FDA-cleared profile

Saige-Dx

DeepHealth, Inc. · Mammography/DBT · FDA-cleared (510(k))

Authorized purpose: Concurrent detection and characterization support for screening DBT mammography

Clinical role
Concurrent detection, localization and diagnostic support
Images and patients
Mammography/DBT · Breast
Key limitation
Keep in mind: Adjunct concurrent interpretation only; physician review remains required. Siemens compatibility and prior-exam processing have distinct validation cohorts and must not be assumed interchangeable across acquisition systems.

Overview status: Source-reviewed overview

Report a correction
Clinical details Purpose, 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: Concurrent detection and characterization support for screening DBT mammography
  • Which images or clinical context are in scope?Modality: Mammography/DBT Anatomy or clinical context: Breast Input: DICOM DBT image stacks and associated FFDM and/or synthetic 2D images from compatible Hologic, GE and Siemens systems; prior-exam processing evaluated for Hologic and GE
  • Who uses it?Intended users: Interpreting physicians qualified to read screening mammography
  • What does the software produce?Output: Finding bounding boxes, Finding Suspicion Level and Case Suspicion Level; DICOM Structured Report for markings and DICOM Secondary Capture summary report
  • What is its most important limitation?Key limitation: Adjunct concurrent interpretation only; physician review remains required. Siemens compatibility and prior-exam processing have distinct validation cohorts and must not be assumed interchangeable across acquisition systems.

Clinical takeaway. Clinical role: Concurrent detection and characterization support for screening DBT mammography

Evidence takeaway. Evidence from the reviewed source record: Two retrospective blinded standalone studies: 2,425 DBT cases (509 Siemens, 514 GE, 1,402 Hologic) and 684 current/prior patients from Hologic and GE. The summary reports successful noninferiority endpoints without usable sensitivity/specificity point estimates.

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
Concurrent detection and characterization support for screening DBT mammography
  • Exact FDA submission
  • Checked 2026-09-05
Workflow role
Concurrent detection, localization and diagnostic support
  • Exact FDA submission
  • Checked 2026-09-05
Required input
DICOM DBT image stacks and associated FFDM and/or synthetic 2D images from compatible Hologic, GE and Siemens systems; prior-exam processing evaluated for Hologic and GE
  • Exact FDA submission
  • Checked 2026-09-05
Output and clinician action
Finding bounding boxes, Finding Suspicion Level and Case Suspicion Level; DICOM Structured Report for markings and DICOM Secondary Capture summary report
  • Exact FDA submission
  • Checked 2026-09-05
Care setting
Adult women undergoing screening mammography
  • Exact FDA submission
  • Checked 2026-09-05
Intended users
Interpreting physicians qualified to read screening mammography
  • Exact FDA submission
  • Checked 2026-09-05
Limitations
Adjunct concurrent interpretation only; physician review remains required. Siemens compatibility and prior-exam processing have distinct validation cohorts and must not be assumed interchangeable across acquisition systems.
  • Exact FDA submission
  • Checked 2026-09-05
Evidence summary
Two retrospective blinded standalone studies: 2,425 DBT cases (509 Siemens, 514 GE, 1,402 Hologic) and 684 current/prior patients from Hologic and GE. The summary reports successful noninferiority endpoints without usable sensitivity/specificity point estimates.
  • Exact FDA submission
  • Checked 2026-09-05

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
Two retrospective blinded standalone studies: 2,425 DBT cases (509 Siemens, 514 GE, 1,402 Hologic) and 684 current/prior patients from Hologic and GE. The summary reports successful noninferiority endpoints without usable sensitivity/specificity point estimates.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Reported sensitivity
Not established in reviewed sources
  • Reviewed sources checked
  • Exact FDA submission
  • Checked 2026-09-05

Submission summary describes noninferiority but does not report a usable exact-version sensitivity estimate with operating point.

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

Exact-version specificity point estimate and operating point were not established in the reviewed summary.

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

K253825 acquisition-system standalone validation

  • DesignRetrospective blinded standalone noninferiority evaluation
  • Population509 Siemens, 514 GE and 1,402 Hologic DBT cases
  • Scopeexact submission
  • Tested versionSaige-Dx in K253825; release number not established
  • Samplen=2425
  • IndependenceIndependence not established

K253825

K253825 prior-exam processing validation

  • DesignRetrospective blinded standalone evaluation
  • PopulationCurrent/prior examinations from Hologic and GE
  • Scopeexact submission
  • Tested versionSaige-Dx prior processing in K253825
  • Samplen=684
  • IndependenceIndependence not established

K253825

Do not add this cohort to the acquisition-system cohort as unique patients without overlap information.

