Authorized purpose: MRI image enhancement by reducing image noise for head, spine, neck, abdomen, pelvis, prostate, breast, and musculoskeletal MRI, or increasing image sharpness for head MRI.
Clinical role
Post-acquisition image processing; the end user selects noise reduction or sharpness enhancement through the DICOM Series Description, a command-line argument, or an environment variable.
Images and patients
MRI · Head, spine, neck, abdomen, pelvis, prostate, breast, and musculoskeletal regions
Key limitation
Keep in mind: The device has no user interface and operates as a fixed nonlinear filter whose parameters depend on the selected enhancement. The packet establishes 1.2T, 1.5T, and 3T MRI inputs but does not identify scanner manufacturers, PACS compatibility, or a broader diagnostic-performance claim.
Exact FDA record: K223623 · Agent source review · . This is not clinician review or local acceptance.
Within this record's scope
Consider for noise reduction in the labeled MRI anatomies, or sharpness enhancement of head MRI, with the supported field strengths.
Limits to check
The reviewed record does not establish a named PACS pairing or a broader diagnostic-performance claim. Head sharpening and multi-anatomy denoising have different scope.
Questions for the vendor and your team
Which release and enhancement functions are licensed, and how is the enhancement choice configured at this site?
Can the team verify the image path, selected enhancement, output identity and small-structure visibility on representative local studies?
These questions are prompts for evaluation, not claims that licensing, compatibility, performance or price has been confirmed.
A tag identifies a documented role; it does not establish compatibility or local acceptance. Methods and sources
What does this software do?Authorized purpose: MRI image enhancement by reducing image noise for head, spine, neck, abdomen, pelvis, prostate, breast, and musculoskeletal MRI, or increasing image sharpness for head MRI.
Which images or clinical context are in scope?Modality: MRI Anatomy or clinical context: Head, spine, neck, abdomen, pelvis, prostate, breast, and musculoskeletal regions Input: Standard-of-care MRI images acquired on 1.2 Tesla, 1.5 Tesla, or 3 Tesla scanners; the subject device processes DICOM files and additionally can process images communicated over ISMRMRD raw-data format.
Who uses it?Intended users: Radiologists in an imaging center, clinic, or hospital.
What does the software produce?Output: MRI images with reduced noise or increased sharpness, with image quality changes evaluated through signal-to-noise ratio, small-structure visibility, anatomic-structure thickness, and boundary sharpness.
What is its most important limitation?Key limitation: The device has no user interface and operates as a fixed nonlinear filter whose parameters depend on the selected enhancement. The packet establishes 1.2T, 1.5T, and 3T MRI inputs but does not identify scanner manufacturers, PACS compatibility, or a broader diagnostic-performance claim.
Clinical takeaway. Clinical role: MRI image enhancement by reducing image noise for head, spine, neck, abdomen, pelvis, prostate, breast, and musculoskeletal MRI, or increasing image sharpness for head MRI.
Evidence takeaway. Evidence from the reviewed source record: FDA software verification and validation included a retrospective clinical-data study divided into noise-reduction and sharpness-enhancement tests. Noise reduction required average ROI signal-to-noise improvement of at least 5% and non-inferior small-structure visibility by Likert assessment; the test passed. Sharpness enhancement required improved anatomic-structure thickness and boundary sharpness in at least 90% of test datasets; the test passed. The packet text does not state the study sample sizes.
Evidence context: questions, not a score
Agent transcription of regulatory evidence context, not independent validation, clinical acceptance or a product recommendation. Separate studies and outcomes are not a leaderboard.
Existing study anchor: SubtleMR (2.3.x) regulatory performance study summary. Tested version label: Exact product version not reported; regulatory study summarized for FDA submission K223623.
What was tested?
Noise reduction and sharpness enhancement in retrospective MRI datasets, with software verification testing.
The reviewed FDA summary does not disclose the test sample size, site count, population composition or scanner-specific distribution. These are explicit unknowns, not zero.
The summary says both tests passed. Mean ROI SNR improvement of at least 5% and sharpness criteria in at least 90% of test datasets are acceptance criteria, not reported average clinical-effect magnitudes.
Passed image-quality criteria do not establish cancer-detection sensitivity, patient outcomes, net throughput or performance for every MRI protocol. Missing sample sizes and confidence intervals remain missing.
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.
Not established: No explicit constraint transcribed from the reviewed labeling sections. Unknown does not mean unrestricted.
Label age limits
Not established: No numerical age bound or explicit all-ages statement in the reviewed labeling sections. Study ages do not establish authorized age limits.
Documented care setting
Imaging center, clinic or hospital; intended for radiologists.
MRI image enhancement: noise reduction in head, spine, neck, abdomen, pelvis, prostate, breast and musculoskeletal MRI; sharpness enhancement for head MRI.
MRI image enhancement by reducing image noise for head, spine, neck, abdomen, pelvis, prostate, breast, and musculoskeletal MRI, or increasing image sharpness for head MRI.
Post-acquisition image processing; the end user selects noise reduction or sharpness enhancement through the DICOM Series Description, a command-line argument, or an environment variable.
