Cirrus Resting State fMRI Software

K251009

Sora Neuroscience, Inc. · cleared 2025-06-06 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“Cirrus Resting State fMRI Software (Cirrus) is software as a medical device (SaMD) that performs image processing, resting state functional magnetic resonance imaging analysis, and output generation.”
Algorithmnonadaptive machine-learning based resting state network (RSN) membership scoring algorithm
source quote (p.5)
“Software components making up Cirrus include (i) a suite of fMRI preprocessing tools; (ii) a voxel-wise resting state fMRI correlation map generator, (iii) a nonadaptive machine-learning based resting state network (RSN) membership scoring algorithm; and (iv) an RSN map output generator.”
Adaptive (vs locked)No
source quote (p.5)
“a nonadaptive machine-learning based resting state network (RSN) membership scoring algorithm”
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.7)
“Software unit testing, verification testing, clinical performance validation testing, host platform testing, and cybersecurity penetration testing have been conducted upon Cirrus according to defined protocols.”

Validation studies (5)

Retrospective clinical

n=48 patients · 1 site(s)

standards: ISO 13485:2016, IEC-62304:2006 + A1:2015, ANSI/AAMI/ISO 14971:2019, AAMI TIR57:2016/R2019, NEMA PS 3.1-3.20 2024e

Retrospective clinical

n=692 patients · 1 site(s)

Retrospective clinical

sample size not stated

endpoints: spatial correlation with corresponding SMN maps; spatial correlation with corresponding LAN maps

Retrospective clinical

n=26 patients

endpoints: area under the ROC curve

Bench

n=8 patients · 8 site(s)

endpoints: Within-subject similarity across scanner types; cross-subject similarity

Reported performance (1 observation)

aurocas written: “auc”0.84
source quote (p.8)
“Cirrus vision maps had a mean area under the ROC curve of 0.84, demonstrating comparability to task-activated vision maps.”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

0
recalls in product code, 24mo
3
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
0
drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K251009