”Radiomics refers to the extraction of mineable high-dimensional data from radiologic images and has been applied within oncology to improve diagnosis and prognostication with the aim of delivering precision medicine. The premise is that imaging data convey meaningful information about tumor biology, behavior, and pathophysiology and may reveal information that is not otherwise apparent to current radiologic and clinical interpretation.”
Radiomics in Oncology: A Practical Guide 
Joshua D. Shur, et al.
RadioGraphics 2021; 41:1717–1732

Radiomics in Oncology: A Practical Guide 
Joshua D. Shur, et al.
RadioGraphics 2021; 41:1717–1732

Radiomics in Oncology: A Practical Guide 
Joshua D. Shur, et al.
RadioGraphics 2021; 41:1717–1732

“Once clinical and radiomic data are collected and curated, statistical models are fitted to predict study endpoints, such as tumor type or survival time. A typical model uses input features (including the radiomic features described previously and clinical features such as tumor markers or lymph node status) in addition to target data that the model aims to predict, such as benign versus malignant or risk of recurrence. The final performance and generalizability of models discovered from a radiomic analysis is determined by validating the model on new test data.”
Radiomics in Oncology: A Practical Guide 
Joshua D. Shur, et al.
RadioGraphics 2021; 41:1717–1732

Recent applications of radiomics in pancreatic imaging:

• Detection
• Classification
• Prognostication

• Radiomics is the high throughput extraction and analysis of quantitative features from medical images
• Extraction of quantifiable imaging markers based on tumor signal intensity, shape, and texture
• Application of these imaging markers for disease diagnosis and prognostication

Gillies RJ et al. Radiology. 2016;278:563-77.

• Tumors are spatially heterogeneous structures
• Heterogeneity can be quantified on imaging data
• Radiomics converts this imaging data into high dimensional mineable feature space

Kumar V et al. Magn Reson Imaging. 2012;30(9):4-48. Aerts HJ et al. Nat Commun. 2014;5:4006.
Gillies RJ et al. Radiology. 2016;278(2):563-577.

“Radiomics converts medical images such as CT scans into high-throughput quantitative data that can be used to improve diagnostic, prognostic, and predictive accuracy. Indeed, radiomics can provide objective and comprehensive information regarding whole or subregions of cancers in a noninvasive and repeatable way. Radiomic signatures have been demonstrated to reflect intratumoral heterogeneity and to be associated with gene-expression profiles, both of which can serve as important prognostic factors.”
Can Artificial Intelligence Fix the Reproducibility Problem of Radiomics? 
Park CM
Radiology 2019; 00:1–2 • https://doi.org/10.1148/radiol.2019191154

• Radiomics features can be classified into first-order, shape, second-order, and high-order statistical outputs:
• First-order statistics:
  • Distribution of individual voxel values
  • Histogram-based methods
  • Mean, median, maximum, minimum
  • Uniformity, entropy, skewness, kurtosis, etc.

Kumar V et al. Magn Reson Imaging. 2012;30(9):4-48. Aerts HJ et al. Nat Commun. 2014;5:4006.
Gillies RJ et al. Radiology. 2016;278(2):563-577.

First-order statistics:

Kumar V et al. Magn Reson Imaging. 2012;30(9):4-48. Aerts HJ et al. Nat Commun. 2014;5:4006.
Gillies RJ et al. Radiology. 2016;278(2):563-577. Lubner MG et al. RadioGraphics. 2017;37:1483-1503.

Shape can be quantified through a combination of shape features such as:

• Compactness
• Max 3D diameter
• Spherical disproportion
• Sphericity
• Surface area
• Surface/volume ratio
• Volume

Kumar V et al. Magn Reson Imaging. 2012;30(9):4-48. Aerts HJ et al. Nat Commun. 2014;5:4006.
Gillies RJ et al. Radiology. 2016;278(2):563-577.

Second-order statistics (texture features):

• Statistical interrelationships between voxels of similar contrast values
• Gray-level co-occurrence matrix (GLCM)
• Gray-level run length matrix (GLRM)

Kumar V et al. Magn Reson Imaging. 2012;30(9):4-48. Aerts HJ et al. Nat Commun. 2014;5:4006.
Gillies RJ et al. Radiology. 2016;278(2):563-577.

