Intended Use

NeuroQuant is intended for automatic labeling, visualization, and volumetric quantification of segmentable brain structures and lesions from a set of MR images. Volumetric measurements may be compared to reference percentile data.

Technology

NeuroQuant is a fully automated MR imaging post-processing software that uses probabilistic methods and neural network models for anatomical labeling and volumetric quantification. It processes various MR sequences, corrects for scanner artifacts and intensity variability, supports DICOM input and outputs volumetric data and segmented images in standard formats. It includes deep-learning models for brain segmentation, FLAIR lesion segmentation, and microbleed detection.

Performance

Performance testing included verification and validation of three deep-learning models: brain segmentation, FLAIR lesion segmentation, and microbleed detection. Metrics such as Dice Similarity Coefficient and F1 Score demonstrated accuracy, robustness, and generalizability on diverse datasets. Testing confirmed substantial equivalence to predicate and compliance with FDA guidance and standards.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    4/22/2024

    4 months
  • 2

    FDA Approval

    8/22/2024

Other devices from CorTechs Labs, 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.