Standard-of-care MRI images acquired on 1.2 Tesla, 1.5 Tesla, or 3 Tesla scanners; the subject device processes DICOM files and additionally can process images communicated over ISMRMRD raw-data format.
MRI images with reduced noise or increased sharpness, with image quality changes evaluated through signal-to-noise ratio, small-structure visibility, anatomic-structure thickness, and boundary sharpness.
The device has no user interface and operates as a fixed nonlinear filter whose parameters depend on the selected enhancement. The packet establishes 1.2T, 1.5T, and 3T MRI inputs but does not identify scanner manufacturers, PACS compatibility, or a broader diagnostic-performance claim.
FDA software verification and validation included a retrospective clinical-data study divided into noise-reduction and sharpness-enhancement tests. Noise reduction required average ROI signal-to-noise improvement of at least 5% and non-inferior small-structure visibility by Likert assessment; the test passed. Sharpness enhancement required improved anatomic-structure thickness and boundary sharpness in at least 90% of test datasets; the test passed. The packet text does not state the study sample sizes.
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
FDA software verification and validation included a retrospective clinical-data study divided into noise-reduction and sharpness-enhancement tests. Noise reduction required average ROI signal-to-noise improvement of at least 5% and non-inferior small-structure visibility by Likert assessment; the test passed. Sharpness enhancement required improved anatomic-structure thickness and boundary sharpness in at least 90% of test datasets; the test passed. The packet text does not state the study sample sizes.
No contextualized exact-version metric has completed evidence review. Regulatory-document values, when available, are shown above with their limitations.
SubtleMR (2.3.x) regulatory performance study summary
DesignStand-Alone Performance
PopulationPopulation described in the exact-submission ACR model card
Scopeexact submission
Tested versionExact product version not reported; regulatory study summarized for FDA submission K223623
IndependenceIndependence not established
K223623
ACR AI Central summarizes the regulatory study; consult the exact FDA materials before comparative use.
Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.
Postmarket safety review
The exact-identifier FDA recall query returned no native recall record for K223623. This limited result does not establish absence of recalls or other safety information and does not cover later versions, family records, MAUDE reports, corrections, or field notices.
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
Existing route context (at most two)
Scanner/input support
Conditional support
AI version: SubtleMR (2.3.x); system version: not established
Scope: exact submission; geography: United States labeling
Configuration: The reviewed SubtleMR release can process images communicated over ISMRMRD; a format-version pairing is not established.
Condition: Agree the exact sender, format version, enhancement choice and supported data path.
Local test needed: Check identifiers, geometry, image identity, enhancement output, latency and recovery using representative site data.
Source review: 2026-11-06
Source documentation describes this scope; local installed-system acceptance remains open.
Installed-system acceptance has not been performed.
Source context, not route validation: Standard-of-care MRI images acquired on 1.2 Tesla, 1.5 Tesla, or 3 Tesla scanners; the subject device processes DICOM files and additionally can process images communicated over ISMRMRD raw-data format.
Scope: Exact FDA submission.
Confirm scanner/model, protocol, series completeness and both software builds.
Source context, not route validation: The FDA packet describes operation on DICOM files on a file system, storage of enhanced images on the file system, and additional ISMRMRD raw-data processing; it does not establish PACS, RIS, EHR, interface-version, or local compatibility.
Scope: Exact FDA submission.
Name gateways, destinations, transfer rules and failure visibility; a DICOM statement does not prove a route.
Unresolved route: Not established for the exact route.
Scope: Exact FDA submission. The reviewed sources do not establish the current exact-release hosting topology, data flow, region, tenancy, or disaster-recovery configuration.
Confirm processing location, queue ownership, exclusions and exact AI build.
Field checked 2026-09-09 ·
Returned objects
Source context, not route validation: MRI images with reduced noise or increased sharpness, with image quality changes evaluated through signal-to-noise ratio, small-structure visibility, anatomic-structure thickness, and boundary sharpness.
Scope: Exact FDA submission.
Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.
Unresolved route: MRI images with reduced noise or increased sharpness, with image quality changes evaluated through signal-to-noise ratio, small-structure visibility, anatomic-structure thickness, and boundary sharpness.
Scope: Exact FDA submission.
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.
Unresolved route: Not established for the exact route.
Scope: Scope not established.
Name the local, platform and AI supplier support owners and escalation path.
Planned local route tests
No tests below have been performed or accepted.
Patient/study identity (planned). Use approved non-patient test data to verify identifiers, accession and result-to-study linkage at every hop.
Study completeness (planned). Test missing views/series, partial transfer, late arrivals, priors and unsupported acquisition inputs; confirm explicit refusal or fallback.
Ordering and duplicates (planned). Send out-of-order, repeated and corrected studies; verify worklist order, deduplication and no misleading stale results.
Report transfer (planned). Verify output object types, annotations, units, report content, destination and availability of original images.
Access (planned). Verify authorized roles, audit trail, denied access and support ownership at each destination.
Latency and failures (planned). Agree a workload and turnaround target; test queues, timeouts, missing results and fallback reading.
