Imaging prediction of KRAS mutation in patients with rectal cancer through deep metric learning using pretreatment [18F]Fluorodeoxyglucose positron emission tomography/computed tomography

Abstract

Objectives: To predict KRAS mutation in rectal cancer (RC) through computer vision of [18F]fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) by using metric learning (ML). Methods: This study included 160 patients with RC who had undergone preoperative PET/CT. KRAS mutation was identified through polymerase chain reaction analysis. This model combined ML with the deep-learning framework to analyze PET data with or without CT images. The Batch Balance Wrapper framework and K-fold cross-validation were employed during the learning process. A receiver operating characteristic (ROC) curve analysis was performed to assess the model’s predictive performance. Results: Genetic alterations in KRAS were identified in 82 (51%) tumors. Both PET and CT images were used, and the proposed model had an area under the ROC curve of 0.836 for its ability to predict a mutation status. The sensitivity, specificity, and accuracy were 75.3%, 79.3%, and 77.5%, respectively. When PET images alone were used, the area under the curve was 0.817, whereas the sensitivity, specificity, and accuracy were 73.2%, 79.6%, and 76.2%, respectively. Conclusions: The ML model presented herein revealed that baseline 18F-FDG PET/CT images could provide supplemental information to determine KRAS mutation in RC. Additional studies are required to maximize the predictive accuracy. Advances in knowledge The results of the ML model presented herein indicate that baseline 18F-FDG PET/CT images could provide supplemental information for determining KRAS mutation in RC. The predictive accuracy of the model was 77.5% when both image types were used and 76.2% when PET images alone were used. Additional studies are required to maximize the predictive accuracy.