Intended Use

To aid in triage and prioritization of non-contrast brain CT studies with features suggestive of acute subdural/epidural hematoma, acute subarachnoid hemorrhage, intra-axial hemorrhage, and intraventricular hemorrhage in patients aged 22 and older, by providing study-level notifications for worklist prioritization to trained clinicians.

Technology

It is a software workflow tool that uses a convolutional neural network trained via deep learning on over 200,000 labeled brain CT studies from multiple CT manufacturers. The AI algorithm identifies specific intracranial hemorrhage types and outputs study-level findings to image and order management systems (PACS/RIS) for triage. It works in parallel to standard clinical workflow and does not downgrade study priority.

Performance

The AI algorithm was validated through retrospective studies on 1,485 to 1,878 de-identified non-contrast brain CT cases from multiple US hospital sites with a variety of scanners. Ground truth was established by consensus among board-certified neuroradiologists. The device demonstrated high sensitivity and specificity for the detection of the target hemorrhage types, with performance comparable to the predicate device. Additionally, performance testing demonstrated a triage turn-around time of approximately 81.6 seconds, similar to the predicate, supporting clinically effective triage and safety for intended use.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    10/20/2022

    5 months
  • 2

    FDA Approval

    4/3/2023

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.