Deep learning system for automated detection of posterior ligamentous complex injury in patients with thoracolumbar fracture on MRI

Abstract

Abstract This study aimed to develop a deep learning (DL) algorithm for automated detection and localization of posterior ligamentous complex (PLC) injury in patients with acute thoracolumbar (TL) fracture on magnetic resonance imaging (MRI) and evaluate its diagnostic performance. In this retrospective and multicenter study, using midline sagittal T2-weighted image with fracture (± PLC injury), a training dataset and internal and external validation sets of 300, 100, and 100 patients, were constructed with equal numbers of injured and normal PLCs. The DL algorithm was developed through two steps (Attention U-net and Inception-ResNet-V2). We evaluate the diagnostic performance for PLC injury between the DL algorithm and radiologists with different levels of experience. The area under the curve generated by the DL algorithm were 0.928, 0.916 for internal and external validations, and by two radiologists for observer performance test were 0.930, 0.830 respectively. There was no significant difference in diagnosing PLC injury by the DL algorithm and the radiologists. However, there was significant difference between the DL algorithm and the radiology trainee, showing significant improvement with the DL algorithm assistance. Therefore, DL algorithm detected PLC injury in patients with acute TL fracture with high diagnostic performance.