Abdominal and Pelvic ImagingHistogram-Based Discrimination of Intravenous Contrast in Abdominopelvic Computed TomographyCheng, Phillip M. MD, MS Author Information From the Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA. Received for publication March 15, 2015; accepted November 15, 2015. Correspondence to: Phillip M. Cheng, MD, MS, USC Norris Cancer Center & Hospital, 1441 Eastlake Ave, Suite 2315B, Los Angeles, CA 90033-0377 (e-mail: [email protected]). The author declares no conflict of interest. Journal of Computer Assisted Tomography: March/April 2016 - Volume 40 - Issue 2 - p 234-237 doi: 10.1097/RCT.0000000000000361 Buy Metrics Abstract Objective The aim of this study was to evaluate the accuracy of fully automated machine learning methods for detecting intravenous contrast in computed tomography (CT) studies of the abdomen and pelvis. Methods A set of 591 labeled CT image volumes of the abdomen and pelvis was obtained from 5 different CT scanners, of which 434 (73%) were performed with intravenous contrast. A stratified split of this set was performed into training and test sets of 443 and 148 studies, respectively. Subsequently, support vector machine and logistic regression classifiers were trained using 5-fold cross-validation for parameter optimization. Results The best in-sample performance was seen with a support vector machine classifier with a χ2 kernel (98.9% accuracy); however, test set performance was similar across the trained classifiers, with 95% to 97% accuracy. Conclusions Histogram-based automated classifiers for the presence of intravenous contrast are accurate and may be useful for verifying the accurate labeling of the presence of intravenous contrast in CT body studies. Copyright © 2016 Wolters Kluwer Health, Inc. All rights reserved.