K-numberK251837
Device nameSalix Coronary Plaque (V1.0.0)
ApplicantArtrya Limited
Product codeQIH
Device classClass II
Decision dateAug 20, 2025
DecisionSubstantially Equivalent
Regulation892.2050
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

Salix Coronary Plaque is a web-based software application for viewing, post-processing, and analyzing cardiac CT images. It provides cardiologists and radiologists with interactive tools to quantify and characterize coronary plaques, assess stenosis, and perform calcium scoring on non-contrast cardiac CT scans. The software is intended as an adjunctive diagnostic tool to complement—not replace—physician decision-making.

Technological characteristics

Salix Coronary Plaque operates as a client-server Google Chrome application hosted on Amazon Web Services, DICOM 3.0 or higher compliant. It includes semi-automated vessel and plaque segmentation (manual and user-editable), multiple measurement capabilities (distance, area, vessel/lumen profiles), 2D/3D imaging with MPR and MIP, and calcium scoring. Compared to CaRi-Plaque, it adds calcium scoring and expanded quantitative outputs (burden metrics, plaque composition categories); compared to Salix Central, it provides additional burden calculations and plaque composition classification.

Test standards cited

FDA 21 CFR Part 820.30 (Design Controls), IMDRF/SaMD WG/N12FINAL:2014, ISO 13485:2016 (Quality Management), IEC 62304:2015 (Software Lifecycle), ISO 14971:2019 (Risk Management), and NEMA 3.1-3.20 (2016) DICOM standards. FDA Guidance documents on Software Premarket Submissions and Cybersecurity in Medical Devices were also followed.

Substantial equivalence argument

The device shares identical intended use and clinical application with both predicates (CaRi-Plaque and Salix Central)—analyzing cardiac CT for coronary plaque and stenosis assessment. Technological differences are minor: the added calcium scoring capability and expanded quantitative measurements are supported by comprehensive clinical validation demonstrating that eight routine CCTA-trained readers achieved expert-level performance (95.8% stenosis categorization within one CAD-RADS grade, ICC values 0.61–0.96 for plaque volumes) against board-certified reference standards across multiple scanner vendors. Performance testing across diverse datasets exceeded all pre-defined acceptance criteria, establishing that these functional enhancements do not introduce unique safety or effectiveness questions.

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 →