Long-Term Outcomes and Cost-Effectiveness of Artificial Intelligence for Breast Cancer Screening: A Modeling Study

  • DesignMicrosimulation using published screening performance and cost assumptions
  • PopulationSimulated average-risk women screened biennially with DBT at ages 40-74
  • Scopeproduct family
  • Tested versionSaige-Dx family performance from earlier evidence; not K253825 testing
  • IndependenceIndependence not established

PMID:40983310 · doi:10.1016/j.jval.2025.09.005

Modeled lifetime outcomes are not observed clinical outcomes. Economic estimates do not establish a current license price or payer coverage.

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 2026-09-04

No native submission-identifier match was found in the checked openFDA radiology recall snapshot. Product-name, manufacturer, and adverse-event searches remain necessary; this does not establish that no recall or safety report exists.

Pricing & contracts Public price, contract terms, and reimbursement

Price not public here; enter your quote

Not verified: Pricing information is recorded but not verified against a resolving source.

Reimbursement

IT implementation Deployment, 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.

Review Merge, Visage, Sectra, AGFA and IntelePACS context

Integration chain: evidence at each hop

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.

  1. Acquisition/source

    Source context, not route validation: DICOM DBT image stacks and associated FFDM and/or synthetic 2D images from compatible Hologic, GE and Siemens systems; prior-exam processing evaluated for Hologic and GE

    Scope: Exact FDA submission.

    Confirm scanner/model, protocol, series completeness and both software builds.

    Field checked 2026-09-05 · Saige-Dx: K253825 decision and 510(k) summary

  2. Routing

    Source context, not route validation: DICOM input and SR/SC output to the calling imaging workflow

    Scope: Exact FDA submission. Local display of markings and prior retrieval require compatibility testing; this note is site acceptance guidance.

    Name gateways, destinations, transfer rules and failure visibility; a DICOM statement does not prove a route.

    Field checked 2026-09-05 · Saige-Dx: K253825 decision and 510(k) summary

  3. AI processing

    Unresolved route: Not established for the exact route.

    Scope: Exact FDA submission. Exact hosting topology, hardware requirements and contracted PACS integration were not established.

    Confirm processing location, queue ownership, exclusions and exact AI build.

    Field checked 2026-09-05 ·

  4. Returned objects

    Source context, not route validation: Finding bounding boxes, Finding Suspicion Level and Case Suspicion Level; DICOM Structured Report for markings and DICOM Secondary Capture summary report

    Scope: Exact FDA submission.

    Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.

    Field checked 2026-09-05 · Saige-Dx: K253825 decision and 510(k) summary

  5. Viewer/worklist/report

    Unresolved route: Finding bounding boxes, Finding Suspicion Level and Case Suspicion Level; DICOM Structured Report for markings and DICOM Secondary Capture summary report

    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.

    Field checked 2026-09-05 · Saige-Dx: K253825 decision and 510(k) summary

  6. Support owner

    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.

  1. Patient/study identity (planned). Use approved non-patient test data to verify identifiers, accession and result-to-study linkage at every hop.
  2. Study completeness (planned). Test missing views/series, partial transfer, late arrivals, priors and unsupported acquisition inputs; confirm explicit refusal or fallback.
  3. Ordering and duplicates (planned). Send out-of-order, repeated and corrected studies; verify worklist order, deduplication and no misleading stale results.
  4. Report transfer (planned). Verify output object types, annotations, units, report content, destination and availability of original images.
  5. Access (planned). Verify authorized roles, audit trail, denied access and support ownership at each destination.
  6. Latency and failures (planned). Agree a workload and turnaround target; test queues, timeouts, missing results and fallback reading.
  7. 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.

Open the printable evaluation checklist

Integration
DICOM input and SR/SC output to the calling imaging workflow
  • Exact FDA submission
  • Checked 2026-09-05

Local display of markings and prior retrieval require compatibility testing; this note is site acceptance guidance.

