Radiology AI Directory

FDA-cleared profile

Lunit INSIGHT MMG

Lunit Inc.

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.

Breast imagingDetection and CADe
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
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.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Intended users
Physicians interpreting screening mammograms; the target population is women undergoing FFDM screening mammography.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Care setting and population
Screening mammography workflow, with the device viewed after the initial physician read.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Workflow role
Second-read adjunct for detection, localization, and characterization; it does not replace complete physician review or clinical judgment.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Required input
Screening mammograms from compatible full-field digital mammography systems, received as DICOM images from a PACS or other radiological imaging equipment.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Output and human action
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.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Limitations
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 source
  • Exact FDA submission
  • Checked 2026-09-09

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
K211678
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Modality
Mammography/DBT
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Anatomy
Breast.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Clearance type
510(k)
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Decision date
2021-11-17
  • 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
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.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Deployment and data flow
On-premise
  • Public source
  • Exact FDA submission
  • Checked 2026-08-13

Deployment category preserved from the prior exact-submission review; hosting region, data flow, and current commercial configuration still require vendor confirmation.

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

Exact-release security controls, data retention, hosting boundaries, and scoped assurance documentation require vendor confirmation.

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

Current training prerequisites, competency checks, and support commitments for the exact configuration require vendor confirmation.

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

Current drift, quality, uptime, alert, escalation, and incident-response commitments for the exact configuration require vendor confirmation.

Supported acquisition environment

Scanner manufacturers: All

exact submission · checked 2026-09-01

Confirm currently supported software versions, protocols, and site-specific acquisition configurations.

Source

ACR exact-submission catalog context

ACR AI Central provides an exact-submission model card for Lunit INSIGHT MMG; FDA labeling remains controlling for clinical use, limitations, and performance.

exact submission · checked 2026-09-09
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
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.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Reported sensitivity
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.

Reported specificity
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.

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 2026-09-09

No public price or quote for the exact K211678 configuration was established in this review.

Reimbursement and coding
Not established in reviewed sources
  • Reviewed sources checked
  • Exact FDA submission
  • Checked 2026-09-09

No exact-product payer policy, coding instruction, or payment determination was established; eligibility must be evaluated by payer, site of service, and use case.

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
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.
  • Public source
  • Exact FDA submission
  • Checked 2026-09-09

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.

Exact FDA record reviewedStatus
2026-09-09Last searched
24Fields reviewed
9Source classes checked
0Awaiting review PubMed leads
4Awaiting review trial leads
0Unreviewed FDA recall leads

Exact-submission ACR model-card fields were normalized under the current provenance rules; vendor and independent-study confirmation remain distinct. Exact FDA scope controls clinical claims. ACR provides bounded exact-submission catalog context. Candidate literature metadata remains a discovery queue until full-text identity, endpoint, population, and version review is completed. Automated exact-name discovery found 0 PubMed and 4 ClinicalTrials.gov candidate records. Candidates require human product and version matching; zero candidates is not evidence that no studies exist. Native FDA recall identifiers produced 0 postmarket candidate records; 0 have been reviewed (0 published, 0 rejected) and 0 remain unreviewed.

Candidate leads remain unpublished until a human confirms the exact product and tested version.

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

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. FDA K211678: Lunit INSIGHT MMG

    U.S. Food and Drug Administration - Published 2021-11-17 - Accessed 2026-09-09

    Scope: identity, clinicalUse, modality, anatomy, workflow, evidence, implementation

  2. Artificial Intelligence-Enabled Medical Devices

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

    Scope: regulatoryIdentity, modalityContext

  3. Lunit INSIGHT MMG model card (K211678)

    American College of Radiology - Published 2026-06-26 - Accessed 2026-09-01

    Scope: intendedUsers, output, limitations, reportedSensitivity, reportedSpecificity, evidenceSummary, 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. openFDA exact recall query for K211678

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

    Scope: postmarketSafety

Research history

  1. K211678 FDA decision

    Regulatory record

    510(k)

  2. Source-review record updated

    Research record

    fda record reviewed

Alternatives

Related tools to compare

FDA-cleared K253825

Saige-Dx

DeepHealth, Inc.

Concurrent detection and characterization support for screening DBT mammography

Modality
Mammography/DBT
Anatomy
Breast
Decision
2026-06-15
Breast imagingDetection and CADe
FDA-cleared K260320

Lunit INSIGHT MMG (v1.1.10)

Lunit, Inc.

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...

Modality
Mammography/DBT
Anatomy
Breast
Decision
2026-04-23
Breast imagingDetection and CADe
FDA-cleared K253796

Lunit INSIGHT DBT (V1.2)

Lunit, Inc.

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...

Modality
Mammography/DBT
Anatomy
Breast
Decision
2026-03-26
Breast imagingDetection and CADe
FDA-cleared K243341

Genius AI Detection 2.0

Hologic, Inc.

Genius AI Detection 2.0 analyzes compatible digital breast tomosynthesis exams to identify and mark soft-tissue densities (masses, architectural distortions, asymmetries) and...

Modality
Mammography/DBT
Anatomy
Breast
Decision
2025-07-31
Breast imagingDetection and CADe