SBIR Phase II: Artificial Intelligence (AI)-Enabled Ultrasound for Imaging and Diagnosing Musculoskeletal Injuries

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is to improve musculoskeletal ultrasound (MSK-US) diagnostics through AI-powered guidance technology. This innovation could democratize the use of ultrasound by enabling novice practitioners to perform accurate MSK-US evaluations at the point of care. Musculoskeletal injuries account for 77% of injury-related healthcare visits in the U.S. Yet up to 85% of those injuries are under or misdiagnosed on the first visit. The commercial impact of the technology could be substantial, as widespread adoption fosters a competitive healthcare market, attracts investment, and strengthens the U.S. as a leader in medical and AI innovation. The technology also has applications in military healthcare, where it can improve injury diagnostics for service members in the field, or after service through the Veteran’s Administration system, where imaging overuse was found to greatly contribute to costs. By integrating AI-driven imaging, this project advances scientific understanding, promotes healthcare access, and promotes economic growth. The proposed project integrates AI with medical imaging, addressing critical challenges in musculoskeletal diagnostic ultrasound utilization. Ultrasound has long been recognized as an accurate and cost effective means to diagnose musculoskeletal injuries. However, practitioners currently experience a steep and time consuming learning curve to become proficient with the use of ultrasound. This is in large part the reason ultrasound has not become widely adopted across the U.S. Healthcare System. The research goals include developing a large database of musculoskeletal images, labeled for the use of AI training, scaling tissue recognition, and developing AI based guidance that allows any novice practitioners to be guided through the automated capture of diagnosable musculoskeletal images. Once collected, diagnosable images will be sent to the cloud for diagnosis and summary. This technology will be device agnostic, available for integration with any ultrasound vendor. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.