EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Diagnostic performance for severity grading of hip osteoarthritis and osteonecrosis of femoral head on radiographs: Deep learning model vs. board-certified orthopaedic surgeons

Chen Chen, Peng Liu, Yong Feng, DeXian Ye, Chi-Cheng Fu, Lin Ye, YanYan Song, DongXu Liu, Guoyan Zheng, ChangQing Zhang

Osteoarthritis Imaging · 2023-06 · 3 (2) · 100092

DOI: 10.1016/j.ostima.2023.100092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Osteoarthritis Imaging, 2023-06. Verfasst von Chen Chen und 9 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To evaluate the diagnostic performance of a single deep learning (DL) model for severity grading of two typical yet challenging hip disorders, primary hip osteoarthritis (PHOA) and osteonecrosis of the femoral head (ONFH), on digital radiography. We conducted a two-center, retrospective study. We trained an XceptionNet-based DL model using a dataset consisting of 56,597 hip images diagnosed as normal, PHOA_I, PHOA_II, PHOA_III, and ONFH_II, ONFH_III, ONFH_IV by a panel of 10 board-certified orthopedic surgeons. The trained model was validated on a separate testing dataset. To demonstrate the model's generalizability, we applied the trained model directly to a dataset consisting of 811 hip images collected from an external clinical center. Accuracy, area under the curve (AUC) of receiver operating characteristics, sensitivity, and specificity were investigated. Validated on the testing dataset, the model achieved an overall AUC of 94.9%, with individual AUC scores of 94.2% for PHOA_I, 95.8% for PHOA_II, 90.9% for PHOA_III, 93.6% for ONFH_II, 93.8% for ONFH_III, and 93.8% for ONFH_IV. The average sensitivity for all classes of the DL algorithm (0.797) was better than the average level of the board-certified orthopedic surgeons (0.756). When applied directly to the external dataset, the AUC of the trained model is degraded. We can train a single DL model to grade the severity of PHOA and ONFH on digital radiographs. The model may be used to provide a second opinion for severity grading of hip disorders on digital radiographs.

Zitieren

APA

Chen, C., Liu, P., Feng, Y., Ye, D., Fu, C., Ye, L., Song, Y., Liu, D., Zheng, G., & Zhang, C. (2023). Diagnostic performance for severity grading of hip osteoarthritis and osteonecrosis of femoral head on radiographs: Deep learning model vs. board-certified orthopaedic surgeons. Osteoarthritis Imaging, 3(2), 100092. https://doi.org/10.1016/j.ostima.2023.100092

Vancouver

Chen C, Liu P, Feng Y, Ye D, Fu C, Ye L, et al. Diagnostic performance for severity grading of hip osteoarthritis and osteonecrosis of femoral head on radiographs: Deep learning model vs. board-certified orthopaedic surgeons. Osteoarthritis Imaging. 2023;3(2):100092. doi:10.1016/j.ostima.2023.100092

BibTeX
@article{Chen2023,
  author = {Chen, Chen and Liu, Peng and Feng, Yong and Ye, DeXian and Fu, Chi-Cheng and Ye, Lin and Song, YanYan and Liu, DongXu and Zheng, Guoyan and Zhang, ChangQing},
  title = {Diagnostic performance for severity grading of hip osteoarthritis and osteonecrosis of femoral head on radiographs: Deep learning model vs. board-certified orthopaedic surgeons},
  journal = {Osteoarthritis Imaging},
  year = {2023},
  volume = {3},
  number = {2},
  pages = {100092},
  doi = {10.1016/j.ostima.2023.100092}
}
Kostenlos starten →