AI-Rad Companion Organs RT is a software product by Siemens that uses deep learning to automatically contour organs at risk on CT imaging data. The output contours help radiation oncologists plan external beam radiation therapy by providing accurate anatomical structures for treatment planning. The software processes CT scans, generates contour data in DICOM RTSTRUCT format, and integrates with treatment planning systems to improve clinician workflow and efficiency in radiation therapy preparation.
AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT imaging data using deep-learning-based algorithms. The contours generated may be used as input for clinical workflows including external beam radiation therapy treatment planning. The output RTSTRUCT objects are intended to be used by trained medical professionals.
The device uses deep learning algorithms to automatically contour organs at risk on CT images. It processes CT input data in DICOM format and outputs RTSTRUCT objects compatible with treatment planning systems. A web-based interface provides visualization of contouring results for review and acceptance. The algorithm is locked and validated, designed to be vendor agnostic with configuration of organ templates via an interface. It supports automated workflows, organ template management and web preview.
Performance validation was conducted on 113 CT datasets from multiple clinical sites across multiple continents. The algorithm's Dice similarity coefficient, absolute symmetric surface distance, and fail rate were evaluated, showing comparable performance to the predicate device (AI-Rad Companion Organs RT VA20) and reference device (Contour ProtégéAI). Results were consistent across different vendors and genders. Validation confirmed the safety and effectiveness of the device with no raise in new safety issues.
No predicate devices specified
Submission
5/5/2022
FDA Approval
10/14/2022
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.