Videa Dental AI

K251002

VideaHealth Inc. · cleared 2025-09-19 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.13)

“Not applicable. The subject device is a software-only device.”

AlgorithmSupervised Deep Learning

source quote (p.12)

“Supervised Deep Learning”

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=1,445 images

standards: ISO 14971:2019 Application of Risk Management to Medical Devices., AAMI CR34971:2022 Guidance on the Application of ISO 14971 to Artificial Intelligence and Machine Learning, IEC 62304 Edition 1.1 2015-06 Consolidated Version: Medical Device Software - Software Life Cycle Processes, Good Machine Learning Practice for Medical Device Development: Guiding Principles October 2021., FDA Content of Premarket Submissions for Device Software Functions (June 14, 2023)

Retrospective clinical

n=378 images

endpoints: determine whether the diagnostic accuracy of readers aided by VDA is superior to reader accuracy when unaided by VDA, as determined by the AFROC Figure of Merit (AFROC FOM)

Reported performance (8 observations)

diceas written: “DICE for caries”0.72

source quote (p.14)

“VDA caries had a DICE of 0.720 and calculus had a DICE of 0.716 respectively.”

diceas written: “DICE for calculus”0.716

source quote (p.14)

“VDA caries had a DICE of 0.720 and calculus had a DICE of 0.716 respectively.”

diceas written: “DICE for Enamel segmentation”0.907

source quote (p.14)

“Enamel is 0.907”

diceas written: “DICE for Pulp segmentation”0.825

source quote (p.14)

“Pulp is 0.825”

diceas written: “DICE for Crown Dentin segmentation”0.878

source quote (p.14)

“Crown Dentin is 0.878”

diceas written: “DICE for Root Dentin segmentation”0.874

source quote (p.14)

“Root Dentin is 0.874”

specificityas written: “standalone specificity for caries (second operating point)”0.867

source quote (p.15)

“VDA caries had a standalone specificity of 0.867 for caries' and 0.989 for PRL' second operating points respectively.”

specificityas written: “standalone specificity for PRL (second operating point)”0.989

source quote (p.15)

“VDA caries had a standalone specificity of 0.867 for caries' and 0.989 for PRL' second operating points respectively.”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

-100%

vs code's own 3-yr baseline

drift signals on this device

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).