Multitask learning for automatic detection of meniscal injury on 3D knee MRI
Journal of Orthopaedic Research · 2025
DOI: 10.1002/jor.26024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Orthopaedic Research, 2025. Verfasst von Yufan Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering and Med-X Research Institute, Shanghai Jiao Tong University, Shanghai, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Tibial Meniscus Injuries, Imaging, Three-Dimensional, Machine Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Innovation Plan Of Shanghai Science and Technology Commission, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Magnetic resonance imaging (MRI) of the knee is the recommended diagnostic method before invasive arthroscopy surgery. Nevertheless, interpreting knee MRI scans is a time‐consuming process that is vulnerable to inaccuracies and inconsistencies. We proposed a multitask learning network MCSNet att which efficiently introduces segmentation prior features and enhances classification results through multiscale feature fusion and spatial attention modules. The MRI studies and subsequent arthroscopic diagnosis of 259 knees were collected retrospectively. Models were trained based on multitask loss with coronal and sagittal sequences and fused using logistic regression (LR). We visualized the network's interpretability by the gradient‐weighted class activation mapping method. The LR model achieved higher area under the curve and mean average precision of medial and lateral menisci than models trained on a single sagittal or coronal sequence. Our multitask model MCSNet at outperformed the single‐task model CNet and two clinicians in classification, with accuracy, precision, recall, F1‐score of 0.980, 1.000, 0.952, 0.976 for medial and 0.920, 0.905, 0.905, 0.905 for the lateral, respectively. With the assistance of model results and visualized saliency maps, both clinicians showed improvement in their diagnostic performance. Compared to the baseline segmentation model, our model improved dice similarity coefficient and the 95% Hausdorff distance (HD 95 ) of the lateral meniscus for 2.3% and 0.860 mm in coronal images and 4.4% and 2.253 mm in sagittal images. Our multitask learning network quickly generated accurate clinicopathological classification and segmentation of knee MRI, demonstrating its potential to assist doctors in a clinical setting.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Biomedical Engineering and Med-X Research Institute, Shanghai Jiao Tong University, Shanghai, China.
- Engineering Research Center of Digital Medicine and Clinical Translation, Ministry of Education, Shanghai, China.
- Department of Orthopedics, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Shanghai Key Laboratory of Orthopedic Implants & Clinical Translation R&D Center of 3D Printing Technology, Department of Orthopedic Surgery, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Med…
ORCID-Profile: Yufan Wang
Förderung
- National Natural Science Foundation of China
- Science and Technology Innovation Plan Of Shanghai Science and Technology Commission
- Fundamental Research Funds for the Central Universities
- The Pudong New Area Science & Technology and Development Fund
Zitieren
APA
Wang, Y., Ying, M., Yang, Y., Chen, Y., Wang, H., Tsai, T. Y., & Liu, X. (2025). Multitask learning for automatic detection of meniscal injury on 3D knee MRI. Journal of Orthopaedic Research. https://doi.org/10.1002/jor.26024
Vancouver
Wang Y, Ying M, Yang Y, Chen Y, Wang H, Tsai TY, et al. Multitask learning for automatic detection of meniscal injury on 3D knee MRI. Journal of Orthopaedic Research. 2025. doi:10.1002/jor.26024
BibTeX
@article{Wang2025,
author = {Wang, Yufan and Ying, Mengjie and Yang, Yangyang and Chen, Yankai and Wang, Haoyuan and Tsai, Tsung-Yuan and Liu, Xudong},
title = {Multitask learning for automatic detection of meniscal injury on 3D knee MRI},
journal = {Journal of Orthopaedic Research},
year = {2025},
doi = {10.1002/jor.26024}
}
EUVIMED