Automatic Pelvic Fracture Segmentation: A Deep Learning Approach and Benchmark Dataset

Yanzhen Liu ¹ Sutuke Yibulayimu ¹ Gang Zhu ² Chao Shi ¹ Chendi Liang ¹ Chunpeng Zhao ³ Xinbao Wu ³ Yudi Sang ^2* Yu Wang ^1*

• ¹ Beihang University, Beijing, Beijing Municipality, China
• ² Beijing Rossum Robot Technology Co., Ltd., Beijing, China
• ³ Beijing Jishuitan Hospital, Beijing, Beijing Municipality, China

Accurate segmentation of pelvic fractures from computed tomography (CT) is crucial for trauma diagnosis and image-guided reduction surgery. The traditional manual slice-by-slice segmentation by surgeons is time-consuming, experience-dependent, and error-prone. The complex anatomy of the pelvic bone, the diversity of fracture types, and the variability in fracture surface appearances pose significant challenges to automated solutions. We propose an automatic pelvic fracture segmentation method based on deep learning, which effectively isolates hipbone and sacrum fragments from fractured pelvic CT. The method employs two sequential networks: an anatomical segmentation network for extracting hipbones and sacrum from CT images, followed by a fracture segmentation network that isolates the main and minor fragments within each bone region. We propose a distance-weighted loss to guide the fracture segmentation network's attention on the fracture surface. Additionally, multi-scale deep supervision and smooth transition strategies are incorporated to enhance overall performance. Tested on a curated dataset of 150 CTs, which we have made publicly available, our method achieves an average Dice coefficient of 0.986 and an average symmetric surface distance of 0.234 mm. The method outperformed traditional max-flow and a transformer-based method, demonstrating its effectiveness in handling complex fracture.