K-numberK251009
Device nameCirrus Resting State fMRI Software
ApplicantSora Neuroscience, Inc.
Product codeQIH
Device classClass II
Decision dateJun 6, 2025
DecisionSubstantially Equivalent
Regulation892.2050
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

Cirrus Resting State fMRI Software is a medical imaging post-processing application that analyzes resting state functional MRI (BOLD fMRI) data from brain scans. It generates task-analogous correlation maps for three brain networks (sensorimotor, language, and vision) in DICOM format for visualization by surgeons, radiologists, and clinicians. The software is adjunctive and not intended to replace direct functional mapping procedures.

Technological characteristics

Both Cirrus and its predicate device perform resting state BOLD fMRI post-processing using the same scientific principle: spontaneous neural activations in resting state data exhibit temporal correlation within functionally connected brain regions. Both co-register BOLD fMRI with anatomical scans, perform fMRI preprocessing, compute correlation matrices, and generate task-analogous motor, language, and vision resting state maps. Technological differences in preprocessing pipelines and analysis methodologies do not raise new safety or effectiveness questions.

Test standards cited

ISO 13485:2016 (quality management), IEC-62304:2006 + A1:2015 (software life cycle), ANSI/AAMI/ISO 14971:2019 (risk management), AAMI TIR57:2016/R2019 (cybersecurity), and NEMA PS 3.1-3.20 2024e (DICOM). Software underwent unit testing, verification testing, clinical performance validation, host platform testing, and cybersecurity penetration testing.

Substantial equivalence argument

Cirrus shares the same indications for use and underlying scientific principle as the predicate Quicktome Software Suite. Clinical validation demonstrated Cirrus sensorimotor and language maps had mean spatial correlation of 0.826 and 0.793 respectively with published literature references, and vision maps achieved ROC area of 0.84 compared to task-activated vision maps. Validation across multiple patient populations (ages 3-71, brain tumor and epilepsy patients) and scanner manufacturers (Siemens and GE) at 99.9% confidence demonstrated comparability, establishing that technological differences do not introduce new safety or effectiveness concerns.

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 →