Intended Use

MRCAT imaging is intended to provide the operator with information of tissue properties for radiation attenuation estimation purposes in photon external beam radiotherapy treatment planning for primary and metastatic brain tumor patients.

Technology

MRCAT brain uses a machine learning-based post-processing algorithm embedded in the MR console to generate CT-like images (MRCAT images) from MR mDixon in-phase and water images. Bones and body outline are segmented, and tissue HU values assigned based on fat and water intensities. Uses a convolutional neural network trained with paired CT and MR images. The software runs automatically after the mDixon scan within the MR workflow and exports DICOM images for treatment planning.

Performance

Non-clinical verification and validation tests demonstrate compliance with multiple FDA-recognized international standards (including IEC 62304, IEC 62366-1, ISO 14971) and meet acceptance criteria for safety and effectiveness. Clinical robustness shown by gamma analysis for dose plan equivalency between MRCAT and CT-based plans with high accuracy (gamma criteria 1%/1mm).

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    11/8/2019

    2 months
  • 2

    FDA Approval

    1/24/2020

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.