UC San Francisco has created a new center to accelerate the application of artificial intelligence (AI) technology to radiology. Researchers in the Center for Intelligent Imaging, or ci2, will use patient images and clinical data from UCSF Health and other institutions to develop, test and validate deep learning algorithms.
Investigators in ci2 will team with Santa Clara, Calif.-based Nvidia Corp. to build infrastructure and tools focused on enabling the translation of AI into clinical practice.
UCSF has long been involved in medical imaging innovation, dating to the development of the MRI and the university’s 1975 collaboration with industry to install the first MRI systems in the United States and worldwide. The center aims to enable the same type of transformation via intelligent radiology, with the goal of again collaborating with industry to become of the first institutions to bring medical imaging AI to the bedside.
Researchers in the center will use patient images and clinical data from UCSF Health and other institutions to develop, test and validate deep learning algorithms. The center’s computational infrastructure includes NVIDIA’s DGX-2 supercomputer.
“The volume of medical imaging has been rapidly increasing and radiologists are struggling to keep up with the sheer number of images,” said Sharmila Majumdar, Ph.D., a professor and vice chair in the UCSF Department of Radiology and Biomedical Imaging, in a story on the UCSF website. “ci2 aims to impact the entire value chain of imaging, from the time the patient comes for a scan to the final delivery of individualized, quantitative, prognostic and care-defining information.”
Majumdar, who will run the center’s operations, will be leading a study funded by the National Institutes of Health to evaluate chronic back pain in the center, using AI-fueled algorithms, data analysis, quantitative sensory assessments, brain imaging, and biomechanical evaluation of the spine.
The center also will link academic innovation to startups to promote collaborative AI imaging research and development. The inaugural start-up company to leverage ci2 in this capacity is London-based Kheiron Medical Technologies Ltd., which will work with the UCSF breast imaging group to ensure that its MiaTM breast cancer screening software can be safely and feasibly deployed in ethnically diverse populations.
