Ezra Flash

K242334

Ezra AI, Inc. · cleared 2025-01-02 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.6)

“Ezra Flash is a Software as a Medical Device (SaMD) consisting of a software algorithm that enhances images of the head, abdomen, and pelvis regions taken by MRI scanners.”

Algorithmconvolutional neural network-based filtering, machine-learning model

source quote (p.8)

“Ezra Flash software implements an image enhancement algorithm using a convolutional neural network-based filtering. Original images are enhanced by running through a cascade of filter banks, where thresholding and scaling operations are applied. These filters result in a single machine-learning model that reduces noise. A dedicated machine-learning model is used for the head and body. The parameters of the filters were obtained through an image-guided optimization process.”

Adaptive (vs locked)No

source quote (p.8)

“These filters result in a single machine-learning model that reduces noise. A dedicated machine-learning model is used for the head and body. The parameters of the filters were obtained through an image-guided optimization process.”

PCCPFDA source did not state this

Cybersecurity addressedYes

source quote (p.11)

“AAMI TIR57: 2016 - Principles For Medical Device Security - Risk Management”

Validation studies (1)

Standalone

sample size not stated

endpoints: Signal-to-Noise Ratio (SNR); Contrast-to-Noise Ratio (CNR); Image Quality - Perceived Noise

standards: ISO 14971:2019 - Medical Devices - Application of risk management to medical devices, IEC 62304 Edition 1.1: 2015 - Medical device software - Software life cycle processes, NEMA PS 3.1-3.20 (2021e) - Digital Imaging and Communications in Medicine (DICOM) set, AAMI TIR57: 2016 - Principles For Medical Device Security - Risk Management

Reported performance (0 observations)

FDA source did not state a quantitative performance metric — non-reporting is itself the signal.

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).