis, and subsequently matched to controls in a 1:4 ratio. Two blinded radiologists scored each imaging exam on the presence of a pancreatic mass and secondary features of PDAC. Additionally, original radiology reports were graded based on the revised RADPEER criteria.
Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
Sanne A. Hoogenboom et al.
Abdominal Radiology (2022) 47:4160–4172 - Results: The cohort of 595 PDAC patients contained 60 patients with a pre-diagnostic CT and 27 with an MRI. A pancreatic mass was suspected in hindsight on CT in 51.7% and 50% of cases and in 1.3% and 0.9% of controls by reviewer 1 (p < .001) and reviewer 2 (p < .001), respectively. On MRI, a mass was suspected in 70.4% and 55.6% of cases and 2.9% and 0% of the controls by reviewer 1 (p < .001) and reviewer 2 (p < .001), respectively. Pancreatic duct dilation, duct interruption, focal atrophy, and features of acute pancreatitis is strongly associated with PDAC (p < .001). In cases, a RADPEER-score of 2 or 3 was assigned to 56.3% of the CT-reports and 71.4% of MRI-reports. Conclusion Radiological features as pancreatic duct dilation and interruption, and focal atrophy are common first signs of PDAC and are often missed or unrecognized. Further investigation with dedicated pancreas imaging is warranted in patients with PDAC-related radiological findings.
Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
Sanne A. Hoogenboom et al.
Abdominal Radiology (2022) 47:4160–4172 
Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
Sanne A. Hoogenboom et al.
Abdominal Radiology (2022) 47:4160–4172- “PDAC arises from ductal epithelial cells and precursor lesions are common in the general elderly population, including pancreatic intraepithelial neoplasia (PanIN), intraductal pancreatic mucinous neoplasia (IPMN), and mucinous cystic neoplasia. Although these precursor lesions predominantly harbor low-grade dysplasia, a fraction will evolve into high-grade dysplasia and these are considered immediate precursors of PDAC. The estimated time of progression from the initiation of PanIN to PDAC and from PDAC to potential metastasis is 12 and 7 years, respectively. Considering this slow progression, there is a notable window of opportunity to detect early-stage PDAC or even precursor lesions with high-grade dysplasia.”
Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
Sanne A. Hoogenboom et al.
Abdominal Radiology (2022) 47:4160–4172 - “As stated earlier, PanIN with high-grade dysplasia and early invasive PDAC lesions do not generally form clear hypodense masses. Still, they may cause visible changes of the pancreatic parenchyma and the pancreatic duct, and these changes are rarely observed in patients who do not subsequently develop PDAC, as demonstrated in this study. Focal parenchymal atrophy may be a less known PDAC related imaging feature, but was observed on CT and MRI in 46%–49% of cases and only in one control patient. These results confirm the conclusion of recently published papers, who recognized focal atrophy as one of the first radiological features of early-stage PDAC.”
Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
Sanne A. Hoogenboom et al.
Abdominal Radiology (2022) 47:4160–4172 - “To conclude, our findings indicate that PDAC-related features on abdominal imaging can be present long before PDAC is diagnosed. These features are rarely present in individuals who are not diagnosed with PDAC, and therefore dedicated pancreas imaging is warranted if these features are found. Future research should focus on an automated second review that can detect otherwise missed lesions or secondary signs, aided by artificial intelligence. In addition, prospective studies should point out if early detection of PDAC would indeed lead to improved survival.”
Prevalence, features, and explanations of missed and misinterpreted pancreatic cancer on imaging: a matched case–control study
Sanne A. Hoogenboom et al.
Abdominal Radiology (2022) 47:4160–4172
- AI and Pancreatic Adenocarcinoma
- Early (earlier) detection
- Improved staging of disease
- Pre-operative planning
- Selection of chemotherapy
- Selection of radiation therapy
- Prediction of outcome/survival - Early Detection
- Pre-Operative Planning
- Pre-Operative Planning
- “Radiomics is a rapidly growing field that quantitatively extracts image features in a high-throughput manner from medical imaging. In this study, we analyzed the radiomics features of the whole pancreas between healthy individuals and pancreatic cancer patients, and we established a predictive model that can distinguish cancer patients from healthy individuals based on these radiomics features.”
Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
Shuo Wang et al.
Technology in Cancer Research & Treatment Volume 21: 1-14 2022 - Results: We identified that 91 radiomics features are stable against various uncertainty sources, including bin width, resampling, image transformation, image noise, and segmentation uncertainty. Eight of the 91 features are nonredundant. Our final predictive model, using these 8 features, has achieved a mean area under the receiver operating characteristic curve (AUC) of 0.99±0.01 on the training dataset (189 subjects) by cross-validation. The model achieved an AUC of 0.910 on the independent test set (77 subjects) and an accuracy of 0.935.
Conclusion: CT-based radiomics analysis based on the whole pancreas can distinguish cancer patients from healthy individuals, and it could potentially become an early detection tool for pancreatic cancer.
Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
Shuo Wang et al.
Technology in Cancer Research & Treatment Volume 21: 1-14 2022 - “Second, our study is a single-institution study without any external validation, which is one of the essential metrics for assessing the robustness of a study. Although we sought to improve the robustness of our study by randomizing the TCIA public dataset into our radiomic analysis and predictive analytics, the generalizability of our results remains to be further validated on new datasets. Third, although all the CT images we collected are the venous phases of the contrast CT, it is difficult to evaluate contrast enhancement variation since it depends on patient-specific physiology (eg, blood flow rate). Therefore, we did not study the feature stability against contrast enhancement variation among various patients.”
Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
Shuo Wang et al.
Technology in Cancer Research & Treatment Volume 21: 1-14 2022 - Conclusion: Our study proved that CT-based radiomics analysis and modeling can distinguish healthy individuals from pancreatic cancer patients, and potentially can become an effective tool to detect cancerous pancreatic tissue at an early stage.
Compute Tomography Radiomics Analysis on Whole Pancreas Between Healthy Individual and Pancreatic Ductal Adenocarcinoma Patients: Uncertainty Analysis and Predictive Modeling
Shuo Wang et al.
Technology in Cancer Research & Treatment Volume 21: 1-14 2022
Practice Management
- • Enteric contrast continues to play an important role in the imaging assessment of patients presenting to the emergency department, especially when combined with computed tomography in specific clinical situations to improve diagnostic accuracy.
• Enteric contrast is particularly helpful in assessing postoperative complications of abdominal surgeries such as anastomotic leaks and fistulas.
• Although not always administered routinely, enteric contrast can be useful to confirm bowel injuries in the setting of penetrating trauma. Enteric contrast can assist in the identification of the appendix in cases of suspected acute appendicitis. Enteric contrast is also effective at guiding operative versus nonoperative management of patients with small-bowel obstruction.
• Although enteric contrast is overall safe and well-tolerated, the benefits of using it should be weighed against potential risks to the patient, including the time required to administer enteric contrast potentially resulting in a delay in diagnosis.
The Use of Enteric Contrast in the Emergency Setting
Mohamed Z. Rajput et al.
Radiol Clin N Am 61 (2023) 37–51 - “Extravasation of enteric contrast has been identified as the most specific sign of an anastomotic leak. CT combined with enteric contrast provides the best diagnostic assessment for identifying the presence and location of a leak with excellent anatomic detail as well as showing additional important findings that may be otherwise clinically unsuspected. Knowledge of the type of surgery and anastomoses performed is critical before determining the appropriate method for administering enteric contrast. To evaluate suspected leaks from esophageal, gastric, or small-bowel anastomoses, including patients following bariatric surgery, enteric contrast is administered orally or via an enteric tube, followed by an appropriate delay before scanning to ensure contrast has reached the anastomotic site.”
The Use of Enteric Contrast in the Emergency Setting
Mohamed Z. Rajput et al.
