Intended Use

Software device intended to assist trained radiation oncology professionals during radiation therapy treatment planning by providing initial contours of organs at risk on non-contrast CT images for adult patients.

Technology

Standalone software using deep learning algorithms to automatically contour organs at risk on CT images. Processes DICOM input, generates RTSTRUCT output, and integrates with DICOM-compliant radiation therapy treatment planning systems. Installed on specialized local servers, no user interface provided within the device itself.

Performance

Performance validated on 1,846 adult cases from radiation oncology, covering multiple body regions, via deep learning model development and testing. Clinical validation on 157 independent CT cases demonstrated high accuracy with mean Dice Similarity Coefficient of 0.83 overall, exceeding non-inferiority margins versus comparison device. Detailed organ-wise metrics and subgroup analyses show consistent and reliable performance.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    6/30/2023

    2 months
  • 2

    FDA Approval

    9/25/2023

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.