Authorized purpose: Aid interpreting physicians in detecting, localizing, and characterizing suspicious breast-cancer areas on mammograms from compatible FFDM systems, viewed after the physician completes the initial read.
Clinical role
Second-read adjunct for detection, localization, and characterization; it does not replace complete physician review or clinical judgment.
Images and patients
Mammography/DBT · Breast.
Key limitation
Keep in mind: Use is limited to screening mammograms from compatible FFDM systems and the female screening population described in the packet. The output is adjunctive after the initial read and is not a replacement for complete physician review, clinical judgment, or other patient/image information. DBT is not established in this packet.
Clinical detailsPurpose, workflow fit, evidence, and safety record
Workflow navigation pilot
Workflow role has not yet been reviewed for this navigation pilot.
A tag identifies a documented role; it does not establish compatibility or local acceptance. Methods and sources
What does this software do?Authorized purpose: Aid interpreting physicians in detecting, localizing, and characterizing suspicious breast-cancer areas on mammograms from compatible FFDM systems, viewed after the physician completes the initial read.
Which images or clinical context are in scope?Modality: Mammography/DBT Anatomy or clinical context: Breast. Input: Screening mammograms from compatible full-field digital mammography systems, received as DICOM images from a PACS or other radiological imaging equipment.
Who uses it?Intended users: Physicians interpreting screening mammograms; the target population is women undergoing FFDM screening mammography.
What does the software produce?Output: Visualized lesion maps/heatmaps, finding-level lesion scores from 1-100, and a per-breast abnormality score based on the maximum of the CC and MLO view scores; analysis results are converted to DICOM for storage.
What is its most important limitation?Key limitation: Use is limited to screening mammograms from compatible FFDM systems and the female screening population described in the packet. The output is adjunctive after the initial read and is not a replacement for complete physician review, clinical judgment, or other patient/image information. DBT is not established in this packet.
Clinical takeaway. Clinical role: Aid interpreting physicians in detecting, localizing, and characterizing suspicious breast-cancer areas on mammograms from compatible FFDM systems, viewed after the physician completes the initial read.
Evidence takeaway. Evidence from the reviewed source record: FDA K211678 reports standalone testing on 2,412 mammograms acquired on Hologic, GE Healthcare, and Siemens systems, using an independent dataset. Standalone ROC AUC was 0.903 (95% CI 0.889-0.917), with sensitivity 85.74% (95% CI 82.95%-88.53%) and specificity 75.62% (95% CI 73.64%-77.60%); LROC AUC values were 0.781 and 0.792. A separate U.S. retrospective MRMC reader study used 240 mammograms and 12 MQSA-qualified readers: ROC AUC was 0.754 unaided versus 0.805 aided, a 0.051 difference (95% CI 0.027-0.075; p=0.0001). Reader sensitivity and non-cancer recall-rate deltas were exploratory and are distinct from standalone algorithm sensitivity/specificity.
Evidence context
Evidence context not reviewed for this FDA record.
Public-label constraints
Label constraints have not been reviewed for this exact FDA record. Unknown is not all ages or evidence of unsuitability.
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.
Purpose
Aid interpreting physicians in detecting, localizing, and characterizing suspicious breast-cancer areas on mammograms from compatible FFDM systems, viewed after the physician completes the initial read.
Screening mammograms from compatible full-field digital mammography systems, received as DICOM images from a PACS or other radiological imaging equipment.
Visualized lesion maps/heatmaps, finding-level lesion scores from 1-100, and a per-breast abnormality score based on the maximum of the CC and MLO view scores; analysis results are converted to DICOM for storage.
Use is limited to screening mammograms from compatible FFDM systems and the female screening population described in the packet. The output is adjunctive after the initial read and is not a replacement for complete physician review, clinical judgment, or other patient/image information. DBT is not established in this packet.
FDA K211678 reports standalone testing on 2,412 mammograms acquired on Hologic, GE Healthcare, and Siemens systems, using an independent dataset. Standalone ROC AUC was 0.903 (95% CI 0.889-0.917), with sensitivity 85.74% (95% CI 82.95%-88.53%) and specificity 75.62% (95% CI 73.64%-77.60%); LROC AUC values were 0.781 and 0.792. A separate U.S. retrospective MRMC reader study used 240 mammograms and 12 MQSA-qualified readers: ROC AUC was 0.754 unaided versus 0.805 aided, a 0.051 difference (95% CI 0.027-0.075; p=0.0001). Reader sensitivity and non-cancer recall-rate deltas were exploratory and are distinct from standalone algorithm sensitivity/specificity.
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 K211678 reports standalone testing on 2,412 mammograms acquired on Hologic, GE Healthcare, and Siemens systems, using an independent dataset. Standalone ROC AUC was 0.903 (95% CI 0.889-0.917), with sensitivity 85.74% (95% CI 82.95%-88.53%) and specificity 75.62% (95% CI 73.64%-77.60%); LROC AUC values were 0.781 and 0.792. A separate U.S. retrospective MRMC reader study used 240 mammograms and 12 MQSA-qualified readers: ROC AUC was 0.754 unaided versus 0.805 aided, a 0.051 difference (95% CI 0.027-0.075; p=0.0001). Reader sensitivity and non-cancer recall-rate deltas were exploratory and are distinct from standalone algorithm sensitivity/specificity.
