K-numberK252608
Device nameAI-Rad Companion Prostate MR
ApplicantSiemens Healthcare GmbH
Product codeLLZ
Device classClass II
Decision dateSep 9, 2025
DecisionSubstantially Equivalent
Regulation892.2050
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

AI-Rad Companion Prostate MR is software that processes and annotates MRI images of the prostate in adult males suspected of having prostate cancer. It provides radiologists with viewing, analysis, and evaluation capabilities for multiple MR image types (DCE, ADC, T2, DWI), hosts an external AI plug-in for lesion detection, and allows acceptance, rejection, or editing of the AI-generated results to support diagnostic interpretation and biopsy planning.

Technological characteristics

The subject device uses an AI-Rad Companion Engine architecture supporting both cloud and edge deployment via web-based interface, whereas the predicate was cloud-only. The automatic segmentation algorithm is now delegated to a separate plug-in device (Prostate MR AI K241770) rather than embedded. The subject offers expanded use scenarios including lesion scoring and PI-RADS computation, plus an automatic workflow option in addition to semi-automatic workflow. Export capabilities now include DICOM Secondary Capture, Structured Report, and GSPS formats.

Test standards cited

ISO 14971 (risk management), IEC 62304 (software lifecycle), IEC 62366-1 (usability engineering), ISO 15223-1 (symbols), IEC 82304-1 (health software safety), ISO 20417 (manufacturer information), and NEMA DICOM PS 3.1–3.20 (medical imaging communications). Testing also adhered to FDA guidance on device software functions (June 2023) and cybersecurity management (September 2023).

Substantial equivalence argument

The subject device maintains equivalent intended use and fundamental technology (MR image processing for prostate oncology assessment) as the predicate K193283. Although the segmentation algorithm is now separated into a plug-in and new features (PI-RADS scoring, automatic workflow, additional export formats) have been added, comprehensive verification and validation testing confirmed these enhancements do not adversely affect safety or effectiveness. The core diagnostic workflow and user roles remain unchanged, with improvements only enhancing workflow efficiency and reducing procedural complexity.

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 →