Development and Validation of an Image-based Deep Learning Algorithm for Detection of Synchronous Peritoneal Carcinomatosis in Colorectal Cancer

Abstract

Objective: The aim of this study was to build a SVM classifier using ResNet-3D algorithm by artificial intelligence for prediction of synchronous PC.

Background: Adequate detection and staging of PC from CRC remain difficult.

Methods: The primary tumors in synchronous PC were delineated on preoperative contrast-enhanced computed tomography (CT) images. The features of adjacent peritoneum were extracted to build a ResNet3D + SVM classifier. The performance of ResNet3D + SVM classifier was evaluated in the test set and was compared to routine CT which was evaluated by radiologists.

Results: The training set consisted of 19,814 images from 54 patients with PC and 76 patients without PC. The test set consisted of 7837 images from 40 test patients. The ResNet-3D spent only 34 seconds to analyze the test images. To increase the accuracy of PC detection, we have built a SVM classifier by integrating ResNet-3D features with twelve PC-specific features (P < 0.05). The ResNet3D + SVM classifier showed accuracy of 94.11% with AUC of 0.922 (0.912-0.944), sensitivity of 93.75%, specificity of 94.44%, positive predictive value (PPV) of 93.75%, and negative predictive value (NPV) of 94.44% in the test set. The performance was superior to routine contrast-enhanced CT (AUC: 0.791).

Conclusions: The ResNet3D + SVM classifier based on deep learning algorithm using ResNet-3D framework has shown great potential in prediction of synchronous PC in CRC.