Higher-order statistics:

• Impose filter grids to extract repetitive or nonrepetitive patterns
• Wavelet: Passes image through low pass or high pass filters in x, y, and z direction
• Laplacian and Gaussian:
  • Gaussian filter smooths the image
  • Laplacian filter detects the edge

Kumar V et al. Magn Reson Imaging. 2012;30(9):4-48. Aerts HJ et al. Nat Commun. 2014;5:4006.
Gillies RJ et al. Radiology. 2016;278(2):563-577.

Extracted 478 radiomics features from CTs of whole 3D pancreas volume to differentiate 190 PDAC vs. 190 normal controls

Chu LC et al. AJR

• 40 radiomics features were selected for random forest classifier
• Validation dataset (n = 125)
  • 60 PDAC + 65 normal controls
• Overall accuracy: 99.2% (124/125)
• Sensitivity: 100% (60/60)
• Specificity: 98.5% (64/65)

Radiomics features can achieve high accuracy in detection of PDAC

Top 5 maximally relevant features included:

• Texture – Heterogeneous texture
• Shape – Less spherical disproportion
• Wavelets – Textural pattern change at the border of the tumor or dilated pancreatic duct

Chu LC et al. AJR in press

“Our results showed that, after manual segmentation of pancreas boundaries, radiomics features and the random forest classifier were highly accurate in differentiating PDAC cases from normal control cases (sensitivity, 100%; specificity, 98.5%; accuracy, 99.2%). The radiomics features most relevant to differentiate PDAC from normal pancreas were based on shape and textural heterogeneity.”
Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue 
Chu LC, Park S, Kawamoto S, Fouladi DF, Shayesteh S, Zinreich ES, Graves JS, Horton KM, Hruban RH, Yuille AL, Kinzler KW, Vogelstein B, Fishman EK.
AJR Am J Roentgenol. 2019 Apr 23:1-9.

“CT features of early PDAC can be subtle and missed by even experienced radiologists. Early signs of PDAC such as pancreatic parenchyma inhomogeneity and loss of normal fatty marbling of the pancreas have been described on retrospective CT review up to 34 months before the diagnosis of PDAC. Quantitative analysis of these imaging features offers the potential for computer-aided diagnosis of PDAC.” 
Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue 
Chu LC, Park S, Kawamoto S, Fouladi DF, Shayesteh S, Zinreich ES, Graves JS, Horton KM, Hruban RH, Yuille AL, Kinzler KW, Vogelstein B, Fishman EK.
AJR Am J Roentgenol. 2019 Apr 23:1-9.

“Given the high accuracy of automatic pan- creas segmentation by existing algorithms, these algorithms could be used to generate the boundaries for pancreas segmentation, and then the radiomics feature analysis algorithm could be performed to differentiate PDAC from normal pancreas. Some technical hurdles need to be overcome before these complex algorithms can be combined, but we anticipate that will be possible in the near future.”
Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue 
Chu LC, Park S, Kawamoto S, Fouladi DF, Shayesteh S, Zinreich ES, Graves JS, Horton KM, Hruban RH, Yuille AL, Kinzler KW, Vogelstein B, Fishman EK.
AJR Am J Roentgenol. 2019 Apr 23:1-9.

”All of the scans in the current study were obtained at a single institution on units manufactured by a single vendor using matched protocols and the same reconstruction algorithm. Differences in image acquisition, reconstruction, segmentation, and feature extraction can affect radiomics features and results. There is currently no standardization in the optimal protocol for imaging acquisition and postprocessing for radiomics analysis.”
Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue 
Chu LC, Park S, Kawamoto S, Fouladi DF, Shayesteh S, Zinreich ES, Graves JS, Horton KM, Hruban RH, Yuille AL, Kinzler KW, Vogelstein B, Fishman EK.
AJR Am J Roentgenol. 2019 Apr 23:1-9.

“Based on the selected radiomics features, a random survival forest was applied for survival prediction in a multivariate dataset with missing variables. Each decision node was divided until three unique deaths (d = 3) remained in the leaf node. Ten thousand trees were built by the training set using the AUC for the split of internal nodes. Each end node stored the survival sta- tus (dead or alive), survival time, and a Cox proportional hazard function of the assigned cases. The survival time and survival status predictions in the validation cohort were determined by majority voting based on the trained trees.”
CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma 
Seyoun Park et al.
AJR 2021; 217:1104–1112

CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma 
Seyoun Park et al.
AJR 2021; 217:1104–1112

