Zebra Medical Vision has announced the latest algorithm to be included in its Deep Learning Imaging Analytics platform. The algorithm, capable of detecting vertebral fractures, is the latest addition to a line of automated tools that have been announced over the past year.
Other algorithms available are designed to detect low bone mineral density, breast cancer, fatty liver, coronary artery calcium, emphysema, and more.
“Research has shown that radiologists miss up to 50% of vertebral fractures, since they are usually focused on looking for other features,” says Kassim Javiad, Clinical Lead of the UK Fracture Liaison Service report from the Department of Rheumatology, Oxford University Hospitals at the University of Oxford, Oxford, UK. “In the UK, with our proven coordinated care programs for effective fracture prevention (Fracture Liaison Services), we believe that early detection of such fractures can yield both better care and significant healthcare cost savings.”
The Zebra vertebral compression fracture algorithm is designed to automatically identify and localise compression fractures. The algorithm uses deep learning to differentiate between compression fractures and more ubiquitous degenerative endplate changes and osteophytes. According to a company release, this knowledge can assist healthcare providers in accurately identifying people at risk and placing them under supervision or fracture prevention programs to reduce the risks of subsequent osteoporotic fractures.
The new algorithm, once released commercially, will be offered as part of Zebra’s Imaging Analytics engine for care providers, as well as on its Profound platform, which allows users to upload their imaging scans and receive automated insights regarding their imaging data.