SONG Ping 1,2,3 , FAN Zheqi 1,2,3 , ZHI Xin 2,3 , CAO Zheng 2,3,4 , MIN Shengfeng 5 , LIU Xingyu 5,6 , ZHANG Yiling 5 , KONG Xiangpeng 2,3 , CHAI Wei 2,3
  • 1. Medical School of Chinese PLA General Hospital, Beijing, 100853, P. R. China;
  • 2. Senior Department of Orthopedics, the Fourth Medical Center of Chinese PLA General Hospital, Beijing, 100048, P. R. China;
  • 3. National Clinical Research Center for Orthopedics, Sports Medicine & Rehabilitation, Beijing, 100853, P. R. China;
  • 4. Medical School of Nankai University, Tianjin, 300071, P. R. China;
  • 5. Longwood Valley Medical Technology Co. Ltd, Beijing, 100190, P. R. China;
  • 6. College of Life Science, Tsinghua University, Beijing, 100084, P. R. China;
KONG Xiangpeng, Email: 18810999609@163.com; CHAI Wei, Email: chaiwei301@163.com
Export PDF Favorites Scan Get Citation

Objective  To develop a neural network architecture based on deep learning to assist knee CT images automatic segmentation, and validate its accuracy. Methods  A knee CT scans database was established, and the bony structure was manually annotated. A deep learning neural network architecture was developed independently, and the labeled database was used to train and test the neural network. Metrics of Dice coefficient, average surface distance (ASD), and Hausdorff distance (HD) were calculated to evaluate the accuracy of the neural network. The time of automatic segmentation and manual segmentation was compared. Five orthopedic experts were invited to score the automatic and manual segmentation results using Likert scale and the scores of the two methods were compared. Results  The automatic segmentation achieved a high accuracy. The Dice coefficient, ASD, and HD of the femur were 0.953±0.037, (0.076±0.048) mm, and (3.101±0.726) mm, respectively; and those of the tibia were 0.950±0.092, (0.083±0.101) mm, and (2.984±0.740) mm, respectively. The time of automatic segmentation was significantly shorter than that of manual segmentation [(2.46±0.45) minutes vs. (64.73±17.07) minutes; t=36.474, P<0.001). The clinical scores of the femur were 4.3±0.3 in the automatic segmentation group and 4.4±0.2 in the manual segmentation group, and the scores of the tibia were 4.5±0.2 and 4.5±0.3, respectively. There was no significant difference between the two groups (t=1.753, P=0.085; t=0.318, P=0.752). Conclusion  The automatic segmentation of knee CT images based on deep learning has high accuracy and can achieve rapid segmentation and three-dimensional reconstruction. This method will promote the development of new technology-assisted techniques in total knee arthroplasty.

Citation: SONG Ping, FAN Zheqi, ZHI Xin, CAO Zheng, MIN Shengfeng, LIU Xingyu, ZHANG Yiling, KONG Xiangpeng, CHAI Wei. Study on the accuracy of automatic segmentation of knee CT images based on deep learning. Chinese Journal of Reparative and Reconstructive Surgery, 2022, 36(5): 534-539. doi: 10.7507/1002-1892.202201072 Copy

  • Previous Article

    LLMKA: A Matlab-based toolbox for musculoskeletal kinematics analysis of lower limbs
  • Next Article

    Accuracy of key point matrix technology based contactless automatic measurement for joint motion of hand