GBrain MRI

GBrain MRI is post-processing software that automatically analyzes and quantifies signal hyperintensities (bright areas) in the brain on FLAIR MRI images. It provides automated segmentation, volume measurements, and reporting of these hyperintensities as a support tool for radiologists in diagnostic radiology, but is not intended to detect disease or replace full clinical evaluation.

GBrain MRI is a software-only device that accepts brain MRI images in DICOM format as input and outputs volumetric measurements using deep learning-based automated segmentation. The output includes segmented color overlays on DICOM images and volumetric reports in DICOM-encapsulated PDF and Structured Report formats, displayed on standard PACS workstations. It performs skull stripping, signal normalization, segmentation, and volume calculation without requiring a user interface after installation.

Not stated in this summary. The document references a Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm and Dice similarity coefficient for performance evaluation, but does not cite formal consensus standards (ISO, IEC, ASTM, etc.).

GBrain MRI is substantially equivalent to OnQ Neuro and QP-Brain because all three devices share the same fundamental intended use of automated segmentation and volumetric quantification of hyperintensities on T2w FLAIR MRI images using deep learning. They have identical technological characteristics (software-only, DICOM input/output, deep learning segmentation followed by volume calculation with color overlay visualization), the same regulatory classification (Class II, 21 CFR 892.2050), and similar intended users (trained clinicians using results as supportive information). While the predicate devices have additional features outside GBrain MRI's scope, the core technical tasks for FLAIR hyperintensity measurement are exactly the same, and GBrain MRI's performance testing demonstrated segmentation accuracy meeting clinically acceptable levels across multiple scanner manufacturers and field strengths.