Intended Use

Change Healthcare Anatomical AI is intended to analyze pixel data from CT or MR images to create comprehensive anatomic descriptors for export to integrated healthcare systems. It supplements traditional methods for selection, presentation, or analysis of image-based medical data, enabling rapid identification of images, series, and/or studies of interest. Not indicated for patients under 18 years old.

Technology

The software is a standalone image processing application that uses API endpoints to receive DICOM images and return inference results in JSON format. It validates input images, processes CT and MR pixel data with a machine learning based non-adaptive AI algorithm to generate anatomical descriptors associated with image data. The results are stored persistently and returned for use by integrated healthcare systems. It operates alongside standard clinical workflows without altering original images.

Performance

Verification and validation testing included software verification of anatomical detection accuracy and overall functional performance. A retrospective multi-center study using diverse datasets (27 institutions, multiple demographics, scanners, and protocols) assessed accuracy on CT and MR images. Cybersecurity controls were implemented per FDA guidance. Test report evaluations confirm safety and effectiveness.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    3/10/2021

    4 months
  • 2

    FDA Approval

    7/20/2021

Other devices from Change Healthcare Canada Company

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.