Radiology AI Directory

FDA-cleared profile

SubtleHD (1.x)

Subtle Medical, Inc.

MRI image enhancement through noise reduction and sharpening for clinical image review.

MRI workflow
Evidence status: each field states its source quality, applicability, and review date. Research pending, information not established, and vendor documentation pending remain distinct outcomes.

Clinical details

What this tool is for

Start with the authorized purpose, then verify how it fits your service line and reading workflow.

Exact purpose
MRI image enhancement through noise reduction and sharpening for clinical image review.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Intended users
Radiologists and technologists in imaging centers, clinics or hospitals.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Care setting and population
Adult and Pediatric
  • Public source
  • Exact FDA submission
  • Checked 2026-09-01

Baseline patient-population label retained; the FDA material defines the acquisition scope.

Workflow role
Post-processing image enhancement
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Required input
Standard-of-care or accelerated DICOM MRI, including 2D/3D, contrast and noncontrast images of all body parts across the described protocols and 0.25-3 T field strengths.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Output and human action
Noise-reduced, sharpened DICOM images sent to a configured PACS, MR device or workstation; enhanced and original images coexist.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Limitations
Produces enhanced images, not diagnostic findings or disease classifications. Radiologists retain responsibility for interpreting the images.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05

Regulatory identity

FDA record and catalog context

The FDA listing establishes the regulatory identity. It does not by itself establish local workflow fit, pricing, security, or performance in your environment.

FDA submission
K243250
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Modality
MRI
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Anatomy
Whole Body
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Clearance type
510(k)
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Decision date
2025-02-12
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
FDA status
FDA-cleared
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31

Implementation

Questions for IT, informatics, and operations

Use these fields to structure a vendor demo, security review, and implementation estimate.

Integration
Background processing without an end-user image-viewing UI; configuration through files, environment settings or series descriptions. DICOM destinations are specified by AE title and IP address.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Deployment and data flow
On-premise
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05

Baseline category retained; the summary describes deployment in a virtual machine with Linux and off-the-shelf host hardware. Current hosting options require separate confirmation.

Security and privacy
Vendor documentation pending
  • Vendor confirmation
  • Exact FDA submission
  • Checked 2026-09-05

No scoped dated 1.x security certification, current host-patching agreement or site data-flow assessment was established.

Training and support
Vendor documentation pending
  • Vendor confirmation
  • Exact FDA submission
  • Checked 2026-09-05

Version-specific onboarding content, competency assessment and training costs were not established.

Monitoring and change control
Vendor documentation pending
  • Vendor confirmation
  • Exact FDA submission
  • Checked 2026-09-05

Current clinical-quality monitoring and upgrade acceptance procedures require confirmation.

Background DICOM routing

Processes DICOM images and returns enhanced images to configured AE-title/IP destinations while retaining original images.

exact submission · checked 2026-09-05
Source

Current scanner examples

Vendor provides MR enhancement examples by scanner manufacturer and body part; these are family context, not an exact-release compatibility matrix.

product family · checked 2026-09-05
Source

Evidence

Performance 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.

Evidence summary
The regulatory summary includes a 97-sample standalone comparison and a separate 410-image reader study assessing enhancement. A later vendor-authored study evaluates downstream classification using enhanced images and is contextual only.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05

Baseline study counts retained with separate study units; no pooled unique-patient total is asserted.

Reported sensitivity
Not established in reviewed sources
  • Reviewed sources checked
  • Exact FDA submission
  • Checked 2026-09-05

No exact-release disease-detection sensitivity is established by the reviewed enhancement studies.

Reported specificity
Not established in reviewed sources
  • Reviewed sources checked
  • Exact FDA submission
  • Checked 2026-09-05

No exact-release disease-detection specificity is established by the reviewed enhancement studies.

No contextualized exact-version metric has completed evidence review. Regulatory-document values, when available, are shown above with their limitations.

K243250 standalone enhancement comparison

  • DesignRetrospective standalone image-quality validation
  • Population97 MRI samples in the standalone comparison described in the summary
  • Scopeexact submission
  • Tested versionSubtleHD 1.x
  • Samplen=97
  • IndependenceSponsor or vendor study

K243250

Source

K243250 MRI reader study

  • DesignReader comparison of standard and enhanced MRI
  • Population410 images across body parts and protocols
  • Scopeexact submission
  • Tested versionSubtleHD 1.x
  • Samplen=410
  • IndependenceSponsor or vendor study

K243250

Image count, not a verified unique-patient total.

