Overjet CBCT Assist

K251514

Overjet, Inc. · cleared 2025-12-05 · product code QIH · Radiology

FDA 510(k) summary for Overjet CBCT Assist (K251514)

Constat organizes this clearance into predicate context, validation evidence, reported performance, postmarket signals, and reimbursement links. Each extracted claim stays tied to the public FDA source; missing fields remain explicitly unstated.

Validation studies
2
Cited predicates
3
Performance observations
3
Product code
QIH
Official FDA 510(k) database record ↗FDA 510(k) source PDF ↗

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
“Overjet CBCT Assist is a software for the analysis of dental and craniomaxillofacial Cone Beam Computed Tomography (CBCT) images. The software utilizes artificial intelligence/machine learning algorithms to provide automated segmentations, user-delineated or automated measurements, and 2D/3D visualizations.”
Algorithmartificial intelligence/machine learning algorithms
source quote (p.4)
“The software utilizes artificial intelligence/machine learning algorithms to provide automated segmentations, user-delineated or automated measurements, and 2D/3D visualizations.”
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

sample size not stated

standards: FDA guidance “General Principles of Software Validation" (FDA, January 2002), IEC 62304:2006+A1:2015

Retrospective clinical

n=100 scans

endpoints: Instance-level sensitivity for dental anatomy, restorative structures, and maxillofacial anatomy; Instance-level specificity for restorative structures; Dice similarity coefficient for all segmented structures; Measurement accuracy (Mean Absolute Error (MAE) and Root Mean Square Error (RMSE)) for automated linear measurements displayed in MPR views; Tooth-level sensitivity and accuracy for tooth numbering

Reported performance (3 observations)

sensitivity87CI 95% CI (82.3%, 91.2%)
source quote (p.11)
“the observed instance-level sensitivity for restorative structures was 87.0% with 95% CI (82.3%, 91.2%)”
diceas written: “Dice similarity coefficient”stated without value
source quote (p.11)
“Dice scores for segmented structures passed their individually associated thresholds across all evaluated classes.”
accuracyas written: “Measurement accuracy (MAE and RMSE)”stated without value
source quote (p.11)
“Measurement accuracy for linear distances also met the target thresholds for MAE and RMSE.”

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

1
recalls in product code, 24mo
4
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
1
drift signals on this device
  • recall_reason_pattern

    Software/algorithm-related recall in product code QIH (PIE Medical Imaging B.V., initiated 2026-05-07): "User measurement value reported by diagnostic bioimaging software intended to measure/visualize cardiovascular structures may be larger (0.8% to 34.4%) than the actual anatomical d" Recalling firm is another firm in the same product code.

    first seen 2026-08-26 · recall res_event_number:98930

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 2026-08-26.

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.

Related FDA clearances

More AI/ML devices under product code QIH

These are recent clearances in the same FDA product-code category. Shared classification does not by itself make a device an appropriate predicate.

ADAS 3D

K253969

Adas3D Medical S.L.

cleared 2026-06-29

Auto-Seg (SO-0012), Spine Auto-Seg (SO-0012)

K253628

Agada Medical, Ltd.

cleared 2026-06-29

syngo.CT Coronary Cockpit

K253786

Siemens Medical Solutions USA, Inc.

cleared 2026-06-25

CMN Capillary Function with Oncology Virtual Expert

K260316

Cercare Medical A/S

cleared 2026-06-22

Synapse PACS (7.6.0)

K261713

FUJIFILM Healthcare Americas Corporation

cleared 2026-06-18

MediAI-OA

K253172

Crescom Co., Ltd.

cleared 2026-06-15

AiORTA - Plan v2.0

K254207

ViTAA Medical Solutions, Inc.

cleared 2026-03-30

SwiftMR

K253775

Airs Medical, Inc.

cleared 2026-03-26

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K251514