Introduction
Magnetic Resonance Imaging (MRI) is an important part of radiologic exam which provides excellent soft tissue contrast under
diverse contrast mechanisms. Despite this benefit and the lack of ionizing radiation, MR exams typically take long time to
complete and causes patient discomfort in many aspects.
SwiftMR™ is FDA 510(k)-cleared* deep learning (DL)-based software medical device developed by AIRS Medical. SwiftMR™
reduces image noise and increases sharpness of MR images based on its vast training dataset of high-quality MR images.
The following clinical cases were collected from two different research collaborations with Seoul National University Hospital
(Seoul, Korea) and Seoul Asan Medical Center (Seoul, Korea). Both studies were approved by the respective institutional
review board (IRB). The purpose of these studies was to clinically evaluate the quality of brain MR images processed with
SwiftMR™ against the clinical standard-of-care images.
* FDA 510(k)-cleared for Standard of Care (SOC) brain, spine(C/T/L) and MSK (Knee, ankle, shoulder, and hip) MR images (K220416).