Intended Use

DeepTek CXR Analyzer v1.0 is a computer-assisted detection (CADe) software device that analyzes chest radiograph studies using machine learning techniques to identify, categorize, and highlight suspicious ROIs in lungs, pleura, cardiac, and hardware. It is intended for use as a concurrent reading aid for radiologists in adults and transitional adolescents (18 to <22 years old).

Technology

DeepTek CXR Analyzer uses deep learning AI algorithms to analyze adult frontal chest X-ray images received from PACS in DICOM format. It detects suspicious regions of interest and annotates these on secondary capture DICOM images which are sent back to PACS. The software includes an authentication GUI and configurable PACS integration parameters. It is intended as an adjunct tool and outputs bounding boxes with suspicious findings but does not provide a diagnosis or treatment recommendation.

Performance

Performance testing included standalone evaluation using 3,000 chest X-ray scans from diverse datasets not used in training and clinical performance with 24 board-certified radiologists reading 300 scans in aided and unaided modes. Standalone results showed high sensitivity, specificity, and AUROC (around 0.9+ for four ROI categories). Clinical testing showed statistically significant improvement in localization performance (wAFROC-FOM) when aided by the software across all ROI categories. User sensitivity and specificity also improved with use of the software.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    4/7/2023

    6 months
  • 2

    FDA Approval

    10/5/2023

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.