Two-stage multi-task deep learning framework for simultaneous pelvic bone segmentation and landmark detection from CT images.

Journal: International journal of computer assisted radiology and surgery
PMID: 37322299

Abstract

PURPOSE: Pelvic bone segmentation and landmark definition from computed tomography (CT) images are prerequisite steps for the preoperative planning of total hip arthroplasty. In clinical applications, the diseased pelvic anatomy usually degrades the accuracies of bone segmentation and landmark detection, leading to improper surgery planning and potential operative complications.

Authors

  • Haoyu Zhai
    School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, Dalian, 116024, China.
  • Zhonghua Chen
    School of Biomedical Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China.
  • Lei Li
    Department of Thoracic Surgery, The Affiliated Huaian No.1 People's Hospital of Nanjing Medical University, Huai'an, China.
  • Hairong Tao
    Shanghai Key Laboratory of Orthopaedic Implants, Shanghai, 200011, China.
  • Jinwu Wang
    Research Institute of Med-X, Shanghai Jiao Tong University, Shanghai, China.
  • Kang Li
    Department of Otolaryngology, Longgang Otolaryngology hospital & Shenzhen Key Laboratory of Otolaryngology, Shenzhen Institute of Otolaryngology, Shenzhen, Guangdong, China.
  • Moyu Shao
    Jiangsu Yunqianbai Digital Technology Co., LTD, Xuzhou, 221000, China.
  • Xiaomin Cheng
    Jiangsu Yunqianbai Digital Technology Co., LTD, Xuzhou, 221000, China.
  • Jing Wang
    Endoscopy Center, Peking University Cancer Hospital and Institute, Beijing, China.
  • Xiang Wu
  • Chuan Wu
    Department of Computer Science, University of Hong Kong, 999077, Hong Kong, China.
  • Xiao Zhang
    Merck & Co., Inc., Rahway, NJ, USA.
  • Lauri Kettunen
  • Hongkai Wang

Keywords

External Resources

Popular Topics
Recent Journals