INT Contour
Carina Medical LLCINTContour is a software tool that uses machine learning to automatically identify and outline organs and treatment targets on medical images to aid radiation therapy planning. This helps clinicians by providing initial segmentations that can be reviewed and edited, saving time and improving efficiency in treatment preparation for cancer patients.
Intended Use
INTContour provides a machine learning-based approach for automatic segmentation of structures including treatment targets and organs at risk to support the radiation therapy treatment planning process.
Technology
INTContour uses machine learning algorithms, specifically convolutional neural networks (CNNs), trained on a library of expert contoured cases, to perform automatic segmentation of anatomical structures. It outputs results in DICOM RTSTRUCT format for integration into clinical workflow and uses a web-based interface deployed on a hospital network workstation with advanced GPU hardware.
Performance
Performance testing included non-clinical verification and validation with diverse patient data from multiple sources covering head and neck, thorax, abdomen, and male pelvis. Metrics such as Dice Similarity Coefficient and 95% Hausdorff Distance were used to compare INTContour against predicate devices, demonstrating non-inferiority and acceptable segmentation accuracy. Risk management activities and software usability testing were conducted to ensure safety and effectiveness.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
7/20/2021
8 months - 2
FDA Approval
4/8/2022
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.