Low-contrast insert brain scans
4 scans
- EndpointSynthetic-object contrast and contrast-to-noise comparison
- PopulationAIR Recon DL
- Tested versionAIR Recon DL with phase correction cleared in K252379
Authorized purpose: AIR Recon DL adds a deep-learning phase-correction and reconstruction option to supported GE 1.5T, 3T, and 7T MR workflows for all labeled anatomies and ages to reduce noise or ringing and support image quality or scan-time choices.
Overview status: Source-reviewed overview
Evaluation pilot
Exact FDA record: K252379 · Agent source review · . This is not clinician review or local acceptance.
These questions are prompts for evaluation, not claims that licensing, compatibility, performance or price has been confirmed.
Image processing · source-reviewed 2026-11-12
Agent source review of original FDA labeling; not clinician sign-off or local workflow qualification.
A tag identifies a documented role; it does not establish compatibility or local acceptance. Methods and sources
Clinical takeaway. Clinical role: AIR Recon DL adds a deep-learning phase-correction and reconstruction option to supported GE 1.5T, 3T, and 7T MR workflows for all labeled anatomies and ages to reduce noise or ringing and support image quality or scan-time choices.
Evidence takeaway. Evidence from the reviewed source record: K252379 FDA material describes bench and clinical image-quality evaluation including six volunteers across 1.5T and 3T systems and 34 de-identified datasets spanning breast, liver, brain, spine, and pelvis; all reported datasets were of diagnostic quality and no patient-outcome claim is made.
Agent transcription of regulatory evidence context, not independent validation, clinical acceptance or a product recommendation. Separate studies and outcomes are not a leaderboard.
K252379 · agent source review 2026-11-12 · exact submission
Existing study anchor: K252379 FDA performance package for AIR Recon DL. Tested version label: AIR Recon DL with phase correction cleared in K252379.
Phase-corrected MR reconstruction in phantom/quantitative tests, plus a separate radiologist clinical image-quality assessment.
Source section: 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
The clinical image-quality assessment used 34 datasets: breast 6, liver 5, brain 5, spine 3 and pelvis 15. Four brain diffusion scans refer only to low-contrast insert testing, not the entire evidence package.
Source section: 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
The summary reports improved phase/signal estimates and quantitative diffusion measures relative to the predicate, and favorable radiologist image-quality assessment. These are reconstruction and image-quality results, not a disease-detection trial.
Source section: 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
A favorable 34-dataset image-quality review does not establish patient outcomes, all-protocol performance, routine throughput or independent validation. Conference/publication citations in the submission are not newly admitted clinical studies here.
Source section: 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
technical validation · 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
technical validation · 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
technical validation · 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
technical validation · 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
technical validation · 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
technical validation · 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
technical validation · 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
regulatory summary · 510(k) summary, Summary of Nonclinical Testing and Clinical Image Quality Study
Public-label constraints, not patient-level eligibility or a medical recommendation. Training and evaluation populations are separate. Read the original labeling and confirm the exact release and protocol.
Exact FDA submission K252379 · agent source review 2026-11-09 · AIR Recon DL with phase correction cleared in K252379
Patients of all ages.
Patients of all ages, explicitly stated in the labeling.
Not established: No explicit constraint transcribed from the reviewed labeling sections. Unknown does not mean unrestricted.
Deep-learning reconstruction on GE HealthCare 1.5 T, 3.0 T and 7.0 T MR systems.
All anatomies, explicitly stated in the labeling.
GE HealthCare 1.5 T, 3.0 T or 7.0 T MR systems. Contrast agents may be used depending on anatomy. Phase-correction enhancement is activated by an additional software option key.
Not established: No explicit constraint transcribed from the reviewed labeling sections. Unknown does not mean unrestricted.
Prior source-backed dossier value: Image reconstruction and phase correction after MR data acquisition and before diagnostic interpretation.
Prior source-backed dossier value: Compatible raw MR acquisition data, including multiple intermediate images for supported diffusion workflows.
Indications for Use wording. The FDA document does not name who reviews the output, so the earlier "for radiologist review" clause was removed. Prior source-backed dossier value: Reconstructed MR images with reduced noise or ringing and phase-corrected combined images.
