A high profile partnership may soon pave the way for faster and more accurate X-ray interpretation. Singularity Healthcare — which combines Imaging Advantage (IA), the largest platform provider of cloud-based radiology service in the U.S., with Massachusetts Institute of Technology and Harvard Medical School/Massachusetts General Hospital (MGH) — have announced plans to develop an artificial intelligence X-ray engine.

The technology, which is expected to launch within the next few months, will use an algorithm to learn from IA’s seven billion images and analyze an X-ray to identify potential areas of disease and injury. The images are then sent to one of the 500 radiologists connected to IA’s cloud-based platform.

Dr. SP Kothari, Gordon Y. Billard professor of management at MIT’s Sloan School of Management, will lead the project, and Dr. Sanjay Saini, professor of radiology at Harvard Medical School and vice-chairman of radiology at MGH, will advise on imaging quality and utility to radiologists.
Singularity hopes to provide a solution in a widely applicable manner to problems found in the U.S. health care system, since X-ray exams constitute approximately 50 percent of all radiology exams, according to the announcement, and radiology is a significant factor in limiting patient flow and treatment in a hospital emergency department.

“Inconsistency in testing and access to care contribute significantly to $1 trillion of waste in the $2.8 trillion U.S. health care industry,” said Brian Hall, president and COO of Imaging Advantage, in a statement. "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."

Dr. Kalyan Veeramachaneni, principal research scientist at MIT’s Institute for Data, Systems and Society, who is also part of the team, is interested in seeing how decisions made at the initial, raw representation stage impact the final predicted accuracy efficacy.

Hall added that this technology has the potential to expand to CT and MR, as well as other areas that have time-consuming diagnostic testing. The engine will not take the place of radiologists, but only help them work more efficiently.

Singularity Healthcare is not the only partnership geared toward artificial intelligence interpretation of images. IBM acquired Merge, an imaging platform with 30 million medical images on it, back in October of 2015. Avicenna, a software that is part of Watson Health, is currently being tested in cardiology and breast radiology on anonymous images and data, but will soon be tested using real patient information.

IBM hopes to have Watson help radiologists compare one image with other images and the patient’s EHR.

Business Affairs Homepage