PhenoMATRIX

K251511

Copan Wasp Srl · cleared 2026-01-22 · product code PPU · Microbiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
“The PhenoMATRIX is an in vitro diagnostic software for automated classification of images of solid culture media plates streaked with microbiological samples derived from the human body.”
AlgorithmImage analysis software modules for semi-quantitative and qualitative assessment of microbial growth, colony counts estimations, and isolates differentiation based on phenotypic colony characteristics, combined with LIS data and customizable logic rules for image classification.
source quote (p.6)
“The PhenoMATRIX comprises software modules intended for image analysis and automatic classification of high-resolution digital images captured by WASPLab device for semi-quantitative and qualitative assessment of microbial growth. WLPostProcessing, its plugin and the Imaging Product SET perform microbial growth detection, colony counts estimations and isolates differentiation basing on phenotypic colony characteristics. The image analysis result is combined with LIS data (such as demographic data, clinical data and / or sample data) according to customizable logic rules defined by the laboratory, for image classification.”
Adaptive (vs locked)No
PCCPNo
Cybersecurity addressedNo

Validation studies (8)

Bench

sample size not stated

endpoints: Overall percent agreement between image interpretation and physical plate inspection; Correct identification of phenotypical characteristics of colonies

Bench

sample size not stated

endpoints: Reproducibility of digital image interpretation for microbial growth detection, quantification, colony morphology/color, and growth purity

Bench

sample size not stated

endpoints: Growth detection accuracy (agreement between software output and human interpretation)

Bench

sample size not stated

endpoints: Agreement on the logarithmic classes of microbial load

Bench

sample size not stated

endpoints: Positive percent agreement of detecting the colony morphology for the species

Bench

sample size not stated

endpoints: Positive percent agreement of detecting the colony morphology for the species; Agreement between software's and operator's morphology semi-quantification

Bench

sample size not stated

endpoints: β-hemolysis detection accuracy (agreement between software output and human interpretation)

Retrospective clinical

n=5,845 images · 3 site(s)

endpoints: Classification agreement with laboratory microbiologist's digital review of plate images

Reported performance (6 observations)

agreement_kappaas written: “Overall percent agreement between image interpretation and physical plates”95CI >95%
source quote (p.13)
“The overall percent agreement between the image interpretation and the inspection of physical plates was always >95%.”
agreement_kappaas written: “Positive percent agreement for growth detection”99CI >99%
source quote (p.13)
“All the image analysis modules achieved >99% positive percent agreement for growth detection.”
agreement_kappaas written: “Positive percent agreement of detecting the colony morphology for most species”80CI >80%
source quote (p.14)
“For most species (and groups of species), the positive percent agreement of detecting the colony morphology for the species is >80%.”
agreement_kappaas written: “Positive percent agreement of detecting the colony morphology for most species”80CI >80%
source quote (p.15)
“For most species (and groups of species), the positive percent agreement of detecting the colony morphology for the species is >80%.”
agreement_kappaas written: “Agreement between software's and operator's morphology semi-quantification”80CI >80%
source quote (p.15)
“The agreement between the software's and the operator's morphology semi-quantification was generally >80%, except when colonies exhibited gradient-like features in both color intensity and morphology.”
accuracyas written: “Accuracy of ẞ-hemolysis detection”95CI >95%
source quote (p.16)
“>95% plates showing ẞ-hemolysis were correctly detected.”

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 Microbiology 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/K251511