• Krishnakartik M
• Manthena Ramakrishna Raju

Osteoporosis is a progressive skeletal disorder characterized by reduced bone mineral density and deterioration of bone microarchitecture, leading to increased fracture risk. Early diagnosis is crucial for effective clinical intervention; however, standard diagnostic tools such as dual-energy X-ray absorptiometry (DXA) are costly and not universally accessible, limiting their use for large-scale screening. This study proposes an artificial intelligence (AI)-driven framework for automated detection and multi-class classification of osteoporosis using knee X-ray images. The proposed methodology integrates deep neural networks, hybrid learning strategies, and transformer-based architectures to identify discriminative radiographic patterns corresponding to normal bone density, osteopenia, and osteoporosis. Robust image preprocessing, feature learning, and model optimization techniques are employed to ensure generalization across diverse imaging conditions. Model performance is evaluated using standard clinical and computational metrics, including accuracy, precision, recall, F1-score, and area under the curve (AUC). The proposed system aims to provide a scalable, interpretable, and cost-effective decision-support tool for opportunistic osteoporosis screening, thereby enhancing early diagnosis and improving clinical outcomes.

Osteoporosis detection, knee X-ray, deep learning, medical image analysis, artificial intelligence, clinical decision support.

"Osteoporosis Detection from Knee X-ray Images Using Deep Learning Approaches", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.e418-e423, January-2026, Available :http://www.jetir.org/papers/JETIR2601462.pdf

"Osteoporosis Detection from Knee X-ray Images Using Deep Learning Approaches", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppe418-e423, January-2026, Available at : http://www.jetir.org/papers/JETIR2601462.pdf