Brain WMH

K251527

Quantib BV · cleared 2025-09-25 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.6)

“Brain WMH is a software as a medical device (SaMD) that provides automatic quantification of white matter hyperintensities (WMHs) based on magnetic resonance (MR) images to assist trained medical professionals.”

Algorithmartificial intelligence-based algorithm

source quote (p.6)

“Brain WMH employs an updated artificial intelligence-based algorithm for WMH segmentation, whereas the predicate device uses a different machine learning approach.”

Adaptive (vs locked)No

source quote (p.8)

“To ensure independence of the test data, the test sets were quarantined datasets not used to train or tune the model, only for software validation following internal processing aligned with good machine learning practices.”

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (1)

Retrospective clinical

n=90 patients

endpoints: WMH segmentation performance (Dice coefficient); anatomical location labeling performance; longitudinal WMH labeling accuracy; scan-rescan reproducibility of volumes

standards: ISO 14971:2019, IEC 62304:2015, NEMA PS3, Guidance for Industry and FDA Staff: Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (May, 2005), Guidance for Industry and FDA Staff: Software as a Medical Devices (SaMD): Clinical Evaluation (December 2017)

Reported performance (2 observations)

diceas written: “Dice coefficient for WMH segmentation”0.58CI ± 0.21

source quote (p.8)

“The standalone performance of Brain WMH segmentation, as measured by Dice coefficient (0.58 ± 0.21) was higher than the standalone performance of the predicate device and fell within the range of interobserver variability.”

accuracyas written: “Longitudinal WMH labeling accuracy”97.1

source quote (p.8)

“The longitudinal validation demonstrated high accuracy in WMH labeling across scans acquired from the same patient (97.1% correctly labelled).”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

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).