Radiol Clin N Am 61 (2023) 37–51 - “CT with oral contrast has been shown to have a high negative predictive value similar to that of fluoroscopy, and shows even greater sensitivity than fluoroscopy, for diagnosing esophageal perforation. In contrast to luoroscopy, CT can also be used to evaluate for extra-esophageal abnormalities that may be contributing to the patient’s symptoms. Protocols vary by institution but typically include precontrast imaging, supine post-contrast imaging performed immediately after administration of enteric contrast orally or via gastric tube placed into the esophagus, and, if needed, prone postcontrast imaging.”
The Use of Enteric Contrast in the Emergency Setting
Mohamed Z. Rajput et al.
Radiol Clin N Am 61 (2023) 37–51 - “Enteric contrast can play an important role in the diagnosis and management of patients with smallbowel obstruction. Typically, enteric contrast is not initially administered to patients with suspected small-bowel obstruction before obtaining CT, as many of these patients are experiencing nausea and/or vomiting limiting any oral intake. In addition, positive intraluminal contrast may potentially obscure the bowel wall and imaging signs of ischemia on CT. Though if enteric contrast had been administered because small-bowel obstruction was not suspected, it may help delineate the transition point of an obstruction where intraluminal contrast abruptly stops.”
The Use of Enteric Contrast in the Emergency Setting
Mohamed Z. Rajput et al.
Radiol Clin N Am 61 (2023) 37–51 - “In conclusion, enteric contrast continues to play an important role in the imaging assessment of patients presenting to the emergency department.Although it may no longer be required to ensure diagnostic accuracy on a routine basis, enteric contrast remains valuable, particularly when used in a targeted fashion to address specific clinical questions on a case-by-case basis. Enteric contrast is safe and well-tolerated by most patients with a low risk of serious side effects. A recent survey revealed that most patients (89%) would prefer to drink oral contrast, even with only the slightest likelihood that this will improve diagnostic accuracy, rather than accepting a risk of a missed finding. Radiologists report increased diagnostic confidence and reader reliability in cases in which any type of enteric contrast is used for CT imaging. This can be particularly important in the emergency setting, where one encounters critical, life-threatening pathologies requiring confident and accurate diagnoses on a routine basis.”
The Use of Enteric Contrast in the Emergency Setting
Mohamed Z. Rajput et al.
Radiol Clin N Am 61 (2023) 37–51
- “Following Kotelnikov’s creation of the sampling theorem, computer scientist Alan Turing invented stored program computers and, soon after, his colleague, John von Neumann, produced the architecture to convert Turing’s idea into hardware to make it perform rapidly. By 1948, Baby, the first computer, was developed in Manchester, England. This was followed by the promulgation, in 1965, of Moore’s law, which stated that everything good about computers improves by an order of magnitude every 5 years.”
More From Moore's Law: The Journey to Toy Story and Implications for Radiology.
Smith AR, Lugo-Fagundo E, Fishman EK, Rowe SP, Chu LC.
J Am Coll Radiol. 2022 Apr;19(4):592-593. - “Although there is much optimism that AI will improve our diagnostic accuracy and efficiency, there is also concern that AI may potentially replace radiologists. This uncertainty has unfortunately dissuaded some medical students from pursing radiology. Although we do not yet know how AI will shape the future of radiology, our specialty can look back on our legacy as innovators and remain confident in our ability to navigate through this technological wave.”
More From Moore's Law: The Journey to Toy Story and Implications for Radiology.
Smith AR, Lugo-Fagundo E, Fishman EK, Rowe SP, Chu LC.
J Am Coll Radiol. 2022 Apr;19(4):592-593. - “In medicine and radiology, we are overly focused on the short-term: to care for an individual patient, to get through a clinical day, or to survive the challenges of the fiscal year. We need to “dream big” and set long-term, 5-year or 10-year plans to pursue projects that we feel passionate about and that we have the commitment to follow through.”
More From Moore's Law: The Journey to Toy Story and Implications for Radiology.
Smith AR, Lugo-Fagundo E, Fishman EK, Rowe SP, Chu LC.
