SwiftSight-Brain

K251483

AIRS Medical Inc. · cleared 2025-09-23 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“SwiftSight-Brain is a fully automated MR image analysis software that provides automatic labeling, visualization, and volumetric quantification of brain structures from a set of MR images and returns segmented images and morphometric reports.”

AlgorithmProprietary automated internal pipeline that performs segmentation, volume calculation and report generation, using deep learning for automatic segmentation and quantification of brain structures.

source quote (p.6)

“SwiftSight-Brain processing architecture includes a proprietary automated internal pipeline that performs segmentation, volume calculation and report generation. Automatic segmentation and quantification of brain structures using deep learning”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (2)

Retrospective clinical

n=72 cases

endpoints: segmentation accuracy compared to expert manual segmentations of 3D T1 MRI scans was evaluated using Dice's coefficient metric; Brain structural reproducibility of repeated 3D T1 MRI scans for same subjects was evaluated by using the percentage absolute volume differences

Retrospective clinical

n=160 cases

endpoints: lesion segmentation accuracy compared to expert manual segmentations of T2 weighted FLAIR scan was evaluated using Dice's coefficient metric; brain lesion segmentation reproducibility was evaluated using repeated T2 weighted FLAIR scan pairs of subjects with brain lesions

Reported performance (3 observations)

diceas written: “Dice's coefficient (major subcortical brain structures)”0.8

source quote (p.8)

“For major subcortical brain structures Dice's coefficients were above 80%”

diceas written: “Dice's coefficient (major cortical structures)”0.75

source quote (p.8)

“and for major cortical were above 75%.”

diceas written: “Dice's coefficient (lesion segmentation accuracy)”0.8

source quote (p.9)

“SwiftSight-Brain's lesion segmentation accuracy compared to expert manual segmentations of T2 weighted FLAIR scan was evaluated using Dice's coefficient metric, which exceeds 0.80.”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).