Developing Rapid MRI Scanning

New York University (NYU) School of Medicine launched the Center for Advanced Imaging Innovation and Research (CAI2R) in 2014 to develop rapid, comprehensive imaging with a focus on MRI scanning.

CAI2R directed by Daniel Sodickson, MD, PhD, Professor of Radiology and Physiology and Neurosciences at NYU’s School of Medicine, receives grant support from the National Institute of Biomedical Imaging and Bioengineering (NIBIB) within NIH.

In August, the NYU Center established a collaboration with the Facebook Artificial Intelligence Research (FAIR) group launched by Facebook in 2013, to work with researchers in academia to advance the state-of-the-art in the emerging Artificial Intelligence (AI) field to speed up making MRI scans.

The imaging project called fastMRI will provide images from 10,000 clinical cases and by using AI will make MRI scans up to ten times faster. FAIR will provide access to AI models, metrics, and techniques. CAI2R offers extensive medical imaging expertise and an enormous data set. The resulting tools and data will be openly accessible to the research community.

Dr. Sodickson explains, “Medical images like almost all other images are compressible using the kinds of computer algorithms that are commonly available on any cell phone. Once all the data has been gathered, the resulting image can be analyzed and unimportant data can be discarded. So maybe some degree of pre-compression will be possible when providing images.

Some say that AI will displace humans in medical imaging. Dr. Sodickson suggests that this fear will abate as people will see the benefit in human machine collaborations. Everybody knows that there are tasks that radiologists absolutely hate to do. Repetitive tasks can likely be handled by machines but other more integrative tasks will enable machines to assist. Humans are still going to play a major role in the radiology field for many years to come.