OsteoSight Spine (v1) is a software tool that uses artificial intelligence to analyze X-ray images of the spine and chest in adults 50 years and older. The system helps radiologists identify patients who may have low bone mineral density, so they can be referred for further bone health assessment. It aims to opportunistically flag patients at risk using routine radiographs, making it easier to screen for osteoporosis risk.
OsteoSight Spine is intended for use opportunistically with standard frontal radiographs of the lumbar spine (AP), thoracic spine (AP), and chest (PA) performed in patients aged 50 years and older. OsteoSight provides a notification in the form of a report to aid radiologists and/or physician interpreters in identifying patients with possible low bone mineral density (BMD) at L1-L4 to prompt a clinical assessment of bone health. OsteoSight should not be used to rule out low BMD.
OsteoSight Spine is an AI-enabled software (SaMD) that receives DICOM radiographs and uses a two-stage pipeline: (1) verifying the input is a suitable radiograph (using a classifier), and (2) estimating a T-score for the L1-L4 vertebrae from the image using a Vision Transformer-based backbone. If the T-score is below a threshold, a notification report is generated for the interpreting physician via PACS integration.
Performance was established via retrospective multi-center studies comparing device sensitivity and specificity with DXA (the gold standard). In the intended use population (n=3599), OsteoSight achieved an AUROC of 0.84, sensitivity of 0.51, and specificity of 0.91. Software verification and validation were also performed per FDA and cybersecurity guidances.
No predicate devices specified
Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.