New analyze on deep discovering technologies for increasing MRI picture top quality revealed in European Radiology

SwiftMR™, an AI-driven MRI reconstruction answer from AIRS Medical proved its performance for maximizing the graphic high-quality of 3D substantial-resolution MRI

SEOUL, South Korea, Nov. 25, 2022 /PRNewswire/ — A new review posted in European Radiology demonstrated that SwiftMR, an AI-run MRI reconstruction option from AIRS Professional medical, successfully denoises 3D MR illustrations or photos and enhances its graphic quality by employing regimen medical scans only.

The examine aimed to acquire a deep neural community (DNN)–based sound reduction and impression high quality enhancement by only working with regimen medical scans and analyzing its general performance in 3D significant-resolution MRI. The examine was performed by AIRS Clinical and Dr. Jinhee Jang, MD, Ph.D. of Seoul St. Mary’s Healthcare facility. The retrospective study incorporated T1-weighted magnetization-geared up immediate gradient-echo (MP-RAGE) photos from 185 scientific scans.

Qualitative evaluation between common MP-RAGE and DNN-based mostly MP-RAGE was done by two radiologists in picture good quality, fine structure delineation, and lesion conspicuity. Quantitative evaluation was done with full sampled data as a reference by measuring quantitative error metrics and volumetry at seven various simulated sound stages. DNN software on VWI was evaluated by two radiologists in picture good quality.

The examine exhibits that DNN-based mostly MP-RAGE outperformed common MP-RAGE in all graphic high quality parameters (normal scores = 3.7 vs. 4.9, p < 0.001). In the quantitative evaluation, DNN showed better error metrics (p < 0.001) and comparable (p> .09) or far 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.

Story continues

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.

About AIRS Medical

AIRS Medical Inc., founded in Oct 2018, is a medical AI solution provider headquartered in Seoul, Korea, that develops innovative products and services to improve the patient experience. AIRS Medical helps healthcare systems achieve greater institutional efficiency in areas where a lack of productivity limits clinical value.

For more information, visit airsmed.com

Euntak Jin
+82-01046972824
[email protected]

View original content:https://www.prnewswire.com/news-releases/new-study-on-deep-learning-technology-for-improving-mri-image-quality-published-in-european-radiology-301687123.html

SOURCE AIRS Medical