AIR Recon DL is a deep learning-based software feature for GE Healthcare MRI systems that improves image quality by reducing noise and ringing artifacts in MRI images. It helps clinicians by enabling shorter scan times without losing image clarity, thus improving patient comfort and diagnostic accuracy across multiple anatomies and MR field strengths.
AIR Recon DL is a deep learning based reconstruction technique that is available for use on GE Healthcare 1.5T, 3.0T, and 7.0T MR systems. AIR Recon DL reduces noise and ringing (truncation artifacts) in MR images, which can be used to reduce scan time and improve image quality. It is intended for use with all anatomies and patients of all ages, with possible use of contrast agents depending on the anatomy.
AIR Recon DL is a software feature integrated into GE MR systems that uses deep learning convolutional neural networks for image reconstruction to remove noise and ringing artifacts. The algorithm was trained with similar network architecture and methods used in the legally marketed predicate device. It has been modified to support additional pulse sequences such as PROPELLER and 3D Cartesian acquisitions and is compatible across 1.5T, 3.0T, and 7.0T MRI systems.
Performance testing included nonclinical phantom studies assessing signal to noise ratio, sharpness, and low contrast detectability, as well as clinical reader evaluation on 133 cases across various anatomies and pulse sequences. Results confirmed improved or equivalent image quality with AIR Recon DL compared to conventional reconstruction, maintenance of quantitative accuracy, and ability to reduce scan times without degradation of images. No new safety risks were identified.
No predicate devices specified
Submission
11/24/2021
FDA Approval
6/8/2022
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.