Intended Use

A software workflow tool designed to aid in prioritizing the clinical assessment of adult non-contrast head CT cases with features suggestive of acute intracranial hemorrhage.

Technology

The core technology is a deep learning algorithm trained on non-contrast head CT scans with expert-labeled ICH ground truth. It uses an end-to-end trainable 3D classification framework for automatic ICH detection and integrates with PACS/worklist systems to triage cases.

Performance

Clinical validation with 388 CT studies showed 90.6% sensitivity and 93.1% specificity in detecting ICH. Performance was consistent across slice thickness, detector rows, and scanner manufacturers. Average processing time per study was 43 seconds.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    8/9/2019

    8 months
  • 2

    FDA Approval

    4/13/2020

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.