Intended Use

Radiological computer aided triage and notification software for use in the analysis of Non-Enhanced Head CT images. Intended to assist hospital networks and trained radiologists in workflow triage by flagging suspected positive findings of intracranial hemorrhage (ICH).

Technology

The software runs a deep learning artificial intelligence algorithm on non-enhanced head CT DICOM image series. It operates on an onsite hospital server with client workstations. It detects suspected intracranial hemorrhage cases, marking them in a worklist for prioritization; the system processes series in order and provides a preview (not for diagnosis). The device does not alter original images or remove cases from the reading queue.

Performance

Clinical testing on 369 non-contrast brain CT scans from US hospitals showed sensitivity of 91.6% and specificity of 92.2% for intracranial hemorrhage detection, exceeding preset performance goals. The area under the ROC curve was 0.962. Average time to notification was 1.07 minutes, significantly faster than the standard of care time-to-opening exam of over 75 minutes. The study demonstrated the device is safe and effective for triage support.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    4/20/2021

    3 months
  • 2

    FDA Approval

    8/12/2021

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.