OBJECTIVE. Pancreatic ductal adenocarcinoma (PDAC) is often a lethal malignancy with limited preoperative predictors of long-term survival. The purpose of this study was to evaluate the prognostic utility of preoperative CT radiomics features in predict- ing postoperative survival of patients with PDAC. 
RESULTS. The mean age of patients with PDAC was 67 ± 11 (SD) years. The mean tumor size was 3.31 ± 2.55 cm. The 10 most relevant radiomics features showed 82.2% ac- curacy in the classification of high-risk versus low-risk groups. The C-index of survival prediction with clinical parameters alone was 0.6785. The addition of CT radiomics features improved the C-index to 0.7414. 
CONCLUSION. Addition of CT radiomics features to standard clinical factors improves survival prediction in patients with PDAC. 
CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma 
Seyoun Park et al.
AJR 2021; 217:1104–1112

CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma 
Seyoun Park et al.
AJR 2021; 217:1104–1112

CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma 
Seyoun Park et al.
AJR 2021; 217:1104–1112

”We found that radiomics features extracted from tumors and from the nonneoplastic pancreas can be used to improve survival prediction models of patients who underwent surgery for PDAC. This algorithm could be combined with other pathologic and genetic biomarkers.”
CT Radiomics–Based Preoperative Survival Prediction in Patients With Pancreatic Ductal Adenocarcinoma 
Seyoun Park et al.
AJR 2021; 217:1104–1112

• Autoimmune pancreatitis (AIP) shares overlapping clinical and imaging features as PDAC
• Importantly, treatment and prognosis for these two conditions vary dramatically
• Retrospective matched case-control study with 32 AIP and 40 PDAC cases

Kawamoto S et al. Manuscript in preparation

• AIP was suspected or included in the differential diagnosis of the CT reports in 47% of cases
• Radiomics analysis of AIP vs. PDAC:
  • Accuracy 94.4%
  • Sensitivity 95.0%
  • Specificity 93.8%

Radiomics features can differentiate AIP from PDAC, which has important treatment implications

Purpose: The purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).
Conclusions: Radiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%.
Differentiating autoimmune pancreatitis from pancreatic ductal adenocarcinoma with CT radiomics features.
Park S, Chu LC, Hruban RH, Vogelstein B, Kinzler KW, Yuille AL, Fouladi DF, Shayesteh S, Ghandili S, Wolfgang CL, Burkhart R, He J, Fishman EK, Kawamoto S.
Diagn Interv Imaging. 2020 Sep;101(9):555-564.

Background: Current imaging methods for prediction of complete margin resection (R0) in patients with pancreatic ductal adeno- carcinoma (PDAC) are not reliable. 
Purpose: To investigate whether tumor-related and perivascular CT radiomic features improve preoperative assessment of arterial involvement in patients with surgically proven PDAC. 
Conclusion: A model based on tumor-related and perivascular CT radiomic features improved the detection of superior mesenteric artery involvement in patients with pancreatic ductal adenocarcinoma. 
CT Radiomic Features of Superior Mesenteric Artery Involvement in Pancreatic Ductal Adenocarcinoma: A Pilot Study 
Francesca Rigiroli et al.
Radiology 2021; 000:1–13 • https://doi.org/10.1148/radiol.2021210699

Purpose: Grades of pancreatic neuroendocrine neoplasms (PNENs) are associated with the choice of treatment strategies. Texture analysis has been used in tumor diagnosis and staging evaluation. In this study, we aim to evaluate the potential ability of texture parameters in differentiation of PNENs grades. 
Results: There were significant differences in tumor margin, pancreatic duct dilatation, lymph nodes invasion, size, portal enhancement ratio (PER), arterial enhancement ratio (AER), mean grey-level intensity, kurtosis, entropy, and uniformity among G1, G2, and pancreatic neuroendocrine carcinoma (PNEC) G3 (p < 0.01). 
Conclusions: Our data indicated that texture parameters have potential in grading PNENs, in particular in differentiating PNEC G3 from PNETs G1/G2. 
Textural analysis on contrast-enhanced CT in pancreatic neuroendocrine neoplasms: association with WHO grade 
Chuangen Guo et al.
Abdom Radiol (2019) 44:576–585

Textural analysis on contrast-enhanced CT in pancreatic neuroendocrine neoplasms: association with WHO grade 
Chuangen Guo et al.
Abdom Radiol (2019) 44:576–585