Overjet Caries Assist

K212519

Overjet, Inc. · cleared 2022-05-10 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“Overjet Caries Assist (OCA) is a radiological automated concurrent read computer-assisted detection (CAD) software intended to aid in the detection and segmentation of caries on bitewing radiographs.”

AlgorithmThe Machine Learning System within the Decision Layer processes bitewing radiographs and annotates suspected carious lesions. It is comprised of four modules: Image Classifier, Tooth Number Assignment module, Caries module (using an ensemble of 3 U-Net based models), and Post Processing. The Caries module outputs a pixel wise segmentation mask of all carious lesions.

source quote (p.4)

“The Machine Learning System within the Decision Layer processes bitewing radiographs and annotates suspected carious lesions. It is comprised of four modules: Image Classifier - The model evaluates the incoming radiograph and predicts the image type between Bitewing and Periapical Radiograph. This classification is used to support the data flow of the incoming radiograph. As part of the classification of the image type any non-radiographs are classified as “junk” and not processed. These include patient charting information, or other non-bitewing or periapical radiographs. OCA shares classifier and Tooth Number modules with the Overjet Dental Assist product cleared under K210187. Tooth Number Assignment module – This module analyzes the processed image and determines what tooth numbers are present and provides a pixel wise segmentation mask for each tooth number. Caries module – This module outputs a pixel wise segmentation mask of all carious lesions using an ensemble of 3 U-Net based models. The shape and location of every carious lesion is contained in this mask as the carious lesions’ predictions. Post Processing - The overlap of tooth masks from the Tooth Number Assignment Module and carious lesions from the Caries Module is used to assign specific carious lesions to a specific tooth. The Image Post Processor module annotates the original radiograph with the carious lesions’ predictions.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedNo

Validation studies (3)

Standalone

n=7,129 cases

endpoints: Sensitivity; Specificity

Standalone

n=96 images

endpoints: Dice score

Reader study (MRMC)

n=352 images

endpoints: reader sensitivity; reader specificity; AFROC scores; Dice scores

standards: ISO 14971

Reported performance (21 observations)

sensitivity0.72CI 62.9%, 81.1%

source quote (p.9)

“Overall standalone sensitivity was 72.0% (62.9%, 81.1%).”

specificity0.981CI 97.7%, 98.5%

source quote (p.9)

“Overall standalone specificity was 98.1% (97.7%, 98.5%).”

aurocas written: “auc”0.649CI 0.744, 0.820

source quote (p.11)

“For the average of all readers, AUC increased from 0.593 (0.686, 0.743) to 0.649 (0.744, 0.820), for an increase in AUC of 0.057 (0.039, 0.098) unassisted to assisted.”

sensitivityas written: “Primary caries sensitivity (standalone)”0.744CI 64.4%, 84.4%

source quote (p.9)

“When broken down further, sensitivity was 74.4% (64.4%, 84.4%) for primary caries, and 62.5% (46.6%, 78.4%) for secondary caries.”

sensitivityas written: “Secondary caries sensitivity (standalone)”0.625CI 46.6%, 78.4%

source quote (p.9)

“When broken down further, sensitivity was 74.4% (64.4%, 84.4%) for primary caries, and 62.5% (46.6%, 78.4%) for secondary caries.”

diceas written: “Mean Dice score (primary caries)”0.69CI 0.66, 0.72

source quote (p.10)

“For 66 images containing primary caries, the mean Dice score was 0.69 (0.66, 0.72) with a standard deviation of 0.122)”

diceas written: “Mean Dice score (secondary caries)”0.75CI 0.71, 0.79

source quote (p.10)

“For 30 images containing secondary caries, the mean Dice score was 0.75 (0.71, 0.79) with a standard deviation of 0.112.”

sensitivityas written: “Overall reader sensitivity (unassisted)”0.579CI 48.9%, 66.0%

source quote (p.11)

“Overall reader sensitivity improved from 57.9% (48.9%, 66.0%) to 76.2% (68.4%, 82.6%) unassisted vs assisted.”

