Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193423,
        author = {Yashraj Gavale and Sharmila Rathod and Adhya Jain and Kajal Gupta},
        title = {A Deep Learning and Ensemble Approach for Osteoporosis Detection Using Conventional X-Ray Imaging},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {226-238},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193423},
        abstract = {Osteoporosis is a progressive skeletal disorder characterized by reduced bone mineral density and an increased risk of fractures, yet it remains significantly underdiagnosed worldwide. The current gold standard for diagnosis, Dual-energy X-ray Absorptiometry (DEXA), provides reliable assessment but is limited by high cost, restricted accessibility, and low availability in developing regions such as India, making large-scale screening challenging. In contrast, X-ray imaging is widely available, cost-effective, and routinely used in clinical practice, offering a practical alternative when combined with advanced computational methods.
This study proposes a weighted ensemble framework based on custom Convolutional Neural Networks (CNNs) for automated osteoporosis detection using knee X-ray images. Two publicly available datasets from Kaggle were utilized to improve model robustness and generalization. An initial custom CNN achieved an accuracy of 95.1%; however, it exhibited comparatively lower recall, which is critical in medical diagnosis to minimize false negatives. To address this, multiple models with identical architectures but different initializations were combined using a weighted ensemble strategy, resulting in enhanced predictive performance.
The proposed approach leverages the accessibility of X-ray imaging and the robustness of ensemble deep learning to provide an efficient and scalable solution for osteoporosis detection.},
        keywords = {Osteoporosis, Deep Learning, CNN, Ensemble Learning, X-ray Imaging, Medical AI},
        month = {March},
        }