Rapid Neuro3D

K243350

iSchemaView, Inc. · cleared 2025-01-22 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.6)

“Rapid Neuro 3D (RN3D) is a Software as a Medical Device (SaMD) image processing module and is part of the Rapid Platform.”

Algorithmpre-trained artificial intelligence / machine-learning models

source quote (p.7)

“The RN3D image processing module is based on pre-trained artificial intelligence / machine-learning models and facilitates a 3D visualization of the neurovasculature supplying arterial blood to the brain.”

Adaptive (vs locked)No

source quote (p.7)

“The RN3D image processing module is based on pre-trained artificial intelligence / machine-learning models and facilitates a 3D visualization of the neurovasculature supplying arterial blood to the brain.”

PCCPFDA source did not state this

Cybersecurity addressedYes

source quote (p.11)

“Rapid has been designed to meet the cybersecurity requirements using design Vulnerability Assessments, SBOM's, and PEN Testing.”

Validation studies (2)

Reader study (MRMC)

n=120 cases

endpoints: clinical accuracy; labeling

standards: ISO 14971:2019, IEC 62304:2015, IEC 62366-1:2015 +A1:2020, NEMA PS 3.1 - 3.20, ISO 15223-1:2021

Retrospective clinical

n=50 cases

endpoints: segmentation accuracy; substantial equivalence; reproducibility; centerline accuracy

Reported performance (4 observations)

accuracyas written: “Labeling accuracy”1

source quote (p.11)

“The secondary endpoint, labeling, passed with 100% of the anatomical labels applied found to be accurate for the vessels visualized.”

diceas written: “Extracranial Dice Coefficient”0.89

source quote (p.12)

“For the extracranial region, the primary endpoint, segmentation accuracy, was met with an average Dice Coefficient of 0.89 and an average Hausdorff Distance of 0.44 mm between the module and ground truth.”

diceas written: “Intracranial Dice Coefficient”0.97

source quote (p.12)

“For the intracranial region, the primary endpoint, substantial equivalence, was met with an average Dice Coefficient of 0.97 and an average Hausdorff Distance of 0.44mm between the module and the predicate device.”

accuracyas written: “CPR centerline accuracy (Hausdorff Distance)”0.31

source quote (p.12)

“For the CPR visualizations, the primary endpoint, centerline accuracy, was met with an average Hausdorff Distance of 0.31 mm between the module and ground truth.”

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).