LumiNE US; Lumi

K240094

Augmedit B.V. · cleared 2024-09-10 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.3)
“The LumiNE US software is intended for the visualization of medical images to provide insights in anatomy and pathology in preparation of surgical treatment.”
Algorithmmachine learning (nnUnet)
source quote (p.12)
“The algorithms were originally trained using machine learning (nnUnet).”
Adaptive (vs locked)No
source quote (p.7)
“Substantially equivalent, the subject device has a more specific common name because of the presence of nonadaptive machine learning algorithms.”
PCCPNo
Cybersecurity addressedYes
source quote (p.13)
“Details and reports are included in Section Software/Firmware and Cybersecurity and Interoperability and Section Performance Testing. Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions, Guidance for Industry and Food and Drug Administration Staff; September 27, 2023”

Validation studies (10)

Retrospective clinical

sample size not stated

endpoints: Dice Similarity Coefficient (DSC); 95% Hausdorff Distance (95% HD)

Bench

sample size not stated

endpoints: similarity

Bench

sample size not stated

endpoints: contrast; optical distortion; luminance; spatial resolution; visual quality

standards: IEC63145-20-20, 63145-20-10

Bench

sample size not stated

endpoints: features related to the manipulation of scans

Bench

sample size not stated

endpoints: acceptable limits; reliable and timely updates

Bench

sample size not stated

endpoints: supported DICOM variations

Bench

sample size not stated

endpoints: correspond with their real-world counterparts

Bench

sample size not stated

endpoints: render colors accurately

Bench

sample size not stated

endpoints: usability

Bench

sample size not stated

endpoints: safely upload and associate 3D models .in STL format to the exact same scan from which they were created

Reported performance (4 observations)

diceas written: “Dice (Brain)”0.96CI 0.95-0.97
source quote (p.12)
“For brain, the 95% CI of the median Dice (0.96, 95% CI 0.95-0.97) was totally above the established criterium (Dice 0.9).”
diceas written: “Dice (Skin)”0.99CI 0.99-0.1
source quote (p.12)
“For skin, the 95% CI of the median Dice (0.99, 95% CI 0.99-0.1) was totally above the established criterium (Dice 0.9).”
diceas written: “Dice (Tumor)”0.93CI 0.92-0.94
source quote (p.12)
“For tumor, the 95% CI of the median Dice (0.93, 95% CI 0.92-0.94) was totally above the established criterium (Dice 0.8).”
diceas written: “Dice (Ventricles)”0.89CI 0.85-0.91
source quote (p.12)
“For ventricles, the 95% CI of the median Dice (0.89, 95% CI 0.85-0.91) was totally above the established criterium (Dice 0.85).”

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); 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/K240094