Intended Use

The qER-Quant device is intended for automatic labeling, visualization and quantification of segmentable brain structures from a set of Non-Contrast head CT (NCCT) images. It automates identifying, labeling and quantifying the volume of segmentable brain structures identified on NCCT images and provides a comparative analysis for images acquired at multiple time points. It is indicated for use in the analysis of Intracranial Hyperdensities, Lateral Ventricles and Midline Shift.

Technology

qER-Quant is a standalone software that processes non-contrast head CT scans using a set of pre-trained convolutional neural networks (CNNs) for segmentation. It includes pre-processing to prepare DICOM images and post-processing to generate visual and tabular output. The software interacts with PACS to receive images and return results, outputting both PDF reports and labeled DICOM overlays.

Performance

Performance testing involved evaluating volume and shift measurement accuracy of target structures against manually labeled expert ground truth on a set of head CT scans. Accuracy was quantified using absolute error and Dice scores for intracranial hyperdensities (mean Dice 0.75), midline shift, and lateral ventricles (Dice ~0.75-0.79). Reproducibility testing using 20% of scans showed performance exceeded preset acceptance criteria. The software also passed system verification and validation checks.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    4/23/2021

    3 months
  • 2

    FDA Approval

    7/30/2021

Other devices from Qure.ai Technologies

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.