GBrain MRI
K252362Galileo CDS, Inc · cleared 2025-08-22 · product code QIH · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.12)
“Both devices are software only medical devices.”
AlgorithmBoth the devices use deep learning to segment hyperintensities in FLAIR MR images, and subsequently calculate the volumes of these regions.
source quote (p.12)
“Both the devices use deep learning to segment hyperintensities in FLAIR MR images, and subsequently calculate the volumes of these regions.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (1)
Retrospective clinical
n=131 patients · 4 site(s)
endpoints: volume measurement accuracy; segmentation overlap agreement
Reported performance (7 observations)
diceas written: “DICE (Contrast Enhancement)”0.81CI 95% CI
source quote (p.14)
“while the lower bound of the 95% CI for DICE was 0.81.”
diceas written: “Median DICE (Contrast Enhancement Measurement performance related to Hyperintensity Size - Small less than 4.2 cm3)”0.73
source quote (p.14)
“0.73”
diceas written: “Median DICE (Contrast Enhancement Measurement performance related to Hyperintensity Size - Between 4.2-64.9 cm3)”0.85
source quote (p.14)
“0.85”
diceas written: “Median DICE (Contrast Enhancement Measurement performance related to Hyperintensity Brightness - Z-score 0-1.49)”0.69
source quote (p.14)
“0.69”
diceas written: “Median DICE (Contrast Enhancement Measurement performance related to Hyperintensity Brightness - Z-score 1.5-1.99)”0.79
source quote (p.14)
“0.79”
diceas written: “Median DICE (Contrast Enhancement Measurement performance related to Hyperintensity Brightness - Z-score 2.0-2.99)”0.81
source quote (p.14)
“0.81”
diceas written: “Median DICE (Contrast Enhancement Measurement performance related to Hyperintensity Brightness - Z-score 3.0+)”0.87
source quote (p.14)
“0.87”
Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.
Predicate network
Postmarket — what happened after clearance
0
recalls in product code, 24mo
3
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
0
drift signals on this device
Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.
Reimbursement — how devices like this got paid
Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).