Radiologist nabs $4.5M grant to eradicate human limitations of mammography reading
A University of Washington radiologist has scored a $4.5 million grant from the National Institutes of Health to help eradicate missed breast cancer diagnoses.
Christopher Lee, MD, who teaches radiology at UW’s School of Medicine, is earning the funds through the NIH’s Method to Extend Research Time award, or MERIT. According to a university announcement, his team is using artificial intelligence to help improve detection rates.
“Screening mammography saves lives but human interpretation alone is imperfect and is associated with significant harms including ~30,000 missed breast cancers and ~3.8 million false-positives exams each year in the U.S. alone,” Lee and colleagues noted in a description of their research.
Lee is leading a multidisciplinary team of experts in breast cancer screening, machine and deep learning, data science and imaging technology assessment. Their goal is to take a validated, highly accurate AI algorithm they’ve developed for 2D mammography and scale it to 3D imaging.
Previously, the team helped organize and lead the Dialogue for Reverse Engineering Assessments and Methods (DREAM) Digital Mammography Challenge, a crowdsourced competition with more than 640,000 images involved. More than half of U.S. imaging facilities are now using 3D mammography, which represents a 50- to 100-fold increase in imaging data and a new “a new critical barrier for both radiologists and AI algorithm developers.” Lee and colleagues are partnering with machine learning company DeepHealth Inc. on this research.
According to the UW announcement, the $4.5 million MERIT award is aimed at supporting early-stage investigators who the NIH has deemed “superior in research and productivity.” The award will extend the time to support Lee’s research for another five years, with an opportunity for two additional years in the future.