MVision AI Segmentation is a software device designed to automatically create segmentation templates of anatomical regions on CT images to assist clinicians in radiation therapy treatment planning. It uses machine learning-based algorithms to generate initial contours for multiple anatomical sites, which clinicians can review and modify before use, helping to save time and improve efficiency in clinical workflows.
MVision AI Segmentation is a software system for image analysis algorithms to be used in radiation therapy treatment planning workflows. It includes processing tools for automatic contouring of CT images using machine learning algorithms, producing segmentation templates as initial contours for medical professional review and approval prior to clinical use.
The device uses pre-trained, locked deep artificial neural network models for automatic segmentation of predefined anatomical structures in CT images. It integrates with clinical IT systems via DICOM for data exchange and supports both on-premises and cloud deployment. The models were trained on hundreds of scans for robustness and produce contours as templates for manual review and edit by clinicians.
Software verification and validation were performed following FDA guidance, including performance evaluation of machine learning algorithms on diverse datasets representing US patient population. Results demonstrated that the device assists in reducing clinician effort and time for contouring, producing clinically usable segmentation templates that enable faster progression in radiation therapy planning stages, confirming safety and effectiveness comparable to predicate device.
No predicate devices specified
Submission
9/13/2021
FDA Approval
5/3/2022
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.