Standalone Lunit INSIGHT MMG sensitivity: 85.74% (95% CI 82.95%-88.53%) on 2,412 screening mammograms; the separate reader-study cancer-group recall-rate difference was 5.97 percentage points.
FDA source
Exact FDA submission
Checked 2026-09-09
The standalone algorithm endpoint must remain separate from the aided-versus-unaided reader-study delta and ROC AUC.
Standalone Lunit INSIGHT MMG specificity: 75.62% (95% CI 73.64%-77.60%) on 2,412 screening mammograms; the separate reader-study non-cancer recall-rate difference was -1.46 percentage points.
FDA source
Exact FDA submission
Checked 2026-09-09
This is the standalone algorithm endpoint; reader-study recall, ROC AUC, and LROC AUC are distinct and must not be substituted.
No contextualized exact-version metric has completed evidence review. Regulatory-document values, when available, are shown above with their limitations.
Lunit INSIGHT MMG regulatory performance study summary
DesignStand-alone performance and reader study (ACR AI Central category)
PopulationPopulation described in the exact-submission ACR model card
Scopeexact submission
Tested versionExact product version not reported; regulatory study summarized for FDA submission K211678
Samplen=2412
IndependenceIndependence not established
K211678
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 K211678. 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.
IT implementationDeployment, interfaces, data handling, and support
System and version relationships
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.
Acquisition/source
Source context, not route validation: Screening mammograms from compatible full-field digital mammography systems, received as DICOM images from a PACS or other radiological imaging equipment.
Scope: Exact FDA submission.
Confirm scanner/model, protocol, series completeness and both software builds.
Source context, not route validation: The software receives mammograms from a client image-storage system such as PACS or other radiological equipment, de-identifies DICOM copies, and saves DICOM results to a designated location such as PACS or an X-ray system. Exact interface versions, routing, and local compatibility are not established.
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 exact FDA decision document was reviewed on 2026-11-14 and does not state where the subject device's software runs or how it is hosted. Confirm the deployment model, hosting, data flow, and current commercial configuration with the vendor.
Confirm processing location, queue ownership, exclusions and exact AI build.
Field checked 2026-11-14 ·
Returned objects
Source context, not route validation: Visualized lesion maps/heatmaps, finding-level lesion scores from 1-100, and a per-breast abnormality score based on the maximum of the CC and MLO view scores; analysis results are converted to DICOM for storage.
Scope: Exact FDA submission.
Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.
Unresolved route: Visualized lesion maps/heatmaps, finding-level lesion scores from 1-100, and a per-breast abnormality score based on the maximum of the CC and MLO view scores; analysis results are converted to DICOM for storage.
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 software receives mammograms from a client image-storage system such as PACS or other radiological equipment, de-identifies DICOM copies, and saves DICOM results to a designated location such as PACS or an X-ray system. Exact interface versions, routing, and local compatibility are not established.
Lunit's information security page states the company is ISO/IEC 27001 certified, with ISO 13485 and MDSAP at its manufacturing site. Company-level; the page gives no scope, dates or product controls.
Vendor-wide
Checked 2026-10-25
Vendor statement, not an attestation; exact-release scope is not established.
ACR AI Central provides an exact-submission model card for Lunit INSIGHT MMG; 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.
This audit distinguishes completed source review from fields that have not yet been researched.
Exact FDA record reviewedStatus
2026-09-20Last searched
25Fields reviewed
10Source classes checked
12Screened PubMed leads
4Screened trial leads
0Unreviewed FDA recall leads
The refreshed discovery snapshot contains 12 PubMed and 4 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 12 PubMed and 4 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 documentation, 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 K211678 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 publicly available - checked 2026-11-14 - Exact FDA submission
The exact FDA decision document was reviewed on 2026-11-14 and does not state where the subject device's software runs or how it is hosted. Confirm the deployment model, hosting, data flow, and current commercial configuration with the vendor.
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: Lunit INSIGHT MMG v1.1.10 aids physicians in detection, localization and characterization of suspicious breast-cancer areas on female screening mammograms from compatible FFDM systems, viewed after the physician's initial read as an adjunct to complete clinical interpretation.
Authorized purpose: Concurrent CADe/x aid for interpreting physicians to detect and characterize breast-cancer-suspicious lesions in screening DBT exams from compatible systems, marking soft-tissue lesions and calcifications with abnormality scores.
Authorized purpose: Genius AI Detection 2.0 analyzes compatible digital breast tomosynthesis exams to identify and mark soft-tissue densities (masses, architectural distortions, asymmetries) and calcifications, providing lesion location/outline, confidence or Certainty of Findings, and a case score for concurrent review; the interpreting physician confirms or dismisses findings.
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.