Oa-Net for Multi Stage Knee Osteoarthritis Classificaton Using an Extended Convolutional Neural Network Framework

DOI

10.2991/978-94-6463-738-0_69How to use a DOI?

Keywords

Knee osteoarthritis; deep learning; extended CNN; multi-stage classification; OAI dataset; feature extraction; spatial hierarchy

Abstract

Knee osteoarthritis (OA) is a common degenerative joint condition that affects millions worldwide. Effective therapy requires early diagnosis and precise staging. The study introduces OA-Net, a sophisticated Convolutional Neural Network (CNN) framework intended for multi-stage knee OA severity classification using X-ray data. By capturing complex spatial hierarchies and minimizing information loss, OA-Net improves on traditional CNN architectures. It uses a specific transition module and advanced feature extraction to provide smooth feature flow between network stages. Data augmentation methods, such as geometric changes and contrast tweaks, are used to alleviate class imbalance. Evaluated on the OAI dataset, OA-Net achieved an accuracy of 92.8%, outperforming existing models and demonstrating significant improvements in sensitivity and F1 score. These findings indicate that OANet holds promise for enhancing diagnostic precision in knee OA classification, supporting improved clinical decision-making.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - M. Nethra
AU  - V. Priyanka
AU  - AThamizh Selvi
AU  - S. Gopikha
PY  - 2025
DA  - 2025/06/22
TI  - Oa-Net for Multi Stage Knee Osteoarthritis Classificaton Using an Extended Convolutional Neural Network Framework
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 890
EP  - 904
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_69
DO  - 10.2991/978-94-6463-738-0_69
ID  - Nethra2025
ER  -