Auto Segmentation
GE Medical Systems, LLCAuto Segmentation by GE Medical Systems is an AI software tool that automatically generates organ-at-risk contours from CT scans to help radiation oncologists, medical physicists, and dosimetrists speed up radiation therapy planning. It produces initial segmentation contours that users can review and adjust, improving workflow efficiency and precision in radiation treatment.
Intended Use
Auto Segmentation is intended to be used as a workflow tool for initial anatomy segmentation of organs at risk on CT images as an aid in radiation therapy planning after user confirmation.
Technology
The device uses deep learning algorithms to automatically generate contours of organs at risk from CT images and outputs a Radiotherapy Structure Set (RTSS) DICOM that can be reviewed and edited by RT practitioners. It supports single energy CT images including contrast and non-contrast, from GE and non-GE scanners, for adult patients.
Performance
Performance testing included training on 911 CT exams and evaluation on 302 independent CT radiation therapy planning exams from multiple global clinical sites. The device was validated against manually annotated ground truth contours using DICE similarity coefficients, demonstrating performance equal or superior to predicate devices, consistent across scanner vendors, demographics, and imaging parameters. Clinical testing with radiation therapy practitioners confirmed contour adequacy for clinical use.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
1/11/2023
3 months - 2
FDA Approval
5/4/2023
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.