AI-driven nano-imaging of bone lacuno-canalicular network: unraveling early osteoporosis signs

Osteoporosis alters bone quality at the nanoscale, yet conventional diagnostic methods fail to capture early-stage changes in the lacuna-canalicular network (LCN). To bridge this gap, we propose a multi-scale, AI-enhanced imaging approach at ESRF beamline ID16B, integrating holotomography for large-field-of-view assessments and ptychography for ultra-high-resolution imaging. Healthy and osteoporotic trabecular bone samples from femoral heads will be analyzed, with mechanical testing conducted outside the hutch to track damage evolution in marked regions. AI-driven segmentation and data augmentation will enhance feature detection and enable predictive modeling of LCN deterioration. This study will generate the first large-scale quantitative dataset of osteoporotic LCN degradation, advancing early diagnosis and therapeutic strategies.