Applying Advanced Computer Vision and Machine Learning to Study Musculoskeletal Disorders and Osteoporosis

“Technology in general, and machine learning specifically, are going to change how we know radiology,” says Valentina Pedoia, PhD, assistant professor in the UC San Francisco Department of Radiology and Biomedical Imaging. As a data scientist, her research focuses primarily on applying computer vision and machine learning techniques to magnetic resonance imaging (MRI) scans to study musculoskeletal disorders and osteoporosis.

Machine learning defines a set of techniques in which you “teach a machine to solve a problem as a human would do.” In medical imaging, it can transform an image into information. This information can be used by radiologists and clinicians for better characterization of the disease and prediction of outcomes.

In the accompanying video, Dr. Pedoia discusses precision medicine – an emerging approach which “aims to collect, connect, and apply vast amounts of scientific research data and information about our health to understand why individuals respond differently to treatments and therapies, and help guide more precise and predictive medicine worldwide.” In the case of an injury such as an anterior cruciate ligament (ACL) tear, a machine learning algorithm can help analyze an image, shape MRI protocol around a patient’s needs, and beyond that, help analyze whether a patient is at future risk for post-traumatic osteoarthritis. By predicting the onset of a disease, steps can be taken to prevent or delay it with early intervention.

Learn more about the Musculoskeletal Research Interest Group (RIG) and how these scientists are exploring the structures that support the human body, their role in health, and how to prevent and heal musculoskeletal damage by visiting the Musculoskeletal RIG web page.