Improved Pancreatic Cancer Detection and Localization on CT Scans: A Computer-Aided Detection Model Utilizing Secondary Features

Simple Summary Pancreatic ductal adenocarcinoma (PDAC) is one of the most aggressive cancers, and most patients present with advanced or irresectable disease due to late recognition. Radiological imaging modalities such as CT scans are key in providing information on the presence or absence of tumors. However, an assessment of pancreatic cancer requires specific radiological expertise, and small tumors are easily overlooked. Computer-aided detection (CAD) using artificial intelligence (AI) techniques is promising and may help in the early detection of pancreatic tumors. In this study, we developed a deep learning-based tumor detection framework that can detect pancreatic head cancer on CT scans with high accuracy when incorporating clinically relevant information. We demonstrate that a tumor detection framework utilizing CT scans and secondary signs of pancreatic tumors results in an increased detection accuracy for the detection of pancreatic head tumors.Abstract The early detection of pancreatic ductal adenocarcinoma (PDAC) is essential for optimal treatment of pancreatic cancer patients. We propose a tumor detection framework to improve the detection of pancreatic head tumors on CT scans. In this retrospective research study, CT images of 99 patients with pancreatic head cancer and 98 control cases from the Catharina Hospital Eindhoven were collected. A multi-stage 3D U-Net-based approach was used for PDAC detection including clinically significant secondary features such as pancreatic duct and common bile duct dilation. The developed algorithm was evaluated using a local test set comprising 59 CT scans. The model was externally validated in 28 pancreatic cancer cases of a publicly available medical decathlon dataset. The tumor detection framework achieved a sensitivity of 0.97 and a specificity of 1.00, with an area under the receiver operating curve (AUROC) of 0.99, in detecting pancreatic head cancer in the local test set. In the external test set, we obtained similar results, with a sensitivity of 1.00. The model provided the tumor location with acceptable accuracy obtaining a DICE Similarity Coefficient (DSC) of 0.37. This study shows that a tumor detection framework utilizing CT scans and secondary signs of pancreatic cancer can detect pancreatic tumors with high accuracy.