K-numberK242600
Device nameSecond Opinion Periapical Radiolucency Contours
ApplicantPearl, Inc.
Product codeMYN
Device classClass II
Decision dateApr 11, 2025
DecisionSubstantially Equivalent
Regulation892.2070
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

Second Opinion PC is computer-aided detection (CADe) software that aids dentists in detecting periapical radiolucencies (bone loss around tooth roots) on periapical radiographs by displaying polygonal overlays highlighting suspected problem areas. It is designed for use by dental health professionals as a second reader to review radiographs of permanent teeth in patients 12 years or older, and is not intended to replace a dentist's clinical judgment.

Technological characteristics

Second Opinion PC uses neural network-based computer vision algorithms developed through supervised machine learning to detect periapical radiolucencies on digital intraoral radiographs processed on Windows operating systems. The key technological difference from the primary predicate device is that Second Opinion PC uses polygonal contours to mark detections, whereas the predicate Second Opinion uses bounding boxes, though both employ the same underlying machine learning approach and produce near-instantaneous results with graphical overlays.

Test standards cited

Not stated in this summary.

Substantial equivalence argument

Second Opinion PC is substantially equivalent because it maintains the same intended use (aiding dentists in detecting periapical radiolucencies as a second reader), employs the same core technology (neural network-based computer vision with machine learning), and demonstrated non-inferior clinical performance to the predicate device using a non-inferiority standalone study. The clinical study showed a wAFROC-FOM of 0.85 (95% CI 0.81-0.89) for the subject device versus 0.75-0.84 for the predicate, with the lower bound of the confidence interval exceeding the -0.05 non-inferiority margin, confirming equivalent or superior detection accuracy despite the change from bounding boxes to polygonal contours for visualization.

Extracted by AI from the official FDA summary PDF →
Source

View the full FDA submission: accessdata.fda.gov

Researching this as a predicate?
Want a transparent AI-ranking score, AI-discovered related predicates, ongoing safety and warning-letter monitoring, full predicate chain lineage, and a drafted SE rationale — all saved to your own project? That's what an account adds.
Start free trial →

Everything you need for a 510(k) submission. Nothing you don't.

14-day free trial. No setup. Cancel anytime.

Start free trial →
Building an AI or ML-enabled device? Predicate search, PCCP tracking, and AI-specific FDA intelligence — built exclusively for AI/ML devices. Try AIFDA Intel →