Neurophet AQUA AD Plus
K252496Neurophet., Inc. · cleared 2026-01-29 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.7)
“Neurophet AQUA AD Plus is a software device intended for the automatic labeling of brain structures, visualization, and volumetric quantification of segmented brain regions and lesions, as well as standardized uptake value ratio (SUVR) quantification using MR and PET images.”
source quote (p.9)
“Automatic segmentation and quantification of brain structures and lesions based on MR and PET image intensities using static deep learning technologies.”
source quote (p.9)
“using static deep learning technologies.”
source quote (p.17)
“• “Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions”, on September 27, 2023”
Validation studies (5)
Standalone
n=60 cases
endpoints: segmentation performance assessed by comparison against expert manual segmentations using the Dice Similarity Coefficient (DSC); Reproducibility: In 60 subjects with paired T1‑weighted scans (120 scans total), the mean Average Volume Difference Percentage (AVDP) was 2.50 ± 0.93% (95% CI: 2.26–2.74) for subcortical regions and 1.79 ± 0.74% (95% CI: 1.60–1.98) for cortical regions
Standalone
n=136 cases
endpoints: Accuracy: In 136 independent T2‑FLAIR cases, the overall mean DSC for lesion segmentation was 0.90 ± 0.04 (95% CI: 0.89–0.91); Reproducibility: Paired T2‑FLAIR scans showed a mean AVDP of 0.99 ± 0.66% and a mean absolute lesion volume difference of 0.08 ± 0.06 cc
Standalone
n=30 cases
endpoints: SUVR accuracy: In 30 paired MRI–PET datasets including multiple tracers and sites, SUVR values showed excellent agreement with an FDA‑cleared reference product (K221405), with intraclass correlation coefficients (ICC) ≥ 0.993 across seven Alzheimer’s‑relevant regions; Centiloid classification: In 176 paired T1‑weighted MRI and amyloid PET scans from ADNI and AIBL, Centiloid‑based amyloid positivity classifications (cutoff: 30) achieved kappa values that met or exceeded the acceptance criterion of κ ≥ 0.70
Standalone
n=100 scans
endpoints: Accuracy: In 100 T2‑FLAIR scans collected from U.S. and U.K. clinical sites, the mean DSC versus expert manual segmentations was 0.91 ± 0.09 (95% CI: 0.89–0.93)
Standalone
n=106 scans
endpoints: Accuracy: In 106 GRE/SWI scans from U.S. clinical sites, the HEM‑SegEngine achieved a median F1‑score (DSC) of 0.860 (95% CI: 0.824–0.902)
Reported performance (5 observations)
source quote (p.14)
“The evaluation results demonstrated a mean DSC of 0.83 ± 0.04 for cortical regions, corresponding to a 95% confidence interval of 0.82–0.84”
source quote (p.14)
“and a mean DSC of 0.87 ± 0.03 for subcortical regions, corresponding to a 95% confidence interval of 0.86–0.88.”
source quote (p.14)
“In 136 independent T2‑FLAIR cases, the overall mean DSC for lesion segmentation was 0.90 ± 0.04 (95% CI: 0.89–0.91)”
source quote (p.14)
“the mean DSC versus expert manual segmentations was 0.91 ± 0.09 (95% CI: 0.89–0.93)”
source quote (p.14)
“the HEM‑SegEngine achieved a median F1‑score (DSC) of 0.860 (95% CI: 0.824–0.902)”
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
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).