Deep Learning Image Reconstruction
GE Healthcare Japan CorporationDeep Learning Image Reconstruction by GE Healthcare is a software that uses deep neural networks to reconstruct high-quality CT images from X-ray transmission data. It helps radiologists by producing images with improved noise reduction, spatial resolution, and artifact suppression, suitable for head, whole body, cardiac, and vascular CT scans at routine clinical throughput.
Intended Use
The Deep Learning Image Reconstruction software is intended for head, whole body, cardiac, and vascular CT Scans.
Technology
Deep Learning Image Reconstruction uses a dedicated Deep Neural Network (DNN) trained on Revolution family CT Scanners to generate CT images with appearance similar to traditional filtered back projection (FBP) images, while maintaining performance in dose, noise, detectability, resolution, and artifact suppression. It integrates into the raw data-based reconstruction chain producing DICOM compatible TrueFidelity CT Images with selectable strength levels (Low, Medium, High) and normal reconstruction throughput.
Performance
Extensive bench testing and a clinical reader study were performed. Bench tests compared images using standard metrics such as noise, low contrast detectability, spatial resolution, artifact suppression, CT number accuracy, contrast to noise ratio, and performance under pediatric and low dose lung cancer screening scenarios. Clinical testing involved 60 retrospective cases evaluated by 9 board-certified radiologists assessing image quality and image noise texture, supporting substantial equivalence and performance claims with no new safety concerns.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
7/2/2021
2 months - 2
FDA Approval
9/17/2021
Other devices from GE Healthcare Japan Corporation
- True Enhance DL2024 • 510K
- Deep Learning Image Reconstruction2023 • 510K
- Deep Learning Image Reconstruction2022 • 510K
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.