AutoContour RADAC V2 is a software tool that helps radiation treatment planners by automatically outlining anatomical structures in CT and MR images to assist in radiation therapy treatment planning. It uses machine learning models trained on large datasets to generate these contours and allows clinicians to review and modify them before exporting for use in treatment.
AutoContour is intended to assist radiation treatment planners in contouring and reviewing structures within medical images in preparation for radiation therapy treatment planning.
AutoContour RADAC V2 is a software system using machine learning-based contouring applied to DICOM-compliant CT and MR images. It consists of a .NET client application, a local agent service, and a cloud-based automatic contouring server. The software performs automatic contouring of anatomical structures with expanded support to MR images and deformable image registration, enabling contour transfer between image sets.
Performance testing included extensive non-clinical validation using independent test datasets for CT and MR images. Results show high Dice Similarity Coefficient (DSC) values above established thresholds for large, medium, and small structures, confirming accuracy comparable to predicate and reference devices. Sensitivity and specificity tests on independent patient samples demonstrated robust performance. Risks from automatic contouring are mitigated by requiring user review and approval before exporting results.
No predicate devices specified
Submission
3/2/2022
FDA Approval
8/24/2022
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.