AutoContour (Model RADAC V4)
Radformation, Inc.AutoContour (Model RADAC V4) by Radformation, Inc. is a software tool designed to automatically contour anatomical structures on CT and MR images to aid radiation treatment planning. Using machine learning, it helps clinicians create accurate contours of organs and tissues, streamlining the preparation process for radiation therapy and improving planning precision.
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
AutoContour Model RADAC V4 uses DICOM-compliant CT and MR image inputs and employs deep learning-based models to automatically contour various structures relevant to radiation therapy planning. The system includes a .NET client on Windows, a local agent monitoring network storage, and a cloud-based contouring service. It supports registration (manual, automatic rigid, and deformable) and outputs DICOM RTSTRUCT data for import into treatment planning systems.
Performance
Performance was validated using mean Dice Similarity Coefficient (DSC) testing on independent datasets with expert ground truth contours. CT and MR models passed predefined DSC thresholds across small, medium, and large structure categories. Additional clinical testing showed average expert ratings indicating clinical usefulness with minor edits. Testing datasets included data from multiple institutions and public repositories.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
9/10/2024
3 months - 2
FDA Approval
12/9/2024
Other devices from Radformation, Inc.
- AutoContour Model RADAC V32023 • 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.