A Hybrid Attention-Driven Deep Learning Model for Osteoporosis Detection in Knees
Ishaq Muhammad and Bumshik Lee
Published in The 7th International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Fukuoka, Japan, 2025
In this work, we propose a hybrid deep learning model that combines DenseNet169 with a custom attention module for accurate osteoporosis detection using knee radiographs. The fused features are classified through a fully connected network, achieving strong performance and outperforming state-of-the-art methods.