An AI algorithm can help radiology providers reduce certain MRI scan times by 57% while still maintaining image quality, according to new research published Monday.
Scientists with the University of Cologne in Germany recently tested this approach via a prospective study involving 20 volunteers. Sequences were acquired with two different resolutions (standard and low), and two radiologists assessed the scans.
The fast 2D knee MRI protocol was achieved by combining compressed sensing with a new deep learning-based image reconstruction approach, experts explained in the European Journal of Radiology [1]. Results were compared against images gathered using the more established compressed sensing method.
This new approach outperformed traditional CS in both standard and low-resolution acquisitions, leading to better ratings for the novel protocol compared to the reference scans.
“The decrease in scan duration allows for a larger number of examinations within the same timeframe, enhances the comfort of the patient, and lessens the chances of image distortions caused by movement,” Dr. Robert Terzis, with the institution’s Department of Diagnostic and Interventional Radiology, and co-authors wrote March 9. “To our best knowledge, this is the first study investigating the impact on scan time reduction and image quality, when combining compressed sensing with the latest deep learning-based image reconstruction approach (CS-SuperRes).”
Terzis et al. conducted their study using a 3T MRI scanner from Philips (Ingenia Elition X). Radiologists (blinded to which images they were reviewing) gave higher ratings to the CS-SuperRes images versus the standard compressed sensing alternatives. The higher rating was statistically significant, especially for low-resolution acquisitions, which were comparable in quality. The new approach was able to reduce scan times from about 11:01 minutes down to 4:46.
You can read further details about the study, including potential limitations, at the link below.
Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic.