MammoScreen® (5)
K260714 · Therapixel · Mammography/DBT · FDA-cleared · FDA decision 2026-06-26
Commercial module/version and current availability require supplier confirmation. FDA record identity does not establish the current offer.
Live profile (may change) · FDA decision sourceClinical fit and evidence limits
Anatomy
Available · Exact FDA submission · Checked 2026-09-05
Breast
Authorized population
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Women undergoing mammography; the indication is screening mammography.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Label age limits
Not established · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
No numerical age bound or explicit all-ages statement in the reviewed labeling sections. Study ages do not establish authorized age limits.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Documented care setting
Not established · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
No explicit constraint transcribed from the reviewed labeling sections. Unknown does not mean unrestricted.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Modality and protocol
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Screening mammograms from compatible FFDM and DBT systems; compatible prior examinations may also be used.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Labeled anatomy
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Breast mammography.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Acquisition constraints
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Requires compatible full-field digital mammography or digital breast tomosynthesis systems; compatible priors are optional.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Exclusions and human review
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Patient management decisions should not be made solely based on MammoScreen 5. The interpreting medical professional remains the sole decision-maker.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Separate study result: Sensitivity at the FDA-reported operating point (percent)
No result in this study context · Reported tested version only, not current offer or local outcome. · Check date not established
No matched endpoint/unit/study-context result is established.
Not directly comparable: matching endpoint, unit and complete study context is not established for the other records. A shared metric name, related brand or sample count is insufficient.
Separate study result: Sensitivity at the FDA-reported operating point (percent)
No result in this study context · Reported tested version only, not current offer or local outcome. · Check date not established
No matched endpoint/unit/study-context result is established.
Not directly comparable: matching endpoint, unit and complete study context is not established for the other records. A shared metric name, related brand or sample count is insufficient.
Separate study result: Exam-based discrimination (AUC)
No result in this study context · Reported tested version only, not current offer or local outcome. · Check date not established
No matched endpoint/unit/study-context result is established.
Not directly comparable: matching endpoint, unit and complete study context is not established for the other records. A shared metric name, related brand or sample count is insufficient.
Separate study result: Exam-based discrimination (AUC)
No result in this study context · Reported tested version only, not current offer or local outcome. · Check date not established
No matched endpoint/unit/study-context result is established.
Not directly comparable: matching endpoint, unit and complete study context is not established for the other records. A shared metric name, related brand or sample count is insufficient.
Purpose
Available · Exact FDA submission · Checked 2026-09-05
Flags calcifications, masses, asymmetries and architectural distortions on compatible FFDM or DBT screening examinations; management must not be based solely on MammoScreen output.
Workflow role
Available · Exact FDA submission · Checked 2026-09-05
Concurrent reading/reporting aid; includes an initial report populated with selected findings.
Required input
Available · Exact FDA submission · Checked 2026-09-05
Compatible GE or Hologic FFDM or DBT screening exams, with optional priors; supplementary XCCM, XCCL and ML views are supported in specified scenarios.
Output and clinician action
Available · Exact FDA submission · Checked 2026-09-05
Finding-, breast- and case-level scores from 1 to 10, locations and finding marks for masses, asymmetries, distortions and calcifications.
Care setting
Available · Exact FDA submission · Checked 2026-09-05
Screening mammography workflow.
Intended users
Available · Exact FDA submission · Checked 2026-09-05
Physicians interpreting screening mammograms.
Limitations
Available · Exact FDA submission · Checked 2026-09-05
Not a standalone diagnostic device and not a substitute for physician review; the MammoScreen 5 algorithm is unchanged from MammoScreen 4.
Evidence summary
Available · Exact FDA submission · Checked 2026-11-12
New MammoScreen 5 standalone non-inferiority testing compared newly introduced scenarios with scenarios already cleared with MammoScreen 4 (9,789 studies). No additional clinical studies were conducted; clinical study results from MammoScreen 3 (K240301) are cited as still applicable.
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.
K260714 · agent source review 2026-11-12 · exact submission
Existing study anchor: MammoScreen 5 standalone performance testing of newly introduced scenarios. Tested version label: MammoScreen 5.
What was tested?
MammoScreen 5 standalone testing evaluated newly introduced image/view and current/prior scenarios. Clinical documentation from MammoScreen 3 was carried forward; no additional clinical study was conducted for this submission.
Source section: 510(k) summary, Non clinical Testing and Clinical Testing
On which cases and versions?
The standalone table reports 9,789 patients/studies with biopsy and follow-up reference classifications. This is not a new 9,789-case version-5 reader trial. The admitted study anchor is MammoScreen 5 standalone testing of newly introduced scenarios; MammoScreen 3 K240301 clinical documentation is a separate carried-forward component.
Source section: 510(k) summary, Non clinical Testing and Clinical Testing
What changed?
The submission states that the algorithm did not change from MammoScreen 4 and reports scenario-level non-inferiority testing. Scenario differences include both positive and negative estimates; no single performance gain is assigned to all scenarios.
Source section: 510(k) summary, Non clinical Testing and Clinical Testing
What does this not establish?
Carryover evidence does not create a new version-5 clinical trial. Ambiguous extracted demographic totals are not converted to percentages. Exact input combinations, downstream recalls and clinical outcomes cannot be inferred from a combined score.
Source section: 510(k) summary, Non clinical Testing and Clinical Testing
Study design, population and missing context
- evidence Role
- Newly introduced scenario standalone evaluation, with clinical documentation carried forward from MammoScreen 3 K240301. These are separate evidence components.
validation · 510(k) summary, Non clinical Testing and Clinical Testing
- design
- Standalone scenario comparisons for MammoScreen 5; no additional clinical studies conducted to support equivalence to MammoScreen 4.
validation · 510(k) summary, Non clinical Testing and Clinical Testing
- setting
- Not established: The reviewed regulatory summary does not establish this field for this study context.
- training Population
- Training/tuning and test data sources were separated; the reviewed table does not provide a complete training cohort description.
training · 510(k) summary, Non clinical Testing and Clinical Testing
- evaluation Population
- The standalone table reports 9,789 patients and 9,789 studies. Earlier MammoScreen 3 clinical-study documentation is cited separately.
validation · 510(k) summary, Non clinical Testing and Clinical Testing
- reference Standard
- Positive cases biopsy-proven; benign cases use biopsy and/or imaging follow-up; negative cases verified by imaging follow-up as described in the table.
validation · 510(k) summary, Non clinical Testing and Clinical Testing
- comparator
- New scenarios compared with reference scenarios previously supported by MammoScreen 4; algorithm described as unchanged from the predecessor.
validation · 510(k) summary, Non clinical Testing and Clinical Testing
- sites
- Not established: The reviewed regulatory summary does not establish this field for this study context.
- scanner Protocol
- FFDM/DBT and prior-exam combinations, supplementary and duplicated views. Exact combination support must be read from the submission, not inferred across all vendors.
validation · 510(k) summary, Non clinical Testing and Clinical Testing
- sample Composition
- The table reports 9,789 studies. Extracted demographic category counts do not provide a consistent complete denominator; no percentages are computed here.
validation · 510(k) summary, Non clinical Testing and Clinical Testing
- sponsor Involvement
- Therapixel submitted the regulatory testing package and carryover clinical documentation. This does not establish independent investigator review.
regulatory summary · 510(k) summary, Non clinical Testing and Clinical Testing
IT implementation and exact system pairings
Deployment
Available · Product family · Checked 2026-09-06
Current family documentation describes a site gateway with cloud computation and an on-premises option available on request.
Integration
Available · Product family · Checked 2026-09-06
Current MammoScreen family documentation describes a site virtual gateway, DICOM Secondary Capture and Structured Report output, and optional EMR/reporting API integration using HL7/FHIR.
