Denti.AI Detect

K230144

Denti.AI Technology, Inc. · cleared 2023-10-06 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.3)

“Denti.AI Detect is a Computer-Assisted Detection (CADe) software device intended to be used by dental professionals, comprising dentists and dental specialists, while reading extraoral and intraoral 2D dental radiographs. The device is not intended to replace a complete clinician's review or clinical judgment that considers other relevant information from the image or patient history. Not applicable. The subject device is a software-only device. It contains no electric components, generates no electrical emissions, and uses no electrical energy of any type.”

AlgorithmFDA source did not state this

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (3)

Standalone

n=709 images · 6 site(s)

endpoints: show that the lower bound of the 95% CI of the across-category wAFROC AUC exceeds the predefined threshold of 0.6

Standalone

n=193 images · 9 site(s)

endpoints: Primary study endpoints and results are shown in Table 2.

Reader study (MRMC)

n=154 images · 5 site(s)

endpoints: evaluate the Denti.AI Detect device's effect on dental professionals' performance in detecting periapical radiolucencies and caries on a range of intraoral and extraoral radiographs

Reported performance (9 observations)

aurocas written: “auc”0.737CI (0.713, 0.761)

source quote (p.7)

“The study met its primary endpoint with an across-category wAFRPOC AUC of 0.737 and a 95% CI of (0.713, 0.761).”

sensitivityas written: “Bitewing: CEJ-Bone: Sensitivity”0.981CI 96%, 99.5%

source quote (p.8)

“98.1% (96%, 99.5%)”

specificityas written: “Bitewing: CEJ-Bone: Specificity”0.93CI 88.7%, 96.7%

source quote (p.8)

“93% (88.7%, 96.7%)”

sensitivityas written: “Periapical: CEJ-Bone: Sensitivity”0.982CI 96.2%, 99.7%

source quote (p.8)

“98.2% (96.2%, 99.7%)”

specificityas written: “Periapical: CEJ-Bone: Specificity”0.885CI 82.8%, 93.4%

source quote (p.8)

“88.5% (82.8%, 93.4%)”

sensitivityas written: “Periapical: CEJ-Root: Sensitivity”0.969CI 94.2%, 99%

source quote (p.8)

“96.9% (94.2%, 99%)”

specificityas written: “Periapical: CEJ-Root: Specificity”0.922CI 87.9%, 96%

source quote (p.8)

“92.2% (87.9%, 96%)”

sensitivityas written: “Extraoral: CEJ-Bone-Root: Sensitivity”0.916CI 89.6%, 93.6%

source quote (p.8)

“91.6% (89.6%, 93.6%)”

specificityas written: “Extraoral: CEJ-Bone-Root: Specificity”0.843CI 70.8%, 95.8%

source quote (p.8)

“84.3% (70.8%, 95.8%)”

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).