How MIT and Harvard Are Helping to Bring AI to X-rays

The 9-year-old company Imaging Advantage is creating a machine learning initiative with the research universities called Singularity Healthcare.

Chris Newmarker

A machine learning initiative called Singularity Healthcare is bringing the expertise of two top U.S. research universities to bear on developing an intelligent x-ray engine. 

The initiative, expected to launch this year, is a partnership between Goldman Sachs-backed Imaging Advantage (Santa Monica, CA) and faculty members from the Massachusetts Institute of Technology and Harvard Medical School/Massachusetts General Hospital.

The goal is to create an AI engine that will be incorporated into Imaging Advantage's proprietary exam routing technology. The idea is for the AI to instantly pre-read digital x-rays, identifying potential areas of injury and disease. The artificial intelligence will continuously learn from Imaging Advantage's expanding database of 7 billion images.  The algorithm will be applied prior to x-ray images being routed to one of the 500 board-certified radiologists who are connected via the cloud to Imaging Advantage's platform.  

"Inconsistency in testing and access to care contribute significantly to $1 trillion of waste in the $2.8 trillion U.S. healthcare industry," Brian Hall, Imaging Advantage's president and chief operating officer, said in a news release.  "If successful, Singularity will introduce a solution with potential to transform radiology by providing faster, more accurate and less expensive diagnostic testing, representing an indispensable innovation for radiologists."

Once Singularity Healthcare figures out how to successfully integrate AI into x-Rays, Hall sees potential to expand the technology to CTs and MRIs, as well as other areas of diagnostic testing. "The goal is to create a useful tool for radiologists, who are in shortage both domestically and internationally," Hall said. "Radiologists will continue to be indispensable," he insisted.

AI is a hot area in the medical device space. IBM, for example, spent $1 billion last year to acquire Merge Healthcare and its imaging technology platform used in thousands of healthcare sights. The deal was described as giving "sight" to IBM's Watson supercomputer, enabling Merge's customers to use the Watson Health Cloud to to analyze and cross-reference medical images against a deep trove of lab results, electronic health records, genomic tests, clinical studies, and other health-related data sources. 

Stephen Holloway, associate director for IHS Inc., noted last year that AI could prove to be a disruptive force in the medical imaging space, providing benefits but also raising ethical and legal issues along the way.

Chris Newmarker is senior editor of Qmed and MPMN. Follow him on Twitter at @newmarker.

Like what you're reading? Subscribe to our daily e-newsletter.