FDA-cleared profile

BU-CAD

TaiHao Medical Inc. · Mammography/DBT · FDA-cleared (510(k))

Authorized purpose: Assist trained interpreting physicians in analyzing breast-ultrasound images of patients with soft-tissue breast lesions suspicious for cancer who are referred for further diagnostic ultrasound examination.

Clinical role
User-in-the-loop lesion detection and characterization during image review; the user may query or replace ROIs, confirm or modify results, and save the findings to a structured report.
Images and patients
Mammography/DBT · Breast and suspicious soft-tissue breast lesions.
Key limitation
Keep in mind: Do not use on sites of post-surgical excision or images containing Doppler, elastography, or other overlays. It is not intended for primary interpretation of digital mammography or for mobile devices, and patient-management decisions should not rely solely on BU-CAD analysis.

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: Assist trained interpreting physicians in analyzing breast-ultrasound images of patients with soft-tissue breast lesions suspicious for cancer who are referred for further diagnostic ultrasound examination.
  • Which images or clinical context are in scope?Modality: Mammography/DBT Anatomy or clinical context: Breast and suspicious soft-tissue breast lesions. Input: DICOM breast-ultrasound images showing up to two orthogonal views of a single lesion. Ultrasound and full-field digital mammography can also be viewed, but the device is not for primary interpretation of digital mammography.
  • Who uses it?Intended users: Trained interpreting physicians.
  • What does the software produce?Output: ROIs and lesion contours; lesion-characteristics score from 0-100; BI-RADS categories 2, 3, 4a, 4b, 4c, or 5; BI-RADS shape, orientation, margin, echo-pattern, and posterior-feature descriptors; image measurements/documentation; and a structured report.
  • What is its most important limitation?Key limitation: Do not use on sites of post-surgical excision or images containing Doppler, elastography, or other overlays. It is not intended for primary interpretation of digital mammography or for mobile devices, and patient-management decisions should not rely solely on BU-CAD analysis.

Clinical takeaway. Clinical role: Assist trained interpreting physicians in analyzing breast-ultrasound images of patients with soft-tissue breast lesions suspicious for cancer who are referred for further diagnostic ultrasound examination.

Evidence takeaway. Evidence from the reviewed source record: FDA K210670 reports a 628-case retrospective fully crossed MRMC reader study with 16 readers (14 radiologists and 2 breast surgeons), including 456 U.S. and 172 Taiwan cases. Reader AUC_LROC was 0.7786 unaided versus 0.8160 aided, a 0.0374 shift (95% CI 0.0190-0.0557; p=0.0001). Aided-reader sensitivity was 93.53% (95% CI 90.50%-96.55%) and specificity 36.11% (95% CI 31.24%-40.98%). A separate 1,139-case standalone assessment reported AUC_LROC 0.8203; its sensitivity narrative states 88.53%, while Table 9 reports 88.33% (439/497; 95% CI 85.51%-91.15%) with wrong-location penalty, and specificity 57.94% (372/642; 95% CI 54.13%-61.76%). Lesion-identification accuracy 93.24% (1062/1139) used an ROI-center/50%-overlap objective and is not general diagnostic accuracy.

