Intended Use

Image processing software used for image enhancement of MR images to reduce image noise in non-contrast MRI exams from 1.5T and 3T Siemens and GE scanners for patients over 18 years old; applicable sequences include Sagittal T1, Axial T2 and Axial Flair for the head, Axial T2 and Coronal T2 for the abdomen, Sagittal T2, Axial T2, and Coronal T2 for the pelvis.

Technology

Software as a Medical Device (SaMD) that enhances image quality by receiving DICOM-compliant non-contrast MR images acquired on 1.5T and 3T scanners. It applies a convolutional neural network-based algorithm using a cascade of filter banks with thresholding and scaling operations to reduce noise, outputting enhanced DICOM-compliant images for radiologists.

Performance

Performance testing demonstrated that Ezra Flash improves signal-to-noise ratio (SNR) by at least 5%, improves contrast-to-noise ratio (CNR) by greater than 0%, and shows improved perceived image quality with average Likert scale improvements of at least 0.5 points compared to original MR images. Testing confirmed the device meets design specifications and is safe and effective for clinical use.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    8/7/2024

    4 months
  • 2

    FDA Approval

    1/2/2025

Other devices from Ezra AI, 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.