The Indications for Use form checks only "Prescription Use (Part 21 CFR 801 Subpart D)" and names no user group. The earlier radiologist, MRI-technologist, and qualified-professional value was not supported by this source and was removed. The U.S. board-certified radiologist in the clinical image-quality study is a study reader, not an intended-user statement. Agent source review, not clinician sign-off.
Prior source-backed dossier value: Acquisition-time savings and image-quality effects depend on sequence, anatomy, field strength, protocol, and workflow. The feature does not itself establish diagnostic accuracy or shorter total room time.
Prior source-backed dossier value: K252379 reports phantom and in-vivo brain diffusion testing. Four brain scans with synthetic low-contrast inserts showed significantly improved contrast-to-noise with phase correction while retaining contrast, and ADC testing reduced low-SNR bias. Independent product-family workflow literature should not be treated as exact-version validation.
Evidence
Metrics are shown only when they are tied to a source, endpoint, population, and tested product version. Candidate literature without exact product and version linkage is not shown as product evidence.
Prior source-backed dossier value: K252379 reports phantom and in-vivo brain diffusion testing. Four brain scans with synthetic low-contrast inserts showed significantly improved contrast-to-noise with phase correction while retaining contrast, and ADC testing reduced low-SNR bias. Independent product-family workflow literature should not be treated as exact-version validation.
Sensitivity is not the primary applicable endpoint for this acquisition, reconstruction, segmentation, planning, guidance, or dose-delivery function. Use the task-specific endpoints and tested population reported below. Sensitivity is not promoted as a product-wide endpoint. Compare only an exact endpoint, threshold, population, version, and source if later verified.
Specificity is not the primary applicable endpoint for this acquisition, reconstruction, segmentation, planning, guidance, or dose-delivery function. Use the task-specific endpoints and tested population reported below. Specificity is not promoted as a product-wide endpoint. Compare only an exact endpoint, threshold, population, version, and source if later verified.
4 scans
K252379
Manufacturer evidence submitted for substantial equivalence; local clinical, technical, and workflow acceptance remains necessary. The subtests use different samples, so no single package sample size is reported; the 4-scan count applies only to low-contrast insert testing.
Safety and lifecycle
Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.
Exact-identifier review does not prove absence of all product-family safety signals. Prior source-backed dossier value: The 2026-09-02 openFDA device-recall snapshot contained no record matched to K252379 by exact submission identifier.
Price not public here; enter your quote
Not publicly available: Reviewed sources do not publish an exact-product procurement price with a stated offer scope.
Prior source-backed dossier value: No separate named-product Medicare payment was identified in the reviewed CMS coverage material. Evaluate the device within the applicable imaging or surgical service line and verify payer, site-of-service, and coding assumptions independently.
No separate named-product payment identified in reviewed public material
Centers for Medicare & Medicaid Services · United StatesBuild a local total-cost and value model; do not infer reimbursement from FDA clearance.
No separate named-product payment identified in reviewed public material
Centers for Medicare & Medicaid Services · United StatesThis is not a product-specific reimbursement determination. Verify payer, site-of-service, coding, and coverage assumptions independently.
Match the AI release, system build, configuration and region. Source documentation does not establish acceptance of an installed system.
No specific system/version pairing has completed review for this FDA record. A broad DICOM or product-family statement does not establish a named viewer build's support.
Public source context, not tested interoperability. Each hop needs its own release/configuration evidence. Missing or unavailable routes are not documented incompatibility. All local tests are planned, not passed; no installed-system acceptance is recorded.
Acquisition/source → routing → AI processing → returned objects → viewer/worklist/report → support owner
No specific route context has been source-reviewed for this record. Obtain both endpoint builds and documents; this is not a finding of incompatibility.
Source context, not route validation: MR acquisition data from supported GE 1.5T, 3T, or 7T systems and labeled sequences, including multi-intermediate sequences such as diffusion-weighted imaging where supported.
