Intended Use

AIRAscore is intended for automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR images. This software is intended to automate the current manual process of identifying, labeling and quantifying the volume of segmentable brain structures identified on MR images.

Technology

AIRAscore is a software as a medical device (SaMD) running on internal servers as a Software as a Service (SaaS). It uses DICOM compliant input of T1-weighted and optionally FLAIR MR images. Segmentation is performed by a supervised voxel classification using Convolutional Neural Networks. Output includes volumetric reports and annotated DICOM images. The segmentation models remain static during the software version lifetime.

Performance

Performance testing involved software verification with unit, integration, and end-to-end testing per IEC 62304. Validation showed AIRAscore performs well across patient populations and scanner manufacturers. Results meet software requirements and comply with relevant standards including ISO 14971 and IEC 62304.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    10/11/2022

    10 months
  • 2

    FDA Approval

    8/25/2023

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.