Detection of Osteoporosis Using Knee X-Rays

This study presents a pipeline for the automated detection of osteoporosis in knees using X-ray images. In particular, we identified trabecular patterns, that serve as an important indicator of osteoporosis, in the images of affected subjects. In addition to incorporating image features for trabecular patterns, we examined the efficacy of a multimodal approach that incorporates auxiliary patient details: subject age and gender, which have been reported to be good indicators of osteoporosis. The results are promising and demonstrate the potential of the proposed solution approach to provide an accessible and inexpensive assessment option for osteoporosis.