Intended Use

Non-invasive labeling and calculation of quantitative measurements for anatomical regions from whole-body MRI images of healthy adult patients.

Technology

Automated image post-processing software that stitches together overlapping MR images from multiple stations, uses non-AI based algorithms and convolutional neural networks for segmentation of several anatomical structures, and outputs quantitative measurements with alpha-blended color label overlays in PDF format.

Performance

Performance evaluation included segmentation accuracy assessed by Dice Similarity Coefficient and mean percent absolute difference, majority voting by radiologists for liver VOI placement, repeatability testing, inter- and intra-rater variability studies, and software verification and usability testing. Results showed the device performs as intended without new safety or effectiveness concerns.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    5/7/2024

    4 months
  • 2

    FDA Approval

    9/12/2024

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.