Deep Learning-Based Framework for Automated Classification of Knee Osteoarthritis Severity and Detection of Joint Space Width in X-Ray Imaging

DOI

10.2991/978-94-6463-718-2_96How to use a DOI?

Keywords

Knee osteoarthritis severity classification; Deep Learning; YOLOv8; VGG16; KL grading

Abstract

Knee osteoarthritis (OA) is a universal degenerative disease that affects millions of people worldwide, mainly in older adults, and often leads to chronic pain and reduced quality of life. Effective management of diseases, both by preventing disease progression and initiating specific therapeutic strategies, relies upon timely and accurate diagnosis. In this paper we propose a new framework for the analysis of digital X-ray images that uses a deep learning approach for detection and classification of knee OA. The tasks being investigated include: quantifying the Knee Joint Space Width (JSW), a relevant marker of OA, and estimating its severity with the prominent Kellgren-Lawrence (KL) score. We need to identify JSW in X-ray images, for which we use the YOLOv8 model, which is optimal for fast and accurate detection and highlighting of JSW region in X-ray images. We employ a VGG16 neural network, augmented by transfer learning, to classify the circumstances following the detection of the JSW. To define the grade of severity of OA according to KL scores. That is, this automated system can aid clinicians by offering reliable diagnostics, increasing the value of OA progression assessments, and allowing for more timely and effective interventions. Incorporating state-of-the-art deep learning models, our framework seeks to improve patient management and clinical accuracy.

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  - Logeshwari Alavanthar
AU  - Jayashree Stalin
AU  - K. Jasmine Mystica
PY  - 2025
DA  - 2025/05/23
TI  - Deep Learning-Based Framework for Automated Classification of Knee Osteoarthritis Severity and Detection of Joint Space Width in X-Ray Imaging
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1152
EP  - 1161
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_96
DO  - 10.2991/978-94-6463-718-2_96
ID  - Alavanthar2025
ER  -