Introduction
Magnetic Resonance Imaging (MRI) plays an important role in the examination and diagnosis of musculoskeletal diseases in
the clinical practice. The major advantage of MRI is that unlike plain radiography and Computed Tomography (CT), MRI does
not require ionizing radiation while providing excellent soft tissue contrast of the cartilage, ligament, tendon, and muscle
structures with relatively high spatial resolution. However, MR exams typically require long scan times – limiting its use compared
to other modalities. This limitation is stressed in patients with musculoskeletal conditions since they are prone to
movement during scans.
SwiftMR™ is a 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.
This allows alleviations of image quality degradation caused by accelerated scans, while also decreasing patient discomfort
and improving scanner throughput.
The following clinical cases were collected from a research collaboration with Yonsei University Severance Hospital (Seoul,
Korea). This study was approved by the institutional review board (IRB) and informed consents were received from all enrolled
subjects who required MRI exams due to internal derangements of the knee. The purpose of this study was to clinically compare
the quality of knee MR images acquired at institutional standard protocol and accelerated protocol reconstructed with
SwiftMR™.
* FDA 510(k)-cleared for Standard of Care (SOC) brain, spine(C/T/L) and MSK (Knee, ankle, shoulder, and hip) MR images (K220416).