Supercomputing Enables Real-Time, In-Depth MRI Analysis Share your comment!

mri scan review

MRI results that used to take days or hours can now be ready in minutes – thanks to technology powered by a supercomputer.

Researchers from the Texas Advanced Computing Center (TACC), the University of Texas Health Science Center (UTHSC) and Philips Healthcare have built a new automated system that can provide in-depth analyses of MRI scans within about five minutes.

The proof-of-concept could not only reduce patient callbacks if there’s a problem with a scan, it can save millions of dollars annually in healthcare costs and advance “precision medicine,” which is an effort to customize healthcare, according to a recent TACC press release.

The system combines the imaging capabilities of a Philips MRI scanner with the processing power of TACC’s Intel Xeon-based Stampede supercomputer. The two systems communicate through an Application Programming Interface (API) developed by TACC, called the Agave API Platform.

“This gives radiologists and other clinical staff the means to provide real-time quality control, precision medicine and overall better care to the patient,” said William (Joe) Allen, a life science researcher for TACC.

During the demonstration project, UTHSC staffers performed MRI scans on a patient with a cartilage disorder. Data from the MRIs were transmitted via a proxy server to the Stampede supercomputer, which used an analysis tool developed by UTHSC to analyze the scans. The analysis can alert clinicians to scrutinize an area of interest, which can accelerate the discovery of medical problems, the release said.

Researchers said they could use the Agave API Platform for other medical devices in the future, which can provide physicians with real-time analyses of many kinds of biomedical data.

“We are very excited by this fruitful collaboration with TACC,” said Refaat Gabr, an assistant professor of Diagnostic and Interventional Imaging at UTHSC and the project’s lead researcher. “By integrating the computational power of TACC, we plan to build a completely adaptive scan environment to study multiple sclerosis and other diseases.”


Posted on March 13, 2017 by Wylie Wong, Slashdot Media Contributing Editor