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
Assist trained interpreting physicians in analyzing breast-ultrasound images of patients with soft-tissue breast lesions suspicious for cancer who are referred for further diagnostic ultrasound examination.
  • Exact FDA submission
  • Checked 2026-09-09
Workflow role
User-in-the-loop lesion detection and characterization during image review; the user may query or replace ROIs, confirm or modify results, and save the findings to a structured report.
  • Exact FDA submission
  • Checked 2026-09-09
Required input
DICOM breast-ultrasound images showing up to two orthogonal views of a single lesion. Ultrasound and full-field digital mammography can also be viewed, but the device is not for primary interpretation of digital mammography.
  • Exact FDA submission
  • Checked 2026-09-09
Output and clinician action
ROIs and lesion contours; lesion-characteristics score from 0-100; BI-RADS categories 2, 3, 4a, 4b, 4c, or 5; BI-RADS shape, orientation, margin, echo-pattern, and posterior-feature descriptors; image measurements/documentation; and a structured report.
  • Exact FDA submission
  • Checked 2026-09-09
Care setting
Further diagnostic breast-ultrasound examination and concurrent interpretation workflow; the FDA packet does not specify a facility type.
  • Exact FDA submission
  • Checked 2026-09-09
Intended users
Trained interpreting physicians.
  • Exact FDA submission
  • Checked 2026-09-09
Limitations
Do not use on sites of post-surgical excision or images containing Doppler, elastography, or other overlays. It is not intended for primary interpretation of digital mammography or for mobile devices, and patient-management decisions should not rely solely on BU-CAD analysis.
  • Exact FDA submission
  • Checked 2026-09-09
Evidence summary
FDA K210670 reports a 628-case retrospective fully crossed MRMC reader study with 16 readers (14 radiologists and 2 breast surgeons), including 456 U.S. and 172 Taiwan cases. Reader AUC_LROC was 0.7786 unaided versus 0.8160 aided, a 0.0374 shift (95% CI 0.0190-0.0557; p=0.0001). Aided-reader sensitivity was 93.53% (95% CI 90.50%-96.55%) and specificity 36.11% (95% CI 31.24%-40.98%). A separate 1,139-case standalone assessment reported AUC_LROC 0.8203; its sensitivity narrative states 88.53%, while Table 9 reports 88.33% (439/497; 95% CI 85.51%-91.15%) with wrong-location penalty, and specificity 57.94% (372/642; 95% CI 54.13%-61.76%). Lesion-identification accuracy 93.24% (1062/1139) used an ROI-center/50%-overlap objective and is not general diagnostic accuracy.
  • Exact FDA submission
  • Checked 2026-09-09

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 K210670 reports a 628-case retrospective fully crossed MRMC reader study with 16 readers (14 radiologists and 2 breast surgeons), including 456 U.S. and 172 Taiwan cases. Reader AUC_LROC was 0.7786 unaided versus 0.8160 aided, a 0.0374 shift (95% CI 0.0190-0.0557; p=0.0001). Aided-reader sensitivity was 93.53% (95% CI 90.50%-96.55%) and specificity 36.11% (95% CI 31.24%-40.98%). A separate 1,139-case standalone assessment reported AUC_LROC 0.8203; its sensitivity narrative states 88.53%, while Table 9 reports 88.33% (439/497; 95% CI 85.51%-91.15%) with wrong-location penalty, and specificity 57.94% (372/642; 95% CI 54.13%-61.76%). Lesion-identification accuracy 93.24% (1062/1139) used an ROI-center/50%-overlap objective and is not general diagnostic accuracy.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Reported sensitivity
Standalone BU-CAD sensitivity: FDA narrative 88.53%; Table 9 reports 88.33% (439/497, 95% CI 85.51%-91.15%) with wrong-location penalty. The separate 628-case aided-reader sensitivity was 93.53% (95% CI 90.50%-96.55%).
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09

The FDA packet contains a narrative/table discrepancy and distinct standalone versus aided-reader endpoints; they must not be collapsed into one sensitivity value.

Reported specificity
Standalone BU-CAD specificity: 57.94% (372/642, 95% CI 54.13%-61.76%) with wrong-location penalty. The separate 628-case aided-reader specificity was 36.11% (95% CI 31.24%-40.98%).
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09

This removes the active-row mix of aided specificity and standalone sensitivity and preserves the endpoint, study, and wrong-location context.

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

BU-CAD 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 K210670
  • Samplen=1139
  • IndependenceIndependence not established

K210670

ACR AI Central summarizes the regulatory study; consult the exact FDA materials before comparative use.

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 K210670. 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
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 breast-ultrasound images showing up to two orthogonal views of a single lesion. Ultrasound and full-field digital mammography can also be viewed, but the device is not for primary interpretation of digital mammography.

    Scope: Exact FDA submission.

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

    Field checked 2026-09-09 · FDA K210670: BU-CAD

  2. Routing

    Source context, not route validation: The Viewer loads breast ultrasound and full-field digital mammography images from local storage or PACS; reports may be saved locally or uploaded to PACS, and CAD results can be exported to third-party reporting software. DICOM input/output is described, but exact interface versions and universal PACS/RIS/EHR compatibility are not established.

    Scope: Exact FDA submission.

