Second Opinion® CS

K243234

Pearl Inc. · cleared 2025-06-12 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“Second Opinion® CS is a computer aided detection ("CADe”) software to aid in the detection and segmentation of caries in periapical radiographs.”

Algorithmcomputer vision neural network algorithms, developed from open-source models using supervised machine learning techniques

source quote (p.8)

“Utilizes computer vision neural network algorithms, developed from open-source models using supervised machine learning techniques”

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)

Retrospective clinical

n=1,250 images

endpoints: sensitivity of caries detection

Reader study (MRMC)

n=330 images

endpoints: caries detection; anatomical segmentation (enamel, dentin) capabilities; wAFROC-FOM difference; lesion-level sensitivity; False positives per image (FPPI); Surface-level specificity; Localization and segmentation accuracy

Reported performance (6 observations)

sensitivity0.88

source quote (p.10)

“The z-score analysis of the lesion level sensitivity for overall caries detection by image type showed the estimated lesion level sensitivity (95% CI) was 0.88.”

aurocas written: “auc”0.05CI 0.01-0.09

source quote (p.11)

“Aided readers showed a significant improvement in caries detection for periapical images (wAFROC-FOM difference: 0.05, 95% CI: 0.01-0.09, adjusted p=0.0345).”

sensitivityas written: “caries subgroup sensitivity (enamel)”0.95CI 0.92, 0.97

source quote (p.10)

“The caries subgroup sensitivity (95% CI) was 0.95 (0.92, 0.97) enamel and 0.86 (0.81, 0.90) dentin.”

sensitivityas written: “caries subgroup sensitivity (dentin)”0.86CI 0.81, 0.90

source quote (p.10)

“The caries subgroup sensitivity (95% CI) was 0.95 (0.92, 0.97) enamel and 0.86 (0.81, 0.90) dentin.”

sensitivityas written: “Lesion level sensitivity increase (enamel)”0.2CI 0.16-0.25

source quote (p.11)

“Lesion level sensitivity increased significantly (0.20, 95% CI: 0.16-0.25) for enamel (0.19, 95% CI: 0.15-0.23) for dentin.”

sensitivityas written: “Lesion level sensitivity increase (dentin)”0.19CI 0.15-0.23

source quote (p.11)

“Lesion level sensitivity increased significantly (0.20, 95% CI: 0.16-0.25) for enamel (0.19, 95% CI: 0.15-0.23) for dentin.”

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) K250525 (decision 2025-11-14) from Pearl, Inc. for a matching device line ("Second Opinion® Panoramic") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K250525

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).