New AI imaging technique could improve quality, speed—without collecting more data
Researchers from Massachusetts General Hospital (MGH) have developed a machine learning and artificial intelligence (AI)-based technique that may generate higher quality images without having to collect additional data.
The new technique, AUTOMAP (dubbed "automated transform by manifold approximation"), produces images while obtaining less amounts of data, ultimately reducing CT and PET scan radiation doses and reducing time for MRI scans, according to a recent Massachusetts General Hospital press release. AUTOMAP also contains an image reconstruction algorithm predetermined by deep learning AI technology.
"With AUTOMAP, we've taught imaging systems to 'see' the way humans learn to see after birth, not through directly programming the brain but by promoting neural connections to adapt organically through repeated training on real-world examples," wrote co-author Bo Zhu, PhD, a research fellow in the MGH Martinos Center in the study, published online March 22 in Nature. "This approach allows our imaging systems to automatically find the best computational strategies to produce clear, accurate images in a wide variety of imaging scenarios."
Additionally, AUTOMAP's processing speed can reconstruct images in milliseconds, which could accelerate a physician's clinical decisions regarding imaging protocols while their patient is still in the scanner.
"Some types of scans currently require time-consuming computational processing to reconstruct the images; in those cases, immediate feedback is not available during initial imaging, and a repeat study may be required to better identify a suspected abnormality. AUTOMAP would provide instant image reconstruction to inform the decision-making process during scanning and could prevent the need for additional visits," said co-author Matt Rosen, PhD, director of the Low-field MRI and Hyperpolarized Media Laboratory and co-director of the Center for Machine Learning at the MGH Martinos Center, in a prepared statement.
According to the press release, the researchers hope that AUTOMAP can play a role in advancing computer-aided diagnostics by providing high quality images for graphical processing unit accelerated computers to ensure more accurate diagnostic evaluations.
A recent graduate from Dominican University (IL) with a bachelor’s in journalism, Melissa joined TriMed’s Chicago team in 2017 covering all aspects of health imaging. She’s a fan of singing and playing guitar, elephants, a good cup of tea, and her golden retriever Cooper.