Intended Use

The Deep Learning Image Reconstruction option is a deep learning based reconstruction method intended to produce cross-sectional images of the head and whole body by computer reconstruction of X-ray transmission data taken at different angles and planes, including Axial, Helical (Volumetric), and Cardiac acquisitions, for all ages. It can be used for head, whole body, cardiac, and vascular CT applications.

Technology

Deep Learning Image Reconstruction uses a dedicated Deep Neural Network (DNN) trained on the CT scanner data to model noise propagation and remove noise, producing images with an appearance similar to traditional filtered back projection but with improved noise, low contrast detectability, spatial resolution, and artifact suppression. It integrates into the scanner’s raw data-based reconstruction chain and supports user-selectable reconstruction strengths (Low, Medium, High).

Performance

Non-clinical bench testing and a clinical reader study were performed. Bench testing compared DLIR images to ASiR-V reconstructed images using identical raw datasets focusing on low contrast detectability, image noise, spatial resolution, artifact suppression, and other image quality metrics. A clinical study with 40 retrospective cases evaluated by 6 board certified radiologists showed DLIR produced diagnostic quality images with significantly better subjective image quality than ASiR-V. The device passed design control testing with no additional hazards identified.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    12/21/2021

    1 month
  • 2

    FDA Approval

    2/18/2022

Ready to Sharpen Your Edge?

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.