Second Opinion® 3D

K243989

Pearl, Inc. · cleared 2025-05-23 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
Second Opinion® 3D is a radiological automated image processing software device intended to identify and mark clinically relevant anatomy in dental CBCT radiographs; specifically Dentition, Maxilla, Mandible, Inferior Alveolar Canal and Mental Foramen (IAN), Maxillary Sinus, Nasal space, and airway. It should not be used in lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis.
AlgorithmThe device utilizes computer vision technology, developed using machine learning techniques, to identify clinically relevant anatomy on CBCT radiographs. Second Opinion® 3D consists of three parts: Application Programing Interface (“API”), Machine Learning Modules (“ML Modules”), Client User Interface (UI) (“Client”). The API sends imagery to the machine learning modules for processing and subsequently receives metadata generated by the machine learning modules which is passed to the interface for rendering. Second Opinion® 3D uses machine learning to identify areas of interest such as Individual teeth, including implants and bridge pontics; Maxillary Complex; Mandible; Inferior Alveolar Canal and Mental Foramen (defined as IAN); Maxillary Sinus; Nasal Space; Airway. Images received by the ML modules are processed yielding detections which are represented as metadata. Both devices use neural network-based computer vision algorithms for 3D modelling of patient anatomy.
source quote (p.6)
The cleared device is a software device, indicated for use by dental health professionals as an aid in reviewing CBCT radiographs. The device utilizes computer vision technology, developed using machine learning techniques, to identify clinically relevant anatomy on CBCT radiographs. Second Opinion® 3D consists of three parts: Application Programing Interface (“API”) Machine Learning Modules (“ML Modules”) Client User Interface (UI) (“Client”) The API sends imagery to the machine learning modules for processing and subsequently receives metadata generated by the machine learning modules which is passed to the interface for rendering. Second Opinion® 3D uses machine learning to identify areas of interest such as Individual teeth, including implants and bridge pontics; Maxillary Complex; Mandible; Inferior Alveolar Canal and Mental Foramen (defined as IAN); Maxillary Sinus; Nasal Space; Airway. Images received by the ML modules are processed yielding detections which are represented as metadata. Both devices use neural network-based computer vision algorithms for 3D modelling of patient anatomy.
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.9)
Pearl developed Security controls and processes in accordance with FDA Guidance - Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions dated September 2023. These processes are used in both the development of Second Opinion® 3D and in post-market surveillance to ensure the product upholds the highest standards of privacy and security.

Validation studies (1)

Bench

n=100 images

endpoints: segmentation accuracy; p-values below 0.05; statistically significant accuracy at a 95% confidence interval

Reported performance (8 observations)

accuracyas written: “Dentition Mean Accuracy0.86CI 0.83, 0.89
source quote (p.10)
Dentition 0.86 (0.83, 0.89)
accuracyas written: “Maxillary Complex Mean Accuracy0.91CI 0.91, 0.92
source quote (p.10)
Maxillary Complex 0.91 (0.91, 0.92)
accuracyas written: “Mandible Mean Accuracy0.97CI 0.97, 0.97
source quote (p.10)
Mandible 0.97 (0.97, 0.97)
accuracyas written: “IAN Canal Mean Accuracy0.76CI 0.74, 0.78
source quote (p.10)
IAN Canal 0.76 (0.74, 0.78)
accuracyas written: “Maxillary Sinus Mean Accuracy0.97CI 0.97, 0.98
source quote (p.10)
Maxillary Sinus 0.97 (0.97, 0.98)
accuracyas written: “Nasal Space Mean Accuracy0.9CI 0.89, 0.91
source quote (p.10)
Nasal Space 0.9 (0.89, 0.91)
accuracyas written: “Airway Mean Accuracy0.95CI 0.94, 0.96
source quote (p.10)
Airway 0.95 (0.94, 0.96)
diceas written: “Dice Similarity Coefficient (Predicate)0.92CI ±0.02
source quote (p.10)
The Relu Creator software demonstrated in a study on the segmentation of dental implants in CBCT images reported a Dice Similarity Coefficient score of 0.92±0.02, demonstrating the effectiveness of their model in accurately segmenting dental implants.

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

0
recalls in product code, 24mo
3
MAUDE reports in code, 12mo
vs code's own 3-yr baseline
2
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

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K243234 (decision 2025-06-12) from Pearl Inc. for a matching device line ("Second Opinion® CS") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K243234

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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K243989