NYU School of Medicine’s Michael Recht, M.D., chair of radiology; Daniel Sodickson; and Yvonne Lui, M.D., director of artificial intelligence, examine MRI scans of a knee at NYU Langone Health. Photo courtesy NYU School of Medicine. (Credit: NIBIB)

The cost and time required to obtain a magnetic resonance imaging (MRI) scan may be significantly reduced in the future, thanks to the application of artificial intelligence (AI) strategies. The imaging project, called fastMRI, will use AI to make MRI scans up to 10 times faster.

The New York University (NYU) School of Medicine’s Center for Advanced Imaging Innovation and Research (CAI2R) is collaborating with the Facebook Artificial Intelligence Research (FAIR) group to work with researchers in academia to advance the state-of-the art in the rapidly emerging AI field. FAIR will provide access to AI models, metrics, and techniques; CAI2R offers extensive medical imaging expertise and an enormous dataset. The resulting tools and data will be openly accessible to the research community.

The fastMRI project builds on work conducted by this NIBIB-funded center to perform image reconstruction with deep learning. It is exciting that the technology industry is interested in real-world medical imaging problems like this. Facebook brings to bear new thinking and complementary expertise, and advanced computational tools that will accelerate and amplify the impact of the center’s work.”

In their collaboration, CAI2R and FAIR will develop ways to generate diagnostic-quality images with only a fraction of the data normally needed. This complex problem is similar to other AI problems that FAIR engages on, but is its first foray into AI for medical imaging.

AI has been explored widely for the automated interpretation of pre-existing images, it is only more recently that it has been used to generate images. The fastMRI project seeks to use similar techniques for medical imaging in order to create rigorously faithful renderings, but with less data and time than ever was required before.

AI can learn complicated functions that succinctly represent the typical relationships between various features in an image. These relationships can then be ascertained with a comparatively small number of data points.

NYU School of Medicine will provide the images from 10,000 clinical cases that will be used by the fastMRI project. It amounts to about 3 million knee, brain, and liver MRIs. Whereas typical data-driven AI approaches require large data sets to train the neural networks robustly, the fastMRI project will investigate different approaches to reconstruction of under-sampled data, some of which require smaller data sets.