Contour+ (MVision AI Segmentation)
MVision AI OyContour+ (MVision AI Segmentation) is a software tool that uses machine learning algorithms to automatically create contour outlines of anatomical regions on CT and MRI scans. It assists clinicians in radiation therapy planning by providing initial segmentations of organs and tissues, which professionals can review and modify before treatment planning. This speeds up the workflow and improves efficiency in radiation treatment preparation.
Intended Use
Software system for image analysis algorithms to be used in radiation therapy treatment planning workflows. Includes automatic contouring tools for CT and MR images using machine learning algorithms, producing segmentation templates for regions of interest for medical professional review and approval prior to clinical use. Creates initial contours of predefined structures of common anatomical sites; not intended to detect lesions or tumors. Not intended for real-time adaptive planning workflows.
Technology
Software-only medical device that integrates with healthcare IT networks to receive DICOM CT and MR images. Uses pre-trained, locked, and static machine learning models based on deep artificial neural networks to perform automatic contouring of predefined regions of interest. Models were trained on hundreds of scans from diverse patient populations across multiple anatomical sites. The segmentation output is transferred as structure sets to image visualization systems for clinician review and modification.
Performance
Performance validation was conducted in accordance with FDA guidance and consensus standards (IEC 62304, IEC 62366-1, ISO 14971, DICOM). Evaluation datasets were sourced from multiple US and EU clinical sites, ensuring representativeness of the US patient population. Effectiveness was measured by similarity scores (Dice Score, Surface Dice Score) comparing auto-segmentations to ground truth segmentations. Results demonstrated robustness, generalizability, and reduction in clinician contouring effort and time. Additional interoperability and platform deployment changes did not affect safety or performance.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
5/24/2024
4 months - 2
FDA Approval
10/18/2024
Other devices from MVision AI Oy
- MVision AI Segmentation2022 • 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.