icobrain aria

K240712

icometrix NV · cleared 2024-11-07 · product code QBS · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“icobrain aria is a software-only device for assisting radiologists with the detection and quantification of amyloid-related imaging abnormalities (ARIA) on brain MRI scans of Alzheimer's disease patients under an amyloid beta-directed antibody therapy.”
Algorithmdeep learning technology
source quote (p.6)
“The image processing implemented in icobrain aria for ARIA-E and ARIA-H detection and segmentation is based on deep learning technology.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (2)

Bench

n=199 patients · 100 site(s)

endpoints: Diagnostic performance testing for distinguishing (on the case-level) between no ARIA-E and (mild, moderate or severe) ARIA-E; Diagnostic performance testing for distinguishing between no ARIA-H and (mild, moderate or severe) ARIA-H; Diagnostic performance testing for distinguishing between severity levels for ARIA-E; Diagnostic performance testing for distinguishing between severity levels for ARIA-H; Detection performance, measured as (finding-level) detection rate, false positive rate and misclassification rate for individual findings (ARIA-E sites of involvement, ARIA-H new microhemorrhages, ARIA-H new areas of superficial siderosis)

standards: IEC 62304:2006/Amd1:2015, ISO 14971:2019, IEC 62366-1:2015/Amd1:2020

Reader study (MRMC)

n=199 cases · 100 site(s)

endpoints: Difference between assisted and unassisted detection of ARIA-E (AUC); Difference between assisted and unassisted detection of ARIA-H (AUC); Difference in diagnostic performance of detecting mild ARIA in the subgroup of cases with no and mild ARIA; Difference in discriminating moderate-or-severe ARIA versus no-or-mild ARIA, for ARIA-E and ARIA-H; Accuracy in ARIA localization performance; Sensitivity; Specificity; Inter-reader variability; Reading time

standards: 21 CFR 892.2090, FDA guidance document Clinical Performance Assessment: Considerations for Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data (issued Sept 2022)

Reported performance (12 observations)

sensitivity0.865
source quote (p.13)
“0.865”
specificity0.83
source quote (p.13)
“0.830”
aurocas written: “auc”0.873
source quote (p.13)
“0.873”
aurocas written: “AUC for ARIA-E detection (standalone software)”0.838
source quote (p.13)
“0.838”
sensitivityas written: “Sensitivity for ARIA-E detection (standalone software)”0.943
source quote (p.13)
“0.943”
specificityas written: “Specificity for ARIA-E detection (standalone software)”0.671
source quote (p.13)
“0.671”
aurocas written: “AUC for ARIA-H detection (assisted)”0.825
source quote (p.13)
“0.825”
aurocas written: “AUC for ARIA-H detection (standalone software)”0.811
source quote (p.13)
“0.811”
sensitivityas written: “Sensitivity for ARIA-H detection (assisted)”0.79
source quote (p.13)
“0.790”
specificityas written: “Specificity for ARIA-H detection (assisted)”0.803
source quote (p.13)
“0.803”
aurocas written: “AUC for ARIA-H microhemorrhages (assisted)”0.808
source quote (p.13)
“0.808”
aurocas written: “AUC for ARIA-H superficial siderosis (assisted)”0.784
source quote (p.13)
“0.784”

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
0
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); a recall is shown as device-attributed only when the recall record itself lists this clearance number. 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).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K240712