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

    Field checked 2026-09-09 · FDA K210670: BU-CAD

  3. AI processing

    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 ·

  4. Returned objects

    Source context, not route validation: ROIs and lesion contours; lesion-characteristics score from 0-100; BI-RADS categories 2, 3, 4a, 4b, 4c, or 5; BI-RADS shape, orientation, margin, echo-pattern, and posterior-feature descriptors; image measurements/documentation; and a structured report.

    Scope: Exact FDA submission.

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

    Field checked 2026-09-09 · FDA K210670: BU-CAD

  5. Viewer/worklist/report

    Unresolved route: ROIs and lesion contours; lesion-characteristics score from 0-100; BI-RADS categories 2, 3, 4a, 4b, 4c, or 5; BI-RADS shape, orientation, margin, echo-pattern, and posterior-feature descriptors; image measurements/documentation; and a structured 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 2026-09-09 · FDA K210670: BU-CAD

  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
The Viewer loads breast ultrasound and full-field digital mammography images from local storage or PACS; reports may be saved locally or uploaded to PACS, and CAD results can be exported to third-party reporting software. DICOM input/output is described, but exact interface versions and universal PACS/RIS/EHR compatibility are not established.
  • Exact FDA submission
  • Checked 2026-09-09

Input or output interoperability

DICOM is explicitly referenced in the described input, output, or workflow.

exact submission · checked 2026-09-01

The model card does not establish every supported DICOM object, transfer method, or local interface.

Supported acquisition environment

Scanner manufacturers: All

exact submission · checked 2026-09-01

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

ACR exact-submission catalog context

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

exact submission · checked 2026-09-09
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
K210670
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Modality
Mammography/DBT
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Anatomy
Breast and suspicious soft-tissue breast lesions.
  • FDA source
  • Exact FDA submission
  • Checked 2026-09-09
Clearance type
510(k)
  • FDA source
  • Exact FDA submission
  • Checked 2026-08-31
Decision date
2021-12-21
  • 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.

Exact FDA record reviewedStatus
2026-09-20Last searched
25Fields reviewed
9Source classes checked
3Screened PubMed leads
1Screened trial leads
0Unreviewed FDA recall leads

The refreshed discovery snapshot contains 3 PubMed and 1 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 3 PubMed and 1 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 K210670 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
  • Security: Not verified - checked 2026-09-09 - Exact FDA submission

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

  • 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.

7 sources - 3 history items

Source ledger

  1. FDA K210670: BU-CAD

    U.S. Food and Drug Administration - Published 2021-12-21 - 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. BU-CAD model card (K210670)

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

    Scope: intendedUsers, output, limitations, reportedSensitivity, reportedSpecificity, 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. openFDA exact recall query for K210670

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

    Scope: postmarketSafety

Research history

  1. K210670 FDA decision

    Regulatory record

    510(k)

  2. Source-review record updated

    Research record

    fda record reviewed

  3. Reader overview source-reviewed

    Editorial review

    Source-reviewed editorial overlay

Alternatives

Related tools to compare

FDA-cleared K260714

MammoScreen® (5)

Therapixel

Authorized purpose: Flags calcifications, masses, asymmetries and architectural distortions on compatible FFDM or DBT screening examinations; management must not be based solely on MammoScreen output.

Modality
Mammography/DBT
Anatomy
Breast
Decision
2026-06-26
FDA-cleared K253825

Saige-Dx

DeepHealth, Inc.

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

Modality
Mammography/DBT
Anatomy
Breast
Decision
2026-06-15
FDA-cleared K254131

BAC

DeepHealth, Inc.

Authorized purpose: BAC processes screening FFDM and DBT mammograms to detect the presence or absence of breast arterial calcifications at study and breast level and localize detected calcifications for qualified interpreting-physician review.

Modality
Mammography/DBT
Anatomy
Breast; breast arterial calcifications
Decision
2026-05-21
FDA-cleared K252954

MammoSightAI

Neurocareai, Inc. (Dba Savelife.Ai)

Authorized purpose: Tags screening cases as suspicious or blank to aid worklist prioritization; radiologists must review every examination and it does not mark original images.

Modality
Mammography/DBT
Anatomy
Breast
Decision
2026-05-04

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