Intended Use

DeepContour is a deep learning based medical imaging software that allows trained healthcare professionals to use DeepContour as a tool to automatically process CT images, create contours using deep-learning algorithms, support quantitative analysis, organ HU distribution statistics, transfer contour files to TPS, and create management archives for patients; analyze anatomical structures at different positions; perform rigid and elastic registration based on CT; and provide 3D reconstruction and editing tools based on organ contours.

Technology

DeepContour uses deep learning algorithms for automated segmentation of organs at risk on CT images, supports creation, editing, and deletion of organ template databases, produces RTSTRUCT outputs compatible with treatment planning systems, and provides an interactive contouring application for editing and review. It supports rigid and elastic registration and 3D reconstruction based on CT data.

Performance

Performance was validated with 203 CT images including both clinical and public datasets. Segmentation performance was assessed via Dice coefficients, ASSD, and other metrics showing the subject device's equivalence or superiority compared to predicate devices. Rigid and deformable registration quality was also validated. No clinical or animal studies were required; software verification and validation followed FDA guidance.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    9/20/2023

    7 months
  • 2

    FDA Approval

    5/7/2024

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.