Johns Hopkins Researchers Build Google Search for MRI Scans
Researchers at Johns Hopkins are building a digital library of MRI scans from children with normal and abnormal brains in an effort to give doctors a Google-like search system to improve how they diagnose and treat these pediatric patients with brain disorders.
The researchers store the images in the cloud. Ultimately, the search system will allow physicians to access thousands of pediatric scans to look for any that resemble their own patient's image. For funding, Hopkins has received a three-year, $600,000 grant from the National Institutes of Health (NIH).
Susumu Mori, Ph.D., a professor of radiology in the Johns Hopkins School of Medicine, is working with Miller on the project. He and Thierry Huisman, M.D., a professor of radiology and pediatrics and the director of pediatric radiology at the Johns Hopkins Children's Center, in four years have created a clinical database of more than 5,000 whole-brain MRI scans of children treated at Johns Hopkins. They have withheld identifying information, but included medical conditions. The software has indexed anatomical information involving up to 1,000 structural measurements in 250 regions of the brain, sorted into 22 brain disease categories.
Currently, the pilot pediatric brain imaging data bank is limited to physicians and patients within the Johns Hopkins medical system. However, researchers say it could eventually be expanded or replicated elsewhere. Beyond the brain imaging data bank for children, the researchers have begun building a similar MRI brain image library focused on disorders commonly found in elderly patients. That project is associated with the National Institute of Aging's Alzheimer's Disease Research Center.