Scope: Exact FDA submission. Prior source-backed dossier value: Compatible raw MR acquisition data, including multiple intermediate images for supported diffusion workflows.
Confirm scanner/model, protocol, series completeness and both software builds.
Field checked 2026-09-04 · FDA 510(k) decision material K252379: AIR Recon DL
Source context, not route validation: The FDA material describes an integrated GE MR software option key and reconstruction path within supported GE MR systems and sequences.
Scope: Exact FDA submission. This is the interface boundary described in the exact FDA decision material; current local compatibility, routing, identity, archive, and downtime behavior still require acceptance testing. Prior source-backed dossier value: Embedded reconstruction on compatible GE MR platforms; validate DICOM appearance, scaling, quantitative maps, protocol transfer, and downstream analysis.
Name gateways, destinations, transfer rules and failure visibility; a DICOM statement does not prove a route.
Field checked 2026-09-04 · FDA 510(k) decision material K252379: AIR Recon DL · GE HealthCare AIR Recon DL · Impact of Deep Learning Image Reconstruction Methods on MRI Throughput
Source context, not route validation: The FDA material describes software integrated into supported GE MR systems and enabled by an option key; current scanner configuration, service, security, and upgrade boundaries remain unverified.
Scope: Exact FDA submission. This is the release-level boundary described in the exact FDA decision material; current hosting, contracts, security, availability, upgrade path, and site configuration remain separate evidence. Prior source-backed dossier value: Licensed reconstruction software on compatible GE 1.5T, 3T, or 7T MR system configurations.
Confirm processing location, queue ownership, exclusions and exact AI build.
Field checked 2026-09-04 · FDA 510(k) decision material K252379: AIR Recon DL · GE HealthCare AIR Recon DL · Impact of Deep Learning Image Reconstruction Methods on MRI Throughput
Source context, not route validation: Reconstructed MR images with reduced noise and ringing (truncation artifacts), which can be used to reduce scan time and improve image quality.
Scope: Exact FDA submission. Indications for Use wording. The FDA document does not name who reviews the output, so the earlier "for radiologist review" clause was removed. Prior source-backed dossier value: Reconstructed MR images with reduced noise or ringing and phase-corrected combined images.
Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.
Field checked 2026-11-12 · FDA 510(k) decision material K252379: AIR Recon DL
Unresolved route: Reconstructed MR images with reduced noise and ringing (truncation artifacts), which can be used to reduce scan time and improve image quality.
Scope: Exact FDA submission. Indications for Use wording. The FDA document does not name who reviews the output, so the earlier "for radiologist review" clause was removed. Prior source-backed dossier value: Reconstructed MR images with reduced noise or ringing and phase-corrected combined images.
Confirm the named viewer/worklist/report build, display behavior and report transfer. Output support alone does not establish this endpoint. The displayed source describes output, not validated end-to-end delivery.
Field checked 2026-11-12 · FDA 510(k) decision material K252379: AIR Recon DL
Unresolved route: Not established for the exact route.
Scope: Scope not established.
Name the local, platform and AI supplier support owners and escalation path.
No tests below have been performed or accepted.
Agree the evidence and acceptance owner with your team and suppliers. Checkmarks apply to this page only and are not acceptance receipts.
This is the release-level boundary described in the exact FDA decision material; current hosting, contracts, security, availability, upgrade path, and site configuration remain separate evidence. Prior source-backed dossier value: Licensed reconstruction software on compatible GE 1.5T, 3T, or 7T MR system configurations.
This is the interface boundary described in the exact FDA decision material; current local compatibility, routing, identity, archive, and downtime behavior still require acceptance testing. Prior source-backed dossier value: Embedded reconstruction on compatible GE MR platforms; validate DICOM appearance, scaling, quantitative maps, protocol transfer, and downstream analysis.
Vendor statement, not an attestation. Identity bridge: GE HealthCare's own Privacy Shield page on gehealthcare.com names GE Medical Systems LLC as a US entity of the GEHC group. Corporate program statement; portal content is credentialed; exact-release scope is not established.
