Stanford AI center's new platform grants worldwide access to free medical imaging datasets
Stanford University is expanding its free repository of imaging and healthcare datasets for artificial intelligence researchers around the globe.
The California school’s Center for Artificial Intelligence in Medicine and Imaging first opened in 2019 and has since amassed annotated datasets for more than 1 million images. AIMI is now partnering with Microsoft’s AI for Health program on a new platform to host these images and create an even larger—and free—global repository.
“What drives this technology, whether you’re a surgeon or an obstetrician, is data,” Matthew Lungren, co-director of AIMI and an assistant professor of radiology at Stanford, said in a university news item published Monday. “We want to double down on the idea that medical data is a public good, and that it should be open to the talents of researchers anywhere in the world.”
Two new datasets will be released within the new hub, and Lungren expects to have more than 2 million images available within the next year.
Researchers can dive into medical problems specific to particular communities, spot bias in data or algorithms, and use the platform’s cloud computing power to avoid using home-grown resources for AI infrastructure.
“This platform will have the largest diversity and volume of AI-ready medical datasets in the world,” Lungren added.
Read the full story below.
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.