Mayo Clinic and Microsoft partner to advance generative AI in radiology
The Mayo Clinic is seeking to advance the use of generative artificial intelligence in imaging through a new collaboration with Microsoft Research.
The duo made the announcement during the 43rd Annual J.P. Morgan Healthcare Conference taking place now in San Francisco. The collaboration will combine Mayo Clinic’s clinical X-ray data with Microsoft’s AI technology to develop a foundational model that incorporates both images and text.
The collaboration will first focus their model on chest X-rays, which represent a significant reading burden for radiologists. It is the pair’s hope that their model will be able to automatically generate reports, evaluate tube and line placements on chest radiographs and identify changes that may have developed since patients’ prior imaging. Automating these tasks could have significant benefits for radiology workflows, Matthew Callstrom, MD, PhD, chair of Mayo Clinic Radiology in the Midwest and medical director for Generative AI and Strategy, indicated in a news release on the partnership.
"Focusing on chest X-ray reports, Mayo's clinical teams and Microsoft researchers will collaborate to advance the state-of-the-art in multimodal AI radiology, helping bring innovation to real-world application faster and at scale, which is key to making exemplary healthcare more accessible,” Callstrom added.
Jonathan Carlson, PhD, managing director of Health Futures at Microsoft Research, also commented on the partnership, stating that it represents a “crucial step” toward developing generative AI capable of improving patient care and clinician experience.
“The fusion of Microsoft's recognized research innovations in biomedical AI and Mayo Clinic's radiology excellence will empower clinicians with the tools they need to deliver more precise and accessible care and furthers Microsoft’s commitment to bringing the power of emerging AI to clinical researchers worldwide,” Carlson said in the same release.
It was also announced during the conference that Mayo Clinic is partnering with Cerebras to develop a genomic foundation model that combines publicly available human reference genome data with Mayo's patient exome data. The team will combine this information to develop a model that could streamline often arduous and lengthy trial and error processes involved in finding suitable treatments for different diseases.
In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She began covering the medical imaging industry for Innovate Healthcare in 2021.