K-numberK251029
Device nameVista OS, Vista AI Scan, RTHawk
ApplicantVista AI, Inc.
Product codeLNH
Device classClass II
Decision dateAug 21, 2025
DecisionSubstantially Equivalent
Regulation892.1000
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

Vista OS is software that operates as an accessory to 1.5T and 3.0T MRI scanners from GE Healthcare and Siemens. It runs on a standalone Linux workstation connected via Ethernet to the MRI console and enables acquisition, reconstruction, and display of static and dynamic cross-sectional MR images of the entire body to assist physicians in diagnosis.

Technological characteristics

Vista OS adds several AI-based automation features not in the predicate: automatic motion artifact detection in cardiac cine imaging, detection of ungateable ECG waveforms, neural-network image denoising for cardiac images, and new localizer apps for brain and prostate with automatic prescription. It also adds a Frequency Scout App, Cine Flow Calibration App, an improved inversion pulse for cardiac T1 mapping, and support for newer GE software versions (HD16, SV25, MR30.1) and Ubuntu 24.04. All AI outputs remain under operator control; no clinical decisions are automated.

Test standards cited

IEC 60601-2-33:2022-08 (MR equipment safety), IEC 60601-1:2020 (general medical device safety, PEMS), MS1-2008 (SNR determination), MS3-2008 (image uniformity), MS4-2010 (acoustic noise), MS8-2016 (SAR characterization), NEMA PS3.1-3.20 (DICOM), and ISO 14971:2019 (risk management).

Substantial equivalence argument

Vista OS shares the same intended use, indications, scanner compatibility (1.5T/3.0T GE and Siemens), and functional architecture as the predicate K212233. Both acquire and display MR images via a parallel workstation with no hardware modification to the scanner. The new AI features are limited to scan optimization tasks (plane localization, artifact detection, parameter suggestions) where the technologist retains final control, and clinical verification testing on diverse patient populations demonstrated each AI model meets or exceeds predefined acceptance criteria. Safety parameters (SAR, dB/dt, operating modes) remain unchanged. The additions enhance workflow efficiency without altering the fundamental diagnostic capability or safety profile.

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 →