Development and clinical validation of a deep learning‐based knee CT image segmentation method for robotic‐assisted total knee arthroplasty
The International Journal of Medical Robotics and Computer Assisted Surgery · 2024-08 · 20 (4)
DOI: 10.1002/rcs.2664 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift The International Journal of Medical Robotics and Computer Assisted Surgery, online erschienen am 12.07.2024. Verfasst von Xingyu Liu und 13 weiteren Autor:innen. Beteiligte Einrichtung: School of Life Sciences, Tsinghua University, Beijing, China. Hauptthemen laut MEDLINE: Arthroplasty, Replacement, Knee, Deep Learning, Robotic Surgical Procedures, Tomography, X-Ray Computed. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: Key Project of Regional Innovation Joint Fund of National Natural Science Foundation, Beijing Science and Technology Commission AI Health Collaborative Innovation Cultivation, CAMS Innovation Fund for Medical Sciences.
Abstract (Originalsprache)
Background
This study aimed to develop a novel deep convolutional neural network called Dual‐path Double Attention Transformer (DDA‐Transformer) designed to achieve precise and fast knee joint CT image segmentation and to validate it in robotic‐assisted total knee arthroplasty (TKA).
Methods
The femoral, tibial, patellar, and fibular segmentation performance and speed were evaluated and the accuracy of component sizing, bone resection and alignment of the robotic‐assisted TKA system constructed using this deep learning network was clinically validated.
Results
Overall, DDA‐Transformer outperformed six other networks in terms of the Dice coefficient, intersection over union, average surface distance, and Hausdorff distance. DDA‐Transformer exhibited significantly faster segmentation speeds than nnUnet, TransUnet and 3D‐Unet ( p < 0.01). Furthermore, the robotic‐assisted TKA system outperforms the manual group in surgical accuracy.
Conclusions
DDA‐Transformer exhibited significantly improved accuracy and robustness in knee joint segmentation, and this convenient and stable knee joint CT image segmentation network significantly improved the accuracy of the TKA procedure.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Life Sciences, Tsinghua University, Beijing, China.
- Institute of Biomedical and Health Engineering (iBHE), Tsinghua Shenzhen International Graduate School, Shenzhen, China.
- School of Biomedical Engineering, Tsinghua University, Beijing, China.
- Department of Orthopedics, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China.
- Department of Orthopedic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
- Departments of Orthopedics, West China Hospital, West China School of Medicine, Sichuan University, Chengdu, China.
ORCID-Profile: Wenwei Qian
Förderung
- Key Project of Regional Innovation Joint Fund of National Natural Science Foundation
- Beijing Science and Technology Commission AI Health Collaborative Innovation Cultivation
- CAMS Innovation Fund for Medical Sciences
- National High Level Hospital Clinical Research Funding
Zitieren
APA
Liu, X., Li, S., Zou, X., Chen, X., Xu, H., Yu, Y., Gu, Z., Liu, D., Li, R., Wu, Y., Wang, G., Liao, H., Qian, W., & Zhang, Y. (2024). Development and clinical validation of a deep learning‐based knee CT image segmentation method for robotic‐assisted total knee arthroplasty. The International Journal of Medical Robotics and Computer Assisted Surgery, 20(4). https://doi.org/10.1002/rcs.2664
Vancouver
Liu X, Li S, Zou X, Chen X, Xu H, Yu Y, et al. Development and clinical validation of a deep learning‐based knee CT image segmentation method for robotic‐assisted total knee arthroplasty. The International Journal of Medical Robotics and Computer Assisted Surgery. 2024;20(4). doi:10.1002/rcs.2664
BibTeX
@article{Liu2024,
author = {Liu, Xingyu and Li, Songlin and Zou, Xiongfei and Chen, Xi and Xu, Hongjun and Yu, Yang and Gu, Zhao and Liu, Dong and Li, Runchao and Wu, Yaojiong and Wang, Guangzhi and Liao, Hongen and Qian, Wenwei and Zhang, Yiling},
title = {Development and clinical validation of a deep learning‐based knee CT image segmentation method for robotic‐assisted total knee arthroplasty},
journal = {The International Journal of Medical Robotics and Computer Assisted Surgery},
year = {2024},
volume = {20},
number = {4},
doi = {10.1002/rcs.2664}
}
EUVIMED