Buyer-facing monitoring guidance derived from the exact cleared scope; it is not a claim that the FDA package provides a live monitoring service. Prior source-backed dossier value: Monitor by exact hardware, software and model version, patient population, anatomy, protocol, operator, input quality, output edits or overrides, failed studies, repeat acquisition or rework, downstream impact, downtime, incidents, recalls, and updates. Track the limits that matter for this product: Acquisition-time savings and image-quality effects depend on sequence, anatomy, field strength, protocol, and workflow. The feature does not itself establish diagnostic accuracy or shorter total room time.
Map the installed model, build, options, population, anatomy, inputs, and outputs to K252379 before acceptance.
exact submission · checked 2026-09-03Later product-family features are not evidence that this cleared release includes them.
Embedded reconstruction on compatible GE MR platforms; validate DICOM appearance, scaling, quantitative maps, protocol transfer, and downstream analysis.
exact submission · checked 2026-09-03Test representative identifiers, orientation, geometry, measurements, units, routing, failure handling, and round trips locally.
Use a signed local test set for the supported population and workflow. Include common and difficult cases, exclusions, acquisition variation, failed or low-quality inputs, reviewer overrides, and downstream effects. Acquisition-time savings and image-quality effects depend on sequence, anatomy, field strength, protocol, and workflow. The feature does not itself establish diagnostic accuracy or shorter total room time.
exact submission · checked 2026-09-03Define stop-use, escalation, rollback, and revalidation triggers before production use.
Model capital and recurring cost against net staff time after review, throughput, repeat imaging or rework, room time, consumables, infrastructure, training, service, downtime, upgrade, and replacement costs.
product family · checked 2026-09-03Vendor productivity claims are scenario inputs, not guaranteed local savings.
Monitor by exact hardware, software and model version, patient population, anatomy, protocol, operator, input quality, output edits or overrides, failed studies, repeat acquisition or rework, downstream impact, downtime, incidents, recalls, and updates. Track the limits that matter for this product: Acquisition-time savings and image-quality effects depend on sequence, anatomy, field strength, protocol, and workflow. The feature does not itself establish diagnostic accuracy or shorter total room time.
exact submission · checked 2026-09-03Revalidate after material software, hardware, model, protocol, interface, or clinical-policy changes.
The FDA material describes software integrated into supported GE MR systems and enabled by an option key; current scanner configuration, service, security, and upgrade boundaries remain unverified.
exact submission · checked 2026-09-04FDA-described deployment boundaries do not establish current hosting contracts, security controls, uptime, or local qualification.
Regulatory identity
The FDA listing establishes the regulatory identity. It does not by itself establish local workflow fit, pricing, security, or performance in your environment.
Documented product family
These links identify a sourced product-family relationship. They do not transfer evidence, metrics, clearance scope, compatibility, pricing, or availability between submissions.
A partial mapping of two reviewed FDA submissions. Evidence, compatible inputs, licensing and availability remain specific to each record.
The K252379 summary explicitly describes a modification of AIR Recon DL K213717. The phase-correction enhancement needs an additional software option key. Scanner-system records are not included.
Latest mapped does not mean latest sold or installed. Choose an exact FDA record before comparing.
AIR Recon DL in K213717
FDA decision: 2022-06-08 · record reviewed 2026-11-09AIR Recon DL with Phase Correction in K252379
Latest mapped FDA decisionFDA decision: 2025-12-23 · record reviewed 2026-11-09MR reconstruction to reduce noise and ringing artifacts. Applies to K213717, K252379. This describes the mapped function only; feature parity and a shared license are not established.
Current availability of an exact FDA-submission configuration is not established. Ask the supplier for the offered release and licensed modules.
Research record
This audit distinguishes completed source review from fields that have not yet been researched.
Screened 12 PubMed and one ClinicalTrials.gov record. AIR Recon DL records do not link their tested release to the K252379 phase-correction configuration, while the remaining records are generic reconstruction studies; all 13 were quarantined and none was promoted. The current discovery snapshot contains 12 PubMed and 1 ClinicalTrials.gov candidate records; its dated, count-matched human screening remains current. Unlinked candidates remain quarantined. Native FDA recall identifiers produced 0 postmarket candidate records; 0 have been reviewed (0 published, 0 rejected) and 0 remain unreviewed.