sensitivityas written: “Overall reader sensitivity (assisted)”0.762CI 68.4%, 82.6%

source quote (p.11)

“Overall reader sensitivity improved from 57.9% (48.9%, 66.0%) to 76.2% (68.4%, 82.6%) unassisted vs assisted.”

sensitivityas written: “Primary caries reader sensitivity (unassisted)”0.605CI 49.3%, 69.2%

source quote (p.11)

“For primary caries, reader sensitivity improved from 60.5% (49.3%, 69.2%) to 79.4% (71.0%, 85.9%).”

sensitivityas written: “Primary caries reader sensitivity (assisted)”0.794CI 71.0%, 85.9%

source quote (p.11)

“For primary caries, reader sensitivity improved from 60.5% (49.3%, 69.2%) to 79.4% (71.0%, 85.9%).”

sensitivityas written: “Secondary caries reader sensitivity (unassisted)”0.498CI 39.5%, 60.6%

source quote (p.11)

“For secondary caries, reader sensitivity improved from 49.8% (39.5%, 60.6%) to 63.0% (52.0%, 74.8%).”

sensitivityas written: “Secondary caries reader sensitivity (assisted)”0.63CI 52.0%, 74.8%

source quote (p.11)

“For secondary caries, reader sensitivity improved from 49.8% (39.5%, 60.6%) to 63.0% (52.0%, 74.8%).”

specificityas written: “Overall reader specificity (unassisted)”0.993CI 99.1%, 99.5%

source quote (p.11)

“Overall reader specificity decreased slightly from 99.3% (99.1%, 99.5%) to 98.4% (94.5%, 98.8%) unassisted vs assisted.”

specificityas written: “Overall reader specificity (assisted)”0.984CI 94.5%, 98.8%

source quote (p.11)

“Overall reader specificity decreased slightly from 99.3% (99.1%, 99.5%) to 98.4% (94.5%, 98.8%) unassisted vs assisted.”

diceas written: “Primary caries mean Dice scores (unassisted)”0.67

source quote (p.11)

“For primary caries, mean Dice scores improved from 0.67 unassisted (standard deviation 0.012) to 0.69 assisted (SD 0.011).”

diceas written: “Primary caries mean Dice scores (assisted)”0.69

source quote (p.11)

“For primary caries, mean Dice scores improved from 0.67 unassisted (standard deviation 0.012) to 0.69 assisted (SD 0.011).”

diceas written: “Secondary caries mean Dice scores (unassisted)”0.65

source quote (p.11)

“For secondary caries, mean Dice scores improved from 0.65 unassisted (SD 0.017) to 0.74 assisted (SD 0.017).”

diceas written: “Secondary caries mean Dice scores (assisted)”0.74

source quote (p.11)

“For secondary caries, mean Dice scores improved from 0.65 unassisted (SD 0.017) to 0.74 assisted (SD 0.017).”

aurocas written: “AUC (unassisted)”0.593CI 0.686, 0.743

source quote (p.11)

“For the average of all readers, AUC increased from 0.593 (0.686, 0.743) to 0.649 (0.744, 0.820), for an increase in AUC of 0.057 (0.039, 0.098) unassisted to assisted.”

aurocas written: “Increase in AUC (unassisted to assisted)”0.057CI 0.039, 0.098

source quote (p.11)

“For the average of all readers, AUC increased from 0.593 (0.686, 0.743) to 0.649 (0.744, 0.820), for an increase in AUC of 0.057 (0.039, 0.098) unassisted to assisted.”

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

re_clearance
The FDA AI/ML device list shows a newer 510(k) K233738 (decision 2024-03-04) from Overjet, Inc for a matching device line ("Overjet Caries Assist-Pediatric") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K233738
re_clearance
The FDA AI/ML device list shows a newer 510(k) K222746 (decision 2023-03-27) from Overjet, Inc. for a matching device line ("Overjet Caries Assist") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K222746

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).