Transfer learning-assisted 3D deep learning models for knee osteoarthritis detection: Data from the osteoarthritis initiative
Frontiers in Bioengineering and Biotechnology · 13.04.2023 · 11
DOI: 10.3389/fbioe.2023.1164655 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 13.04.2023. Verfasst von Pauline Shan Qing Yeoh und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Universiti Malaya, Kuala Lumpur, Malaysia. Die Arbeit wurde bisher 90-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xuzhou Science and Technology Bureau, Universiti Malaya.
Abstract (Originalsprache)
Knee osteoarthritis is one of the most common musculoskeletal diseases and is usually diagnosed with medical imaging techniques. Conventionally, case identification using plain radiography is practiced. However, we acknowledge that knee osteoarthritis is a 3D complexity; hence, magnetic resonance imaging will be the ideal modality to reveal the hidden osteoarthritis features from a three-dimensional view. In this work, the feasibility of well-known convolutional neural network (CNN) structures (ResNet, DenseNet, VGG, and AlexNet) to distinguish knees with and without osteoarthritis (OA) is investigated. Using 3D convolutional layers, we demonstrated the potential of 3D convolutional neural networks of 13 different architectures in knee osteoarthritis diagnosis. We used transfer learning by transforming 2D pre-trained weights into 3D as initial weights for the training of the 3D models. The performance of the models was compared and evaluated based on the performance metrics [balanced accuracy, precision, F1 score, and area under receiver operating characteristic (AUC) curve]. This study suggested that transfer learning indeed enhanced the performance of the models, especially for ResNet and DenseNet models. Transfer learning-based models presented promising results, with ResNet34 achieving the best overall accuracy of 0.875 and an F1 score of 0.871. The results also showed that shallow networks yielded better performance than deeper neural networks, demonstrated by ResNet18, DenseNet121, and VGG11 with AUC values of 0.945, 0.914, and 0.928, respectively. This encourages the application of clinical diagnostic aid for knee osteoarthritis using 3DCNN even in limited hardware conditions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Engineering, Universiti Malaya, Kuala Lumpur, Malaysia.
- Faculty of Medicine, Universiti Malaya, Kuala Lumpur, Malaysia.
- School of Medical Information and Engineering, Xuzhou Medical University, Xuzhou, China.
- Information Department, Affiliated Hospital of Xuzhou Medical University, Xuzhou, China.
Förderung
- Xuzhou Science and Technology Bureau
- Universiti Malaya
Zitieren
APA
Yeoh, P. S. Q., Lai, K. W., Goh, S. L., Hasikin, K., Wu, X., & Li, P. (2023). Transfer learning-assisted 3D deep learning models for knee osteoarthritis detection: Data from the osteoarthritis initiative. Frontiers in Bioengineering and Biotechnology, 11. https://doi.org/10.3389/fbioe.2023.1164655
Vancouver
Yeoh PSQ, Lai KW, Goh SL, Hasikin K, Wu X, Li P. Transfer learning-assisted 3D deep learning models for knee osteoarthritis detection: Data from the osteoarthritis initiative. Frontiers in Bioengineering and Biotechnology. 2023;11. doi:10.3389/fbioe.2023.1164655
BibTeX
@article{Yeoh2023,
author = {Yeoh, Pauline Shan Qing and Lai, Khin Wee and Goh, Siew Li and Hasikin, Khairunnisa and Wu, Xiang and Li, Pei},
title = {Transfer learning-assisted 3D deep learning models for knee osteoarthritis detection: Data from the osteoarthritis initiative},
journal = {Frontiers in Bioengineering and Biotechnology},
year = {2023},
volume = {11},
doi = {10.3389/fbioe.2023.1164655}
}
EUVIMED