Goldman Sachs-backed imaging startup partners with MIT, Harvard for machine learning

Medical imaging is expected to be one of the early useful applications of artificial intelligence and machine learning in healthcare. And a slew of deals have been built around that premise in the last year or so--IBM Watson Health bought cloud-based imaging company Merge for $1 billion; Philips partnered with Hitachi to incorporate AI into its image management; and GE added deep learning software from startup Arterys to its cardiac imaging.

SP Kothari, professor of management at MIT's Sloan School of Management

Now, another major cloud-based imaging startup is working to incorporate machine learning, first into X-ray analysis and eventually into other imaging modalities including CT and MRI. The Goldman Sachs-backed startup Imaging Advantage, which reportedly tapped into up to $250 million in debt in January 2015, has partnered with the Massachusetts Institute of Technology as well as Harvard Medical School and Massachusetts General Hospital to develop an artificial intelligence engine known as Singularity Healthcare. The result is expected to launch this quarter.

"We have a number of opportunities for research and innovation at MIT, but were particularly intrigued by the bold initiative proposed by Imaging Advantage," said SP Kothari, a professor of management at MIT's Sloan School of Management who will lead the project, in a statement. "Given IA's platform approach to healthcare delivery, national scale and significant imaging data set, and the contribution of Dr. Saini from MGH, one of the leading global radiology teaching and research institutions, the project is not only achievable, but also has potential to touch nearly every person in world. This is how we think artificial intelligence and deep learning should be developed and deployed."

The idea is to incorporate artificial intelligence into existing exam routing technology. It would pre-read digital X-rays and identify potential areas of injury or disease. The algorithm will be applied ahead of being read by a radiologist, of which Imaging Advantage has 500 for centralized, cloud-based image analysis at about 400 facilities. The expectation is that the system will continuously learn from conducting this analysis on images; Imaging Advantage already houses 7 billion images.

Brian Hall, Imaging Advantage COO

"We believe diagnostics is the gateway for the integration of artificial intelligence in healthcare," said Brian Hall, Imaging Advantage's President and COO.  "Once we successfully develop this mechanism for X-rays, we see the potential to expand the technology to CTs and MRIs, as well as other areas of time consuming diagnostic testing. The goal is to create a useful tool for radiologists, who are in shortage both domestically and internationally."

He concluded, "If successful, Singularity will introduce a solution with potential to transform radiology by providing faster, more accurate and less expensive diagnostic testing."

- here is the announcement