Automated Identification of Skull Fractures With Deep Learning: A Comparison Between Object Detection and Segmentation Approach

Objective: Skull fractures caused by head trauma can lead to life-threatening complications. Hence, timely and accurate identification of fractures is of great importance. Therefore, this study aims to develop a deep learning system for automated identification of skull fractures from cranial computed tomography (CT) scans. Method: This study retrospectively analyzed CT scans of 4,782 patients (median age, 54 years; 2,583 males, 2,199 females; development set: n = 4,168, test set: n = 614) diagnosed with skull fractures between September 2016 and September 2020. Additional data of 7,856 healthy people were included in the analysis to reduce the probability of false detection. Skull fractures in all the scans were manually labeled by seven experienced neurologists. Two deep learning approaches were developed and tested for the identification of skull fractures. In the first approach, the fracture identification task was treated as an object detected problem, and a YOLOv3 network was trained to identify all the instances of skull fracture. In the second approach, the task was treated as a segmentation problem and a modified attention U-net was trained to segment all the voxels representing skull fracture. The developed models were tested using an external test set of 235 patients (93 with, and 142 without skull fracture). Results: On the test set, the YOLOv3 achieved average fracture detection sensitivity and specificity of 80.64, and 85.92%, respectively. On the same dataset, the modified attention U-Net achieved a fracture detection sensitivity and specificity of 82.80, and 88.73%, respectively. Conclusion: Deep learning methods can identify skull fractures with good sensitivity. The segmentation approach to fracture identification may achieve better results.