Intended Use

Provide automatic 3D segmentation and labeling of anatomical landmarks of the aorta in CT Angiography scans of adult patients, except those with certain aortic and metallic device exclusions.

Technology

A software as a medical device (SaMD) deployed as a containerized application running on standard hardware or cloud platforms. It uses supervised deep learning-based algorithms to process CT Angiography DICOM images and outputs DICOM result files with segmentation and anatomical landmarks. The device does not alter input data or provide diagnoses.

Performance

A retrospective study was conducted with 170 adult patient CT Angiography scans, including those with aortic dilation or valve disease. Performance was measured by comparing the device's lumen and aortic wall segmentation (DICE scores) and anatomical landmark detection against ground truth established by radiologists. Acceptance criteria required average DICE >=80% and landmark detection passing rates of >=80% with confidence bounds. The device achieved a mean DICE of 88% for lumen and 90% for aorta segmentation and passed all landmark evaluation criteria, demonstrating safety and effectiveness equivalent to the predicate device.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    9/30/2024

    3 months
  • 2

    FDA Approval

    1/23/2025

Other devices from TeraRecon, Inc.

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.