Vendor product-family identity

DeepHealth identifies SmartMammo Dx as also known as Saige DX within the multi-component SmartMammo offering

product family · checked 2026-09-06

The 2024 announcement predates K253825; other SmartMammo components and later rebranded products are not automatically capabilities of this submission.

Reading-aid output

DICOM SR markings and SC summary report

exact submission · checked 2026-09-05
Sources & review details FDA 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.

FDA submission
K253825
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Modality
Mammography/DBT
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Anatomy
Breast
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-05
Clearance type
510(k)
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Decision date
2026-06-15
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
FDA status
FDA-cleared
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31

Research record

What has been checked

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

Human reviewedStatus
2026-09-06Last searched
19Fields reviewed
11Source classes checked
1Screened PubMed leads
0Screened trial leads
0Unreviewed FDA recall leads

Stored PubMed candidate reviewed and retained as contextual family economic modeling; no exact-version outcomes or payer coverage promoted. Stored clinical-trial candidate array is empty. The current discovery snapshot contains 1 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, acr ai central product, fda decision summary, vendor product page, literature index, peer reviewed publication, trial registry, recall database, 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 2026-09-06 - Exact FDA submission

    A published family economic model references a consumer screening add-on charge. This does not establish K253825 procurement cost, a current quote or a software-only price.

  • 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 2026-10-26 - Exact FDA submission

    Bounded web search on 2026-10-26 (query: "DeepHealth Saige-Dx reimbursement CPT"; top results reviewed) found no vendor or payer page stating coding, coverage or payment for this product. This records what was found, not that none exists; eligibility depends on payer, site of service and use case.

  • Deployment: Not verified - checked 2026-09-05 - Exact FDA submission

    Exact hosting topology, hardware requirements and contracted PACS integration were not established.

  • 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
  • Security: Not verified - checked 2026-09-05 - Exact FDA submission

    No scoped dated attestation for the Saige-Dx deployment was reviewed.

  • Installation timeline: Not yet reviewed
  • Training: Not verified - checked 2026-09-05 - Exact FDA submission

    Site training, suspicion-score interpretation curriculum and competency assessment remain unestablished.

  • Monitoring: Not verified - checked 2026-09-05 - Exact FDA submission

    Post-deployment false-positive/false-negative auditing and update-specific acceptance requirements remain to be confirmed.

9 sources - 3 history items

Source ledger

  1. K253825 FDA decision source

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

    Scope: regulatoryIdentity, purpose, modality, anatomy

  2. Artificial Intelligence-Enabled Medical Devices

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

    Scope: regulatoryIdentity, modalityContext

  3. Saige-Dx model card (K253825)

    American College of Radiology - Published 2026-08-17 - Accessed 2026-09-01

    Scope: 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. Saige-Dx: K253825 decision and 510(k) summary

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

    Scope: identity, clinical, evidence, implementation

  8. Long-Term Outcomes and Cost-Effectiveness of Artificial Intelligence for Breast Cancer Screening: A Modeling Study

    Value in Health / PubMed - Published 2025-09-20 - Accessed 2026-09-05

    Scope: evidenceStudies, economicEvidence

  9. RadNet's DeepHealth Subsidiary Expands FDA Clearance for SmartMammo Solution

    DeepHealth - Published 2024-11-29 - Accessed 2026-09-06

    Scope: productFamilyIdentity

Research history

  1. K253825 FDA decision

    Regulatory record

    510(k)

  2. Source-review record updated

    Research record

    human reviewed

  3. Reader overview source-reviewed

    Editorial review

    Source-reviewed editorial overlay

Alternatives

Related tools to compare

FDA-cleared K260320

Lunit INSIGHT MMG (v1.1.10)

Lunit, Inc.

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.

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

Lunit INSIGHT DBT (V1.2)

Lunit, Inc.

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.

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

Genius AI Detection 2.0

Hologic, Inc.

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.

Modality
Mammography/DBT
Anatomy
Breast
Decision
2025-07-31
FDA-authorized DEN240047

Allix5

Clairity, Inc.

Authorized purpose: Allix5 generates a five-year breast-cancer-risk prediction from bilateral screening mammograms for eligible patients without known breast cancer at presentation; it is not intended to diagnose or detect cancer, recommend care, or serve as the sole determinant of care.

Modality
Mammography/DBT
Anatomy
Breast
Decision
2025-05-30

Correct this exact record

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 destination

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.

Correction policy and limits · Public repository change history