Rapid MRI scans generated with Artificial Intelligence (AI) can be just as accurate, useful and reliable as traditional magnetic resonance imaging, shows a study by Facebook AI researchers and NYU Langone Health.
For the study, radiologists reviewed two sets of knee MRIs from 108 patients — one set using the standard imaging techniques and the other set using the fast MRI AI model.
The results, published in the American Journal of Roentgenology, found no significant differences in the radiologists' evaluations.
Follow NewsGram on LinkedIn to know what's happening around the world.
NYU Langone Health and Facebook teamed up to launch the fast MRI initiative two years ago in a bid to speed up MRI scans.
The fastMRI scans require four times less data, patients can be imaged much faster and spend less time in the scanning machine, said the study. Pexels
Because the fastMRI scans require four times less data, patients can be imaged much faster and spend less time in the scanning machine, said the study.
"This is an important step toward the clinical acceptance, and utilization of AI-accelerated MRI scans," Michael Recht, Professor and Chair of Radiology at NYU Langone Health, said in a statement.
To create the image that your clinician or radiologist reviews, the MRI machine uses magnetic fields that interact with hydrogen atoms in the body's soft tissue and vital organs.
Those atoms then emit electromagnetic signals that act like beacons, indicating where in the body the atoms are located.
The signals are collected by the scanner as a sequence of individual 2D frequency measurements, known as k-space data.
Once all the data is finally collected, the system then applies a complex mathematical formula — an inverse Fourier transform — to that raw k-space data to create detailed MR images of the knee, back, or brain, or other area of the body.
Without a complete set of data points, the math cannot pinpoint exactly where every signal comes from.
The fastMRI team used an entirely different way to create an image — one that requires far less raw data.
The researchers built a neural network and trained it using the world's largest open source data set of knee MRIs, which was created and shared by NYU Langone Health and as part of the fastMRI initiative.
The model then learned to generate complete images from the limited data. Unsplash
The fastMRI research team removed roughly three-fourths of the raw data in each scan and then fed the remaining info into the AI model.
The model then learned to generate complete images from the limited data.
Importantly, the images produced by the AI model did not just look like generic MRIs; the AI-generated images matched the ground truth image created by the standard slow MRI process, Facebook said.
The study showed that fastMRI can generate "diagnostically interchangeable" MRI images of knee injuries while using about 75 per cent less raw data from the scanning machine.
While the study focused specifically on knee scans, the researchers are now working to extend the results to other parts of the body, such as the brain. (IANS)