AutoContour Model RADAC V3
Radformation, Inc.AutoContour Model RADAC V3 is an AI-enabled software designed to automatically contour anatomical structures in CT and MR images to assist radiation treatment planners in preparing radiation therapy plans more efficiently. It uses deep learning models to generate contours of organs and tumors, allowing clinicians to review and adjust as needed, which streamlines the treatment planning process and improves accuracy.
Intended Use
AutoContour is intended to assist radiation treatment planners in contouring and reviewing structures within medical images in preparation for radiation therapy treatment planning.
Technology
The device is a software system utilizing DICOM-compliant CT and MR images as input and applies machine learning-based contouring models trained on extensive datasets of adult patients. It includes a .NET client, a local agent service monitoring datasets, and a cloud-based contouring server. Outputs are DICOM RT Structure Sets usable in radiation therapy planning systems.
Performance
Validation involved training and testing on independent CT and MR datasets, including publicly available records. Dice Similarity Coefficients (DSC) were used to measure accuracy, with mean DSC exceeding specified thresholds (0.8 for large, 0.65 for medium, and 0.5 for small structures). External clinical reviews rated the contours highly, averaging 4.4 to 4.5 out of 5, confirming clinical appropriateness. The software met all functional and safety requirements without the need for clinical trials.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
3/13/2023
1 month - 2
FDA Approval
4/14/2023
Other devices from Radformation, Inc.
- AutoContour (Model RADAC V4)2024 • 510K
- AutoContour Model RADAC V22022 • 510K
- AutoContour2020 • 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.