Candidate leads were screened against the exact product and tested version. Unlinked records remain quarantined.
Source classes: fda ai list, fda decision summary, fda decision material, peer reviewed literature, clinical trial registry, reimbursement policy, fda device recall, vendor product page, pubmed, clinical trials, openfda device recall
Recorded state, verification date, notes and sources for fields without a publishable value. Conflicting records stay explicitly unsettled here; no plain settled value is shown for them.
The exact FDA decision-summary packet limits use to "GE HealthCare 1.5T, 3.0T, and 7.0T MR systems" but states no hospital, outpatient, or other care setting; the earlier hospital and outpatient value was not supported by this source and was removed. Unknown does not mean unrestricted. Agent source review, not clinician sign-off.
No public list price for the exact cleared configuration was found. Obtain a written quote separating hardware or license basis, enabled features, implementation, interfaces, infrastructure, training, service, upgrades, renewal, consumables, and exit costs. Obtain a written quote separating hardware or license basis, implementation, interfaces, infrastructure, training, service, upgrades, renewal, consumables, and exit costs.
The exact FDA decision-summary packet states no operator or interpreter group and no training requirement beyond the checked "Prescription Use (Part 21 CFR 801 Subpart D)" box; the earlier user-restriction value was not supported by this source and was removed. Training prerequisites and competency checks for the exact configuration require vendor confirmation; local onboarding should still cover the exact release, supported population, limitations, failure examples, escalation, downtime, and competency documentation. Agent source review, not clinician sign-off.
11 sources - 3 history items
Scope: identity, productIdentity, purpose, clinicalUse, modality, anatomy, intendedUsers, careSetting, workflowRole, input, output, limitations, evidenceSummary
Scope: regulatoryIdentity, modalityContext
Scope: evidenceDiscovery
Scope: evidenceDiscovery, studyStatus
Scope: coverage, codingContext
Scope: recallDiscovery, nativeSubmissionMatching
Scope: evidenceSummary, evidenceStudy, evidenceMetrics, economicsObservation, implementationCapabilities
Scope: integration, deployment, monitoring, productFamilyContext
Scope: security
Scope: purpose, modality, anatomy, evidenceSummary, input, output, limitations, clinicalUse, product_family
Scope: identity, productIdentity, purpose, clinicalUse, modality, anatomy, intendedUsers, careSetting, workflowRole, input, output, limitations, evidenceSummary, product_family
Regulatory record
510(k)
Research record
human reviewed
Editorial review
Source-reviewed editorial overlay
Alternatives
Canon Medical Systems Corporation
Authorized purpose: Vantage Fortian and Orian 1.5T produce diagnostic MR images of the head and body, including labeled noncontrast angiography, for trained technologists and physician interpretation.
Esaote, S.p.A.
Authorized purpose: S-scan Open is an Esaote MR system for diagnostic image acquisition, reconstruction, display, and professional interpretation within the labeled scanner, coil, sequence, and anatomy scope.
Siemens Healthcare GmbH
Authorized purpose: The listed MAGNETOM 1.5T and 3T MRI systems produce cross-sectional images, spectroscopic images or spectra, and derived physical parameters of the head, body, and extremities for trained-physician interpretation and can support imaging during MR-compatible interventions.
Siemens Shenzhen Magnetic Resonance, Ltd.
Authorized purpose: MAGNETOM Free.Max and Free.Star with syngo MR XA80A are 0.55T MRI systems for broad imaging and compatible interventions; this release adds dentomaxillofacial coil and assist functions plus reconstruction and energy-mode updates.
Copy this public context and add the field, proposed wording and original source before sending. Nothing here is submitted automatically. Form-specific prefill has not been verified.
Open existing correction destinationPermission to display a submission is not evidence verification. A submission enters editorial review; it does not approve a public change. Form availability, data entry, receipt, review and publication are separate steps. Data entry and receipt remain unverified.
No entry has been added to this scoped change history for this record. This is not proof that the record never changed.
Correction policy and limits · Public repository change history