Intended Use

DeepCT is a notification-only, parallel workflow tool for use by hospital networks and trained clinicians to identify and communicate images of specific patients to a specialist, independent of standard of care workflow. It analyzes non-contrast CT brain images acquired in the acute setting to identify suspected intracranial hemorrhage and notifies specialists.

Technology

DeepCT is software-only consisting of Image Forwarding Software and Image Processing and Analysis Server. It uses a deep residual convolutional neural network (ResNet-34) trained with CT brain images to identify and quantify image features suggestive of intracranial hemorrhage. The software transmits DICOM images securely, analyzes them, and sends notification messages if ICH is detected.

Performance

Retrospective multicenter study with 260 head CT cases showed DeepCT achieved 93.8% sensitivity and 92.3% specificity in detecting intracranial hemorrhage. The average processing time per case was 30.6 seconds. Software verification and validation testing were performed per FDA guidance.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    10/12/2018

    9 months
  • 2

    FDA Approval

    7/10/2019

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.