Deep Learning Image Reconstruction for Gemstone Spectral Imaging
GE Medical Systems, LLCDeep Learning Image Reconstruction for Gemstone Spectral Imaging by GE Medical Systems is an AI-powered CT image reconstruction method designed to produce high-quality cross-sectional CT images from dual-energy X-ray data. It is intended for whole body, vascular, and contrast-enhanced head CT applications, enhancing image quality with a deep neural network-based algorithm that improves low contrast detectability, noise reduction, and artifact suppression, supporting accurate and reliable diagnosis.
Intended Use
The Deep Learning Image Reconstruction for Gemstone Spectral Imaging option is intended for whole body, vascular, and contrast enhanced head CT applications.
Technology
Uses a dedicated convolution neural network (CNN) trained specifically on dual-energy CT images to reconstruct CT images that maintain or improve upon traditional filtered back projection (FBP) images and ASiR-V performance, producing monochromatic, material decomposition, and virtual unenhanced images. Integration into the existing CT scanner's raw data-based reconstruction chain enables generation of DICOM-compatible images with selectable reconstruction strengths (Low, Medium, High).
Performance
The device was tested through extensive bench and clinical testing including low contrast detectability, image noise, spatial resolution, contrast to noise ratio, CT number accuracy, material decomposition accuracy, metal artifact reduction, and pediatric phantom testing. A clinical reader study with 40 retrospective cases evaluated by multiple radiologists confirmed that DLIR-GSI produces diagnostic quality images with preferred noise textures compared to ASiR-V, supporting safety and effectiveness.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
6/26/2020
5 months - 2
FDA Approval
12/10/2020
Other devices from GE Medical Systems, LLC
- SIGNA MAGNUS2024 • 510K
- Sonic DL2023 • 510K
- Critical Care Suite with Pneumothorax Detection AI Algorithm, Critical Care Suite 2.1, Critical Care Suite2023 • 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.