Intended Use

The software performs digital enhancement of a radiographic image generated by an x-ray device. The software can be used to process adult and pediatric x-ray images. This excludes mammography applications.

Technology

The software uses a Convolutional Neural Network (CNN) trained on clinical images with added simulated noise to reduce noise in digital radiography images prior to enhancement processing. It is integrated as an optional module within the Eclipse II software and supports both Computed Radiography (CR) and Digital Radiography (DR) detectors from Carestream. The noise suppression is implemented via a CNN based on a U-Net architecture generating a noise field map for noise reduction.

Performance

Clinical testing involved board-certified radiologists evaluating images processed with the software using visual difference preference scales and RadLex scales. Results demonstrated diagnostic quality images at 50% dose reduction for CsI panel images and 40% dose reduction for GOS panel images, with image quality equivalent to or better than nominal dose images over various exams, detector types, and exposures.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    10/4/2021

    3 months
  • 2

    FDA Approval

    1/14/2022

Other devices from Carestream Health, Inc.

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.