Spectral Bone Marrow
GE Medical Systems, LLCSpectral Bone Marrow is an automated deep learning-based software designed for spectral CT images of the body and extremities. It segments bone regions and creates enhanced, color-coded images to help radiologists better visualize bone marrow. This assists in diagnosing traumatic and non-traumatic bone conditions more efficiently by providing improved image visualization and an automated clinical workflow.
Intended Use
An automated image processing software application utilizing deep learning for bone segmentation to facilitate optimized visualization of bone marrow in spectral body and extremity CT images for reviewing traumatic and non-traumatic bone pathologies.
Technology
Deep learning based bone segmentation algorithm that generates fused colored material density images (e.g. water minus hydroxyapatite) overlayed on monochromatic or Virtual Unenhanced spectral CT images. Fully automated image post-processing workflow hosted on GE Edison Health Link platform, providing secondary capture DICOM outputs for clinical review.
Performance
Non-clinical testing included design control, risk management, software and system testing. Engineering bench testing verified accurate bone segmentation using a dataset of 146 retrospective spectral CT exams with ground truth from three board-certified radiologists. Clinical testing involved retrospective case assessments by three expert radiologists, demonstrating additional diagnostic value and increased reader efficiency.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
11/22/2022
3 months - 2
FDA Approval
3/9/2023
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.