Updates and rollback (planned). Define version change control, revalidation triggers, stop-use criteria and a tested rollback route.
Local implementation checklist
Agree the evidence and acceptance owner with your team and suppliers. Checkmarks apply to this page only and are not acceptance receipts.
The FDA packet describes operation on DICOM files on a file system, storage of enhanced images on the file system, and additional ISMRMRD raw-data processing; it does not establish PACS, RIS, EHR, interface-version, or local compatibility.
Subtle Medical's compliance page lists annual SOC 2 Type II + HIPAA security audits and independent certifications including EN ISO 13485:2016 (with MDSAP) and ISO/IEC 42001:2023 (AI management systems), with stated validity dates.
Vendor-wide
Checked 2026-10-27
Vendor statements; audit reports and certificates not read. SubtleMR is now branded SubtleHD (MR) on the vendor site. Exact-release scope is not established.
ACR AI Central provides an exact-submission model card for SubtleMR (2.3.x); FDA labeling remains controlling for clinical use, limitations, and performance.
Sources & review detailsFDA identity, research record, source ledger, and history
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.
These links identify a sourced product-family relationship. They do not transfer evidence, metrics, clearance scope, compatibility, pricing, or availability between submissions.
SubtleMR V2.0.0 · K203182. Name for this exact FDA record, not an alias for every commercial configuration. Name source
SubtleMR 2.3.x · K223623. Name for this exact FDA record, not an alias for every commercial configuration. Name source
SubtleMR image enhancement
MRI noise reduction and head-image sharpness enhancement. Applies to K203182, K223623. This describes the mapped function only; feature parity and a shared license are not established.
K223623 · 2023-05-11. Latest mapped decision only. Not automatically the latest sold or installed version, and not a supersession claim.
Latest documented release
Current commercial release or exact offered configuration is not established by this partial mapping.
Current commercial availability
Current commercial release or exact offered configuration is not established by this partial mapping.
Research record
What has been checked
This audit distinguishes completed source review from fields that have not yet been researched.
Exact FDA record reviewedStatus
2026-09-20Last searched
21Fields reviewed
9Source classes checked
2Screened PubMed leads
0Screened trial leads
0Unreviewed FDA recall leads
The refreshed discovery snapshot contains 2 PubMed and 0 ClinicalTrials.gov candidate records. Discovery metadata alone does not establish exact tested-product, version, population, and endpoint applicability, so all candidates remain quarantined and none was promoted. 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, fda device recall, literature index, trial registry, pubmed, clinical trials, openfda device recall
Field review details
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.
Public pricing: Not verified - checked 2026-09-09 - Exact FDA submission
No public price or quote for the exact K223623 configuration was established in this review.
Pricing model: Not yet reviewed
Setup and integration fees: Not yet reviewed
Recurring fees: Not yet reviewed
Minimum commitment: Not yet reviewed
Contract duration: Not yet reviewed
Renewal terms: Not yet reviewed
Cancellation terms: Not yet reviewed
Support and service terms: Not yet reviewed
Trial or pilot terms: Not yet reviewed
Reimbursement: Not publicly available - checked 2026-09-09 - Exact FDA submission
No exact-product payer policy, coding instruction, or payment determination was established; eligibility must be evaluated by payer, site of service, and use case.
Deployment: Not verified - checked 2026-09-09 - Exact FDA submission
The reviewed sources do not establish the current exact-release hosting topology, data flow, region, tenancy, or disaster-recovery configuration.
Data hosting location: Not yet reviewed
Data retention: Not yet reviewed
Documented data use: Not yet reviewed
Hardware requirements: Not yet reviewed
Network requirements: Not yet reviewed
Identity and access: Not yet reviewed
Installation timeline: Not yet reviewed
Training: Not verified - checked 2026-09-09 - Exact FDA submission
Current training prerequisites, competency checks, and support commitments for the exact configuration require vendor confirmation.
Monitoring: Not verified - checked 2026-09-09 - Exact FDA submission
Current drift, quality, uptime, alert, escalation, and incident-response commitments for the exact configuration require vendor confirmation.
Authorized purpose: SIGNA Bolt is a whole-body MRI system for high-resolution diagnostic imaging of the labeled body regions, with supported AI-assisted reconstruction, positioning, and protocol functions.
Authorized purpose: SIGNA Sprint Select is a whole-body MRI system for diagnostic imaging of the labeled body regions, with supported AI-assisted reconstruction, positioning, and protocol functions.
Authorized purpose: SIGNA Sprint is a 1.5T whole-body MRI system for diagnostic imaging of the labeled head, neck, TMJ, spine, breast, heart, abdomen, pelvis, joints, prostate, vessels, and musculoskeletal regions.
Authorized purpose: SIGNA Prime Elite is a whole-body MR system that produces cross-sectional, spectroscopic, parametric, and dynamic images of the labeled body regions for trained physician interpretation, with contrast use depending on the region and protocol.
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.
Permission 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.
Accepted repository change history
No entry has been added to this scoped change history for this record. This is not proof that the record never changed.