J Am Coll Radiol. 2022 Apr;19(4):592-593. - “A number of years ago, we were approached by a Japanese company to make the first digital movie at Lucas- film based on the story of the monkey character in The Journey to the West. After running the numbers, however, I knew that given Moore’s law (now broadly understood to mean that technological progress results in the doubling of computer speed every 2 years), the technology was just not ready. We needed 5 more years before we could make their request a reality. To understand Moore’s law and computer graphics, we first need to understand the pixel, and to do that, we need to travel back to 19th- century France.”
More From Moore's Law: The Journey to Toy Story and Implications for Radiology.
Smith AR, Lugo-Fagundo E, Fishman EK, Rowe SP, Chu LC.
J Am Coll Radiol. 2022 Apr;19(4):592-593. - “Wonder Woman embodied additional qualities of empathy, intellect, peace, justice, and equality. The Wonder Woman comics mirrored shifts in traditional gender roles that were occurring after World War II. During the war, many women worked outside of the home to meet the demands of wartime industrial production. They worked in heavy industrial manufacturing plants that were previously dominated by men. This unleashed the genie in the bottle and instilled the idea that women could work along men as equals in the workforce, rather than staying at home. These changing attitudes paved the way for the women’s rights movement of the 1960s and 1970s.”
What Can Wonder Woman Teach Radiologists?,
Lynda Carter, Elliot K. Fishman, Steven P. Rowe, Linda C. Chu
JACR Volume 19, Issue 2, Part A, 2022, Pages 314-315, - “Wonder Woman served as an inspirational role model at a time when there were few role models in real life. She was a trailblazer who showed that she did not need to fit into the culturally expected mold. She embraced her unique qualities and forged her own path. Nowadays, we have high-profile women leaders such as US vice president Kamala Harris, longtime German chancellor Angela Merkel, and New Zealand prime minister Jacinda Ardern, who reinforce the idea that women can be strong leaders.”
What Can Wonder Woman Teach Radiologists?,
Lynda Carter, Elliot K. Fishman, Steven P. Rowe, Linda C. Chu
JACR Volume 19, Issue 2, Part A, 2022, Pages 314-315, - Many institutions are providing wellness or mindfulness training to physicians to combat burnout. Although these programs may help provide or enhance coping mechanisms and improve resilience, burnout rates are substantial even among the most resilient physicians, and physicians are not generally deficient in resilience compared with the general population. Our burnout is a stress fracture rather than an insufficiency fracture. We need to use our empathy superpowers to listen more and understand one another’s challenges. We need to “put one foot in front of the other” and strive toward systemic and organizational changes with open dialogue among radiologists and practice leaders to foster an environment of mutual trust, respect, and support.
What Can Wonder Woman Teach Radiologists?,
Lynda Carter, Elliot K. Fishman, Steven P. Rowe, Linda C. Chu
JACR Volume 19, Issue 2, Part A, 2022, Pages 314-315,
Trauma
- "The “hard” or overt signs of extremity arterial injury include active pulsatile bleeding; rapidly expanding hematoma; palpable thrill/audible bruit; or classic signs of severe acute limb ischemia (a.k.a. 5 “P”: pulselessness, pallor, paresthesia, pain, and paralysis). The presence of these hard signs correlates with high probability of vascular injury and need of invasive management. In cases where hard signs are present and intervention is indicated, exact localization and characterization of the vascular injury is necessary (ie, multiple extremity fractures or shotgun wound), and the trauma team may pursue CTA imaging if the clinical condition permits and the study can be obtained in a timely fashion.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “The “soft” signs of extremity arterial injury include history of arterial bleeding at the scene of trauma or in transit; proximity of a penetrating wound or blunt injury to an artery; small nonpulsatile hematoma over an artery; and neurologic deficit originating in a nerve adjacent to a named artery. The incidence of arterial injuries in such trauma patients ranges from 3% to 25%, depending on which individual soft sign or combination of signs is present. In patients presenting with soft signs and ankle brachial index (ABI) or arterial pressure index (API) less than 0.9, further imaging (CTA or duplex ultrasound) is usually indicated.