Source

Deep Learning-Based Enhancement of Already Diagnostic-Quality MRI for Alzheimer's Disease Classification: Effects on Model Performance and Training Data Requirements

  • DesignRetrospective downstream machine-learning classification study
  • Population2293 ADNI brain MRI scans split into training, validation and internal testing; 270 NACC scans for external testing, 1.5 T 3D T1 gradient echo
  • Scopeproduct family
  • Tested versionSubtleHD; software release not established in the reviewed abstract
  • Samplen=2293
  • IndependenceSponsor or vendor study

PMID:42593101 · DOI:10.1002/jmri.70507

Several authors are affiliated with Subtle Medical. ResNet34/DenseNet121, not SubtleHD itself, performed Alzheimer/MCI/normal classification. No diagnostic indication or numeric accuracy is transferred to K243250.

Source

Costs and setup

Budget and ongoing governance

These are common procurement questions; unknown values remain visible until a source supports them.

Pricing and total cost
Vendor documentation pending
  • Vendor confirmation
  • Exact FDA submission
  • Checked 2026-09-05

Current marketing offers a demo and operational-benefit examples, not a verified 1.x license/implementation price.

Reimbursement and coding
Research pending
  • Needs research
  • Exact FDA submission
  • Checked 2026-09-05

No applicable payer policy reviewed; throughput marketing does not establish separate reimbursement.

Safety and lifecycle

Postmarket record

Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.

Postmarket safety review
Not established in reviewed sources
  • Reviewed sources checked
  • Exact FDA submission
  • Checked 2026-09-06

Downloaded exact-ID recall packet contained zero records; this limited result does not establish absence of recall or safety information.

Buyer worksheet

Open questions to take to the vendor

Open evaluation checklist

Research record

What has been checked

This audit distinguishes completed source review from fields that have not yet been researched.

Human reviewedStatus
2026-09-05Last searched
20Fields reviewed
11Source classes checked
2Screened PubMed leads
0Screened trial leads
0Unreviewed FDA recall leads

42608377 is editorial metadata, excluded as primary performance evidence. 42593101 abstract reviewed and retained as vendor-associated family study of downstream classification; exact release unverified. The current discovery snapshot contains 2 PubMed and 0 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, acr ai central product, vendor product page, peer reviewed literature, stored candidate metadata, literature index, trial registry, pubmed, clinical trials, openfda device recall

Sources & history

How this profile was documented

Open the ledger for source dates, scope, and research-record updates.

View source ledger and history

Source ledger

  1. SubtleHD (1.x): K243250 clearance and summary

    U.S. Food and Drug Administration - Accessed 2026-09-05

    Scope: purpose, clinicalUse, modality, anatomy, input, output, deployment, integration, evidenceStudies

  2. Artificial Intelligence-Enabled Medical Devices

    U.S. Food and Drug Administration - Accessed 2026-08-31

    Scope: regulatoryIdentity, modalityContext

  3. SubtleHD (1.x) model card (K243250)

    American College of Radiology - Published 2026-07-20 - Accessed 2026-09-01

    Scope: purpose, modality, intendedUsers, careSetting, output, evidenceSummary, integration, anatomy, evidenceStudies, implementationCapabilities

  4. PubMed biomedical literature index

    U.S. National Library of Medicine - Accessed 2026-09-01

    Scope: evidenceDiscovery

  5. ClinicalTrials.gov study registry

    U.S. National Library of Medicine - Accessed 2026-09-01

    Scope: evidenceDiscovery, studyStatus

  6. openFDA Device Recall API

    U.S. Food and Drug Administration - Accessed 2026-09-02

    Scope: recallDiscovery, nativeSubmissionMatching

  7. SubtleHD(MR) product page

    Subtle Medical - Accessed 2026-09-05

    Scope: productFamilyContext, implementationCapabilities

  8. Deep Learning-Based Enhancement of Already Diagnostic-Quality MRI for Alzheimer's Disease Classification: Effects on Model Performance and Training Data Requirements

    Journal of Magnetic Resonance Imaging / U.S. National Library of Medicine - Published 2026-08-13 - Accessed 2026-09-05

    Scope: evidenceStudies, productFamilyContext

Research history

  1. K243250 FDA decision

    Regulatory record

    510(k)

  2. Source-review record updated

    Research record

    human reviewed

Alternatives

Related tools to compare

FDA-cleared K253775

SwiftMR

Airs Medical, Inc.

MRI image enhancement through noise reduction and sharpening; clinicians retain responsibility for final patient management decisions.

Modality
MRI
Anatomy
Whole Body
Decision
2026-03-26
MRI workflow
FDA-cleared K253690

LungMaps

Siemens Healthineers AG

LungMaps processes one or more 2D lung MRI time series to support radiologist interpretation of ventilation and perfusion maps; it is not the sole source for diagnosis.

Modality
MRI
Anatomy
Chest/Lung
Decision
2026-06-15
MRI workflow
FDA-cleared K260113

uMR Astra

Shanghai United Imaging Healthcare Co., Ltd.

uMR Astra is a diagnostic MR system for cross-sectional and spectroscopic imaging of the labeled head, body, and extremities.

Modality
MRI
Anatomy
Head; body; and extremities
Decision
2026-05-22
MRI workflow