Background The role of bone structure, one component of bone quality, has emerged as a contributor to bone strength. The application of high-resolution imaging in evaluating bone structure has evolved from an in vitro technology for small specimens to an emerging clinical research tool for in vivo studies in humans. However, many technical and practical challenges remain to translate these techniques into established clinical outcomes. Questions/purposes We reviewed use of high-resolution CT for evaluating trabecular microarchitecture and cortical ultrastructure of bone specimens ex vivo, extension of these techniques to in vivo human imaging studies, and recent studies involving application of high-resolution CT to characterize bone structure in the context of skeletal disease. Methods We performed the literature review using PubMed and Google Scholar. Keywords included CT, MDCT, micro-CT, high-resolution peripheral CT, bone microarchitecture, and bone quality. Results Specimens can be imaged by micro-CT at a resolution starting at 1 μm, but in vivo human imaging is restricted to a voxel size of 82 μm (with actual spatial resolution of ~ 130 μm) due to technical limitations and radiation dose considerations. Presently, this mode is limited to peripheral skeletal regions, such as the wrist and tibia. In contrast, multidetector CT can assess the central skeleton but incurs a higher radiation burden on the subject and provides lower resolution (200–500 μm). Conclusions CT currently provides quantitative measures of bone structure and may be used for estimating bone strength mathematically. The techniques may provide clinically relevant information by enhancing our understanding of fracture risk and establishing the efficacy of antifracture for osteoporosis and other bone metabolic disorders.

A deep learning model was trained to identify and subclassify hip fractures from radiographs, with an overall binary accuracy for hip fracture detection of 93.7% and a functional subclassification ... Purpose To investigate the feasibility of automatic identification and classification of hip fractures using deep learning, which may improve outcomes by reducing diagnostic errors and decreasing t...

Knee Osteoarthritis (OA) is a common musculoskeletal disorder in the United States. When diagnosed at early stages, lifestyle interventions such as exercise and weight loss can slow OA progression, but at later stages, only an invasive option is available: total knee replacement (TKR). Though a generally successful procedure, only 2/3 of patients who undergo the procedure report their knees feeling “normal” post-operation, and complications can arise that require revision. This necessitates a model to identify a population at higher risk of TKR, particularly at less advanced stages of OA, such that appropriate treatments can be implemented that slow OA progression and delay TKR. Here, we present a deep learning pipeline that leverages MRI images and clinical and demographic information to predict TKR with AUC 0.834 ± 0.036 (p < 0.05). Most notably, the pipeline predicts TKR with AUC 0.943 ± 0.057 (p < 0.05) for patients without OA. Furthermore, we develop occlusion maps for case-control pairs in test data and compare regions used by the model in both, thereby identifying TKR imaging biomarkers. As such, this work takes strides towards a pipeline with clinical utility, and the biomarkers identified further our understanding of OA progression and eventual TKR onset.