Segmentron Viewer

K251072

DGNCT, LLC · cleared 2025-09-09 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“Segmentron Viewer is a semi-automated software as a medical device (SaMD) for dental image processing and management.”
Algorithmsupervised machine learning algorithm utilizing artificial neural network models (AI)
source quote (p.6)
“Both devices are software-only, Al-based devices that utilize a supervised machine learning algorithm to provide comparable tools for processing and manipulation of maxillofacial radiographic images.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (4)

Retrospective clinical

n=126 scans

endpoints: Dice Coefficient (primary endpoint) exceeding the pre-defined performance goal (PG)

Retrospective clinical

n=43 scans

endpoints: Dice Coefficient (primary endpoint)

Retrospective clinical

n=56 scans

endpoints: Dice Coefficients for each anatomical region exceeded their respective pre-defined PGs.

Retrospective clinical

n=40 scans

endpoints: accuracy of labels automatically generated by the device

Reported performance (3 observations)

diceas written: “Dice Coefficient (Tooth Segmentation)”0.96CI 95% CI: 0.95, 0.96
source quote (p.7)
“Dice Coefficient (primary endpoint) exceeding the pre-defined performance goal (PG) with a result of 0.96 (95% CI: 0.95, 0.96; p < 0.0001)”
diceas written: “Dice Coefficient (Pulp Segmentation)”0.88CI 95% CI: 0.87, 0.89
source quote (p.7)
“Dice Coefficient (primary endpoint) = 0.88 (95% CI: 0.87, 0.89; p < 0.0001)”
accuracyas written: “labeling accuracy”100
source quote (p.7)
“Across all teeth, pulp, and anatomical structures in all CBCT scans, Segmentron Viewer achieved a labeling accuracy of 100%, demonstrating strong concordance between the labels automatically generated by the device and those determined by an expert radiologist.”

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/K251072