New study on deep learning technology for improving MRI image quality published in European Radiology

SwiftMR™, an AI-powered MRI reconstruction solution from AIRS Medical proved its performance for enhancing the image quality of 3D high-resolution MRI

SEOUL, South KoreaNov. 25, 2022 /PRNewswire/ — A recent study published in European Radiology demonstrated that SwiftMR, an AI-powered MRI reconstruction solution from AIRS Medical, successfully denoises 3D MR images and improves its image quality by using routine clinical scans only.

The study aimed to develop a deep neural network (DNN)–based noise reduction and image quality improvement by only using routine clinical scans and evaluating its performance in 3D high-resolution MRI. The study was conducted by AIRS Medical and Dr. Jinhee Jang, MD, Ph.D. of Seoul St. Mary’s Hospital. The retrospective study included T1-weighted magnetization-prepared rapid gradient-echo (MP-RAGE) images from 185 clinical scans.

Qualitative evaluation between conventional MP-RAGE and DNN-based MP-RAGE was performed by two radiologists in image quality, fine structure delineation, and lesion conspicuity. Quantitative evaluation was performed with full sampled data as a reference by measuring quantitative error metrics and volumetry at seven different simulated noise levels. DNN application on VWI was evaluated by two radiologists in image quality.

The study shows that DNN-based MP-RAGE outperformed conventional MP-RAGE in all image quality parameters (average scores = 3.7 vs. 4.9, p < 0.001). In the quantitative evaluation, DNN showed better error metrics (p < 0.001) and comparable (p > 0.09) or better (p < 0.02) volumetry results than conventional MP-RAGE. DNN application to VWI also revealed improved image quality (3.5 vs. 4.6, p < 0.001).

“We are very pleased that we have proved SwiftMR™ contributes to not only reducing time but also helps make images good to great, eventually contribute radiologists could read images with confidence.” remarked Hyeseong Lee, MD, CEO of AIRS Medical. “We are expecting more adaptions and collaborations with radiologists around the world thus we could grow together.” he added.

AIRS Medical recently announced its participation in the 108th Scientific Assembly and Annual Meeting of the RSNA 2022, held from November 27 to 30th in Chicago. During the event, AIRS Medical showcases its award-winning MRI reconstruction solution SwiftMR™and also delivering two oral presentations at scientific session.

“We are proud of ourselves since it is quite unusual for a startup to deliver oral presentations at RSNA scientific session. Being adopted as oral presentation means recognition of academically important achievements.” he added.