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “The continuous advances of CT technology have improved image quality, permitted faster acquisition and imaging reconstruction times, and allowed incorporation of postprocessing techniques to routine readings with the use of curved multiplanar reformats, maximum intensity projection (MIP), bone subtraction, trajectography, and three dimensional (3D) volume-rendering.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “At our institution, the submillimeter isotropic voxel data set is routinely reconstructed at 1.5 and 3.0 mm in the conventional axial plane and submitted for evaluation. Multiplanar reconstructions on sagittal and coronal planes along the axis of the extremity as well as MIP images are also obtained by technologists at the scanner. 3D volume rendering images and curved planar reformats, including trajectography, can be requested or constructed using postprocessing software available on the workstations.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “There are 5 recognized types of acute vascular injuries with corresponding imaging findings.: (1) intimal tears (intimal flaps, surface disruptions, or subintimal/intramural hematomas), (2) full thickness vessel wall defects with pseudoaneurysms or hemorrhage, (3) complete transections with active hemorrhage and/or occlusion, (4) arteriovenous fistulas (AVF), and (5) spasm. Low-grade intimal injuries and/or intramural hematomas are more often associated with blunt trauma and can lead to secondary occlusion. Full thick wall defects, complete transections, and AVF usually occur with penetrating trauma. Spasm is a temporary finding more common in young patients, which can occur after blunt or penetrating trauma.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “Arterial transections occur when the circumference of the vessel is disrupted and usually leads to active contrast extravasation from the proximal segment and/or thrombotic occlusion of the disconnected distal artery. As for traumatic venous injuries in the extremity, wall defects in many peripheral veins seem to heal when local tissue pressure is applied which prevents significant extravasation of blood in most traumatic cases.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “Metallic projectiles retained in soft tissues, bone fragments, and orthopedic hardware can result in significant artifacts, commonly limiting the evaluation of adjacent vessels, and obscuring or creating“false” vascular injury imaging findings. Often, adequate contrast opacification of the vessels and the use of multiplanar reformats still alloevaluation of large vessels and the diagnosis of major traumatic injuries. In cases where the streak artifact precludes the evaluation of the vascular bed in question, DSA may be indicated to evaluate and exclude the presence of vascular injury. Recent imaging advancements using metal artifact reduction algorithms and/or DECT have shown to decrease metal and/or bone fragment artifacts, improving visualization of the of the soft-tissues and bones details, and as such can be useful to evaluate vascular injuries.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - • Peripheral vascular injuries account for 40% to 75% of all vascular injuries treated in civilian trauma centers.
• Extremity vascular injury is more often associated with penetrating trauma (75% to 80% of cases in urban trauma centers) than blunt trauma (5%–25% of cases), and among the penetrating mechanisms, more often after a gunshot wound than a stab wound.
• CTA is a highly effective tool for the detection and characterization of peripheral vascular injuries with proven outstanding sensitivities in the range of 95% to 100%, specificities of 87% to 100%, and accuracy around 93%.
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - • Patient preparation is key to obtain optimal diagnostic images of the peripheral vessels. Adequate IV access, iodine contrast flow, patient position, and lack of motion are all important to avoid the formation of imaging artifacts and allow adequate imaging evaluation.
• AVF is differentiated from asymmetric hyperemia and early venous return on the injured extremity by having the contrast density in the opacified venous segment of the fistula approaching the adjacent artery.
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150
Vascular
- "The “hard” or overt signs of extremity arterial injury include active pulsatile bleeding; rapidly expanding hematoma; palpable thrill/audible bruit; or classic signs of severe acute limb ischemia (a.k.a. 5 “P”: pulselessness, pallor, paresthesia, pain, and paralysis). The presence of these hard signs correlates with high probability of vascular injury and need of invasive management. In cases where hard signs are present and intervention is indicated, exact localization and characterization of the vascular injury is necessary (ie, multiple extremity fractures or shotgun wound), and the trauma team may pursue CTA imaging if the clinical condition permits and the study can be obtained in a timely fashion.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “The “soft” signs of extremity arterial injury include history of arterial bleeding at the scene of trauma or in transit; proximity of a penetrating wound or blunt injury to an artery; small nonpulsatile hematoma over an artery; and neurologic deficit originating in a nerve adjacent to a named artery. The incidence of arterial injuries in such trauma patients ranges from 3% to 25%, depending on which individual soft sign or combination of signs is present. In patients presenting with soft signs and ankle brachial index (ABI) or arterial pressure index (API) less than 0.9, further imaging (CTA or duplex ultrasound) is usually indicated.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “The continuous advances of CT technology have improved image quality, permitted faster acquisition and imaging reconstruction times, and allowed incorporation of postprocessing techniques to routine readings with the use of curved multiplanar reformats, maximum intensity projection (MIP), bone subtraction, trajectography, and three dimensional (3D) volume-rendering.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “At our institution, the submillimeter isotropic voxel data set is routinely reconstructed at 1.5 and 3.0 mm in the conventional axial plane and submitted for evaluation. Multiplanar reconstructions on sagittal and coronal planes along the axis of the extremity as well as MIP images are also obtained by technologists at the scanner. 3D volume rendering images and curved planar reformats, including trajectography, can be requested or constructed using postprocessing software available on the workstations.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “There are 5 recognized types of acute vascular injuries with corresponding imaging findings.: (1) intimal tears (intimal flaps, surface disruptions, or subintimal/intramural hematomas), (2) full thickness vessel wall defects with pseudoaneurysms or hemorrhage, (3) complete transections with active hemorrhage and/or occlusion, (4) arteriovenous fistulas (AVF), and (5) spasm. Low-grade intimal injuries and/or intramural hematomas are more often associated with blunt trauma and can lead to secondary occlusion. Full thick wall defects, complete transections, and AVF usually occur with penetrating trauma. Spasm is a temporary finding more common in young patients, which can occur after blunt or penetrating trauma.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “Arterial transections occur when the circumference of the vessel is disrupted and usually leads to active contrast extravasation from the proximal segment and/or thrombotic occlusion of the disconnected distal artery. As for traumatic venous injuries in the extremity, wall defects in many peripheral veins seem to heal when local tissue pressure is applied which prevents significant extravasation of blood in most traumatic cases.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - “Metallic projectiles retained in soft tissues, bone fragments, and orthopedic hardware can result in significant artifacts, commonly limiting the evaluation of adjacent vessels, and obscuring or creating“false” vascular injury imaging findings. Often, adequate contrast opacification of the vessels and the use of multiplanar reformats still alloevaluation of large vessels and the diagnosis of major traumatic injuries. In cases where the streak artifact precludes the evaluation of the vascular bed in question, DSA may be indicated to evaluate and exclude the presence of vascular injury. Recent imaging advancements using metal artifact reduction algorithms and/or DECT have shown to decrease metal and/or bone fragment artifacts, improving visualization of the of the soft-tissues and bones details, and as such can be useful to evaluate vascular injuries.”
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - • Peripheral vascular injuries account for 40% to 75% of all vascular injuries treated in civilian trauma centers.
• Extremity vascular injury is more often associated with penetrating trauma (75% to 80% of cases in urban trauma centers) than blunt trauma (5%–25% of cases), and among the penetrating mechanisms, more often after a gunshot wound than a stab wound.
• CTA is a highly effective tool for the detection and characterization of peripheral vascular injuries with proven outstanding sensitivities in the range of 95% to 100%, specificities of 87% to 100%, and accuracy around 93%.
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150 - • Patient preparation is key to obtain optimal diagnostic images of the peripheral vessels. Adequate IV access, iodine contrast flow, patient position, and lack of motion are all important to avoid the formation of imaging artifacts and allow adequate imaging evaluation.
• AVF is differentiated from asymmetric hyperemia and early venous return on the injured extremity by having the contrast density in the opacified venous segment of the fistula approaching the adjacent artery.
Computer Tomography Angiography of Peripheral Vascular Injuries
Fabio M. Paes, MD, Felipe Munera
Radiol Clin N Am 61 (2023) 141–150
