Facebook, under criticism for its business practices, seems to be branching off into other industries including medicine. Case in point is a partnership with NYU School of Medicine’s Department of Radiology to develop artificial intelligence (AI) tools to improve how fast MRIs can be performed.
Currently, a simple scan of a knee can take up to a half hour to perform. This is compared to only a few minutes, or even seconds, for X-rays and CT scanners. Part of the problem is the enormous amounts of data that MRI machines generate. The more data, the better the picture, but also more time is required to render this data into a high quality image.
Top: (L) Raw MRI data before it’s converted to an image. To capture full sets of raw data for a diagnostic study, MRI scans can often take 15-60+ minutes. (R) MRI image of the knee reconstructed from fully sampled raw data. Bottom: (L) Raw MRI data that has been under-sampled. The MRI scan to capture this data was conducted more quickly than one to capture full data for a diagnostic study, but under-sampling generates noise and artifacts in the resulting MRI image. (R) MRI image of the knee reconstructed from subsampled data. The fastMRI project seeks to use AI to create useful MRI images, without noise and artifacts like those shown here.
The Facebook/NYU partnership is working to minimize the amount of data that is captured, instead relying on computers to reconstruct the image from imperfect inputs. If this is successful, we may see a 10x reduction in scan times, which would lead to lower costs for MRIs and a much greater utilization of these machines for medical applications where they’re now only sparsely used.
The technology the team is working relies on artificial neural networks that can recognize what they’re actually looking at and automatically fill in areas that are poorly resolved. They’re working on training these neural networks using previously captured MRIs and are expanding NYU’s previous efforts at harnessing artificial intelligence for MRI data processing.
The researchers plan to release their technology in an open source format to allow other teams to take advantage of it and for companies making MRI software to grab and use it in their applications.
Some more details about the project according to Facebook:
The imaging data set used in the project, collected exclusively by NYU School of Medicine, consists of 10,000 clinical cases and comprises approximately 3 million magnetic resonance images of the knee, brain, and liver.
All data, including both images and raw scanner data, are fully stripped of patient names and all other protected health information. The work is fully HIPAA-compliant and approved under NYU Langone’s Institutional Review Board, which oversees all human subject research at the medical center. The project is governed by strict human subject data protection protocols and supported by the world-class information technology team at NYU Langone.
The magnetic resonance images (which generally represent small targeted regions of anatomy) used for this project have been scrubbed of any potential distinguishing features. Comparisons of the performance between AI-based reconstructions and traditional reconstructions will, likewise, be devoid of any identifying information. No Facebook data of any kind will be used in the project.
Via: Facebook…
