Automated Traumatic Bleeding Detection in Whole-Body CT Using 3D Object Detection Model

This is the authors' abstract. We don't add key points for this paper.

Traumatic injury remains a major cause of death worldwide, with bleeding being one of its most critical and life-threatening consequences. Whole-body computed tomography (WBCT) has become a standard diagnostic method in trauma settings; however, timely interpretation remains challenging for acute care physicians. In this study, we propose a new automated method for detecting traumatic bleeding in CT images using a three-dimensional object detection model enhanced with an atrous spatial pyramid pooling (ASPP) module. Furthermore, we incorporate a false positive (FP) reduction approach based on multi-organ segmentation, as developed in our previous study. The proposed method was evaluated on a multi-institutional dataset of delayed-phase contrast-enhanced CT images using a six-fold cross-validation approach. It achieved a maximum sensitivity of 90.0% with 587.3 FPs per case and a sensitivity of 70.0% with 46.9 FPs per case, outperforming previous segmentation-based methods. In addition, the average processing time was reduced to 4.2 ± 1.1 min. These results suggest that the proposed method enables rapid and accurate bleeding detection, demonstrating its potential for clinical application in emergency trauma care.