A Two stage deep learning network for automated femoral segmentation in bilateral lower limb CT scans.

Journal: Scientific reports
PMID:

Abstract

This study presents the development of a deep learning-based two-stage network designed for the efficient and precise segmentation of the femur in full lower limb CT images. The proposed network incorporates a dual-phase approach: rapid delineation of regions of interest followed by semantic segmentation of the femur. The experimental dataset comprises 100 samples obtained from a hospital, partitioned into 85 for training, 8 for validation, and 7 for testing. In the first stage, the model achieves an average Intersection over Union of 0.9671 and a mean Average Precision of 0.9656, effectively delineating the femoral region with high accuracy. During the second stage, the network attains an average Dice coefficient of 0.953, sensitivity of 0.965, specificity of 0.998, and pixel accuracy of 0.996, ensuring precise segmentation of the femur. When compared to the single-stage SegResNet architecture, the proposed two-stage model demonstrates faster convergence during training, reduced inference times, higher segmentation accuracy, and overall superior performance. Comparative evaluations against the TransUnet model further highlight the network's notable advantages in accuracy and robustness. In summary, the proposed two-stage network offers an efficient, accurate, and autonomous solution for femur segmentation in large-scale and complex medical imaging datasets. Requiring relatively modest training and computational resources, the model exhibits significant potential for scalability and clinical applicability, making it a valuable tool for advancing femoral image segmentation and supporting diagnostic workflows.

Authors

  • Wenqing Xie
    Kidney Disease Center, The First Affiliated Hospital, College of Medicine, Zhejiang University, 79 Qingchun Road, Hangzhou, 310003, Zhejiang, China.
  • Peng Chen
  • Zhigang Li
    Hefei Institute of Physical Science, Chinese Academy of Sciences Hefei 230036 PR China liuyong@aiofm.ac.cn zhanglong@aiofm.ac.cn wangchongwen1987@126.com.
  • Xiaopeng Wang
    Suzhou TCM Hospital Affiliated to Nanjing University of Chinese Medicine, Suzhou 215009, China.
  • Chenggong Wang
    Deparment of Orthopedics, Xiangya Hospital, Central South University, Changsha, 410008, Hunan, China.
  • Lin Zhang
    Laboratory of Molecular Translational Medicine, Centre for Translational Medicine, Key Laboratory of Birth Defects and Related Diseases of Women and Children, Ministry of Education, Clinical Research Center for Birth Defects of Sichuan Province, West China Second Hospital, Sichuan University, Chengdu, Sichuan, 610041, China. Electronic address: zhanglin@scu.edu.cn.
  • Wenhao Wu
    Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, 519000, Guangdong, China.
  • Junjie Xiang
    Changzhou Jinse Medical Information Technology Co., Ltd, Changzhou, 213000, Jiangsu, China.
  • Yiping Wang
    Shenzhen Key Laboratory of Photonic Devices and Sensing Systems for Internet of Things, Guangdong and Hong Kong Joint Research Centre for Optical Fibre Sensors, State Key Laboratory of Radio Frequency Heterogeneous Integration, Shenzhen University, Shenzhen 518060, China.
  • Da Zhong
    Deparment of Orthopedics, Xiangya Hospital, Central South University, Changsha, 410008, Hunan, China. zhongda@csu.edu.cn.