A Multi-Modal Approach for Automated Osteoporosis Diagnosis Using Knee X-ray Imaging Data

DOI

10.2991/978-94-6239-654-8_40How to use a DOI?

Keywords

3D bone reconstruction; fracture risk prediction; knee X-ray; multi-task learning; osteoporosis classification

Abstract

Osteoporosis is a degenerative skeletal condition associated with decreased bone mineral density (BMD) that increases the risk of osteoporotic fractures in older individuals. Nevertheless, traditional BMD measurement with DXA does not consistently provide operator-independent repeatability and is only somewhat sensitive to microarchitectural alterations. We propose here a novel diagnostic approach driven by deep learning, which will assist in carrying out automatic osteoporosis screening on knee X-ray images. The system combines 2D X-ray image analysis and 3D bone density reconstruction with fracture risk calculation. By integrating patient metadata, such as age, body mass index, and menopausal status, the proposed model allows for customized stratification of fracture risk according to FRAX thresholds. This tool enables, on one hand, early pharmacological interventions based on bisphosphonates or ho⁠rmone⁠ therapy, with a classi⁠fication accur⁠acy of 9⁠4.8% and an AUC of 0.92. On the other hand, this tool enhances clinical decision-making and ensures timely treatment planning⁠, Future work will consider the validation on multi-center datasets and its inclusion in hospital workflows.

Copyright

© 2026 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  - Geetha Ramamoorthy
AU  - Arulselvi Subramanian
AU  - Tamilselvi Rajendran
AU  - Parisa BehamMohamed
AU  - Nandhineeswari
PY  - 2026
DA  - 2026/04/24
TI  - A Multi-Modal Approach for Automated Osteoporosis Diagnosis Using Knee X-ray Imaging Data
BT  - Proceedings of the Global Conference on Sustainable Energy Systems, Smart Electronics and Intelligent Computing (GCSESEIC 2025)
PB  - Atlantis Press
SP  - 492
EP  - 507
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-654-8_40
DO  - 10.2991/978-94-6239-654-8_40
ID  - Ramamoorthy2026
ER  -