Utility of CT Radiomics Features in Differentiation of Pancreatic Ductal Adenocarcinoma From Normal Pancreatic Tissue

• Published in: American journal of roentgenology (1976) Vol. 213; no. 2; pp. 349 - 357
• Main Authors: Chu, Linda C., Park, Seyoun, Kawamoto, Satomi, Fouladi, Daniel F., Shayesteh, Shahab, Zinreich, Eva S., Graves, Jefferson S., Horton, Karen M., Hruban, Ralph H., Yuille, Alan L., Kinzler, Kenneth W., Vogelstein, Bert, Fishman, Elliot K.
• Format: Journal Article
• Language: English
• Published: United States 01.08.2019
• Subjects: Adenocarcinoma - diagnostic imaging; Adenocarcinoma - pathology; Aged; Carcinoma, Pancreatic Ductal - diagnostic imaging; Carcinoma, Pancreatic Ductal - pathology; Contrast Media; Diagnosis, Differential; Female; Humans; Imaging, Three-Dimensional; Iohexol; Male; Middle Aged; Pancreatic Neoplasms - diagnostic imaging; Pancreatic Neoplasms - pathology; Phenotype; Sensitivity and Specificity; Tomography, X-Ray Computed - methods; Tumor Burden; CT; radiomics; random forest classification; pancreatic ductal adenocarcinoma
• ISSN: 0361-803X; 1546-3141; 1546-3141
• DOI: 10.2214/AJR.18.20901

The objective of our study was to determine the utility of radiomics features in differentiating CT cases of pancreatic ductal adenocarcinoma (PDAC) from normal pancreas. In this retrospective case-control study, 190 patients with PDAC (97 men, 93 women; mean age ± SD, 66 ± 9 years) from 2012 to 2017 and 190 healthy potential renal donors (96 men, 94 women; mean age ± SD, 52 ± 8 years) without known pancreatic disease from 2005 to 2009 were identified from radiology and pathology databases. The 3D volume of the pancreas was manually segmented from the preoperative CT scans by four trained researchers and verified by three abdominal radiologists. Four hundred seventy-eight radiomics features were extracted to express the phenotype of the pancreas. Forty features were selected for analysis because of redundancy of computed features. The dataset was divided into 255 training cases (125 normal control cases and 130 PDAC cases) and 125 validation cases (65 normal control cases and 60 PDAC cases). A random forest classifier was used for binary classification of PDAC versus normal pancreas of control cases. Accuracy, sensitivity, and specificity were calculated. Mean tumor size was 4.1 ± 1.7 (SD) cm. The overall accuracy of the random forest binary classification was 99.2% (124/125), and AUC was 99.9%. All PDAC cases (60/60) were correctly classified. One case from a renal donor was misclassified as PDAC (1/65). The sensitivity was 100%, and specificity was 98.5%. Radiomics features extracted from whole pancreas can be used to differentiate between CT cases from patients with PDAC and healthy control subjects with normal pancreas.