Current family documentation, not evidence that every interface or package shipped with the cleared version.
Data hosting location: Not yet reviewed · check date not established
Data retention: Not yet reviewed · check date not established
Documented data use: Not yet reviewed · check date not established
Hardware requirements: Not yet reviewed · check date not established
Network requirements: Not yet reviewed · check date not established
Identity and access: Not yet reviewed · check date not established
Security
Available · Vendor-wide · Checked 2026-10-25
Therapixel's own page says Therapixel and its operations for MammoScreen are ISO/IEC 27001 certified by an independent certification body. The page gives no certificate number, scope statement, issue date or expiry, and the certificate was not read.
Vendor-wide statement, not an independent attestation. It does not establish certificate or report scope for this exact release, expiry, data location, retention, identity and access, or incident-response terms for a deployed configuration. Obtain these from the vendor.
Installation timeline: Not yet reviewed · check date not established
Training
Available · Product family · Checked 2026-09-06
The vendor offers a limited-time pilot with remote installation and training.
Duration, curriculum and applicability to version 5 are not stated.
Monitoring: Not verified · checked 2026-09-06 · No site monitoring or update-acceptance procedure was established.
System: Merge PACS
Not reviewed for this pairing · Scope: product family; geography: Geography not established for this exact pairing · Checked 2026-11-06
AI version: not established; system version: not established Scope: product family; geography: Geography not established for this exact pairing Configuration: Merge describes mammography integrations including Therapixel. The source does not identify MammoScreen 5 and a specific Merge build. Condition: A supplier-family integration statement is context, not qualification of this FDA record or site installation. Local test needed: Obtain the two exact builds, licensed interface and conformance/acceptance evidence from both suppliers. Source review: 2026-11-06 Broader product-family or vendor context. The exact AI release and system build pairing is not reviewed. Installed-system acceptance has not been performed. Public version baseline: 9.5; Public technical document; reviewed 2026-11-06. Highest version listed in Merge's public DICOM index. Regional availability and corrected patch/build need supplier confirmation. The reviewed FDA record identifies affected 9.5 software. Confirm the supplier's correction and exact build before acceptance. Reference baseline only. Installed build and AI compatibility remain to be established.
System: Visage 7: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: Sectra IDS7: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: AGFA Enterprise Imaging: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: IntelePACS: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: GE FFDM/DBT input
Conditional support · Scope: exact submission; geography: United States labeling · Checked 2026-11-06
Conditional support. AI version: MammoScreen 5; system version: not established
Configuration: FDA-labeled FFDM/DBT input from compatible GE equipment; a software build is not identified. Condition: Confirm the precise acquisition model, software, priors and supported scenarios against the release-specific labeling. Local test needed: Route representative labeled exams and verify study identity, findings, reporting and fallback review. Source review: 2026-11-06 Source documentation describes this scope; local installed-system acceptance remains open. Installed-system acceptance has not been performed.
System: Hologic FFDM/DBT input
Conditional support · Scope: exact submission; geography: United States labeling · Checked 2026-11-06
Conditional support. AI version: MammoScreen 5; system version: not established
Configuration: FDA-labeled FFDM/DBT input from compatible Hologic equipment; a software build is not identified. Condition: Confirm the precise acquisition model, software and current/prior image scenarios; do not extend the claim to every Hologic configuration. Local test needed: Test the agreed inputs and exclusions, findings, initial report and retained physician review. Source review: 2026-11-06 Source documentation describes this scope; local installed-system acceptance remains open. Installed-system acceptance has not been performed.
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
Existing route context (at most two)
Broader supplier context
- Not reviewed for this pairing
- AI version: not established; system version: not established
- Scope: product family; geography: Geography not established for this exact pairing
- Configuration: Merge describes mammography integrations including Therapixel. The source does not identify MammoScreen 5 and a specific Merge build.
- Condition: A supplier-family integration statement is context, not qualification of this FDA record or site installation.
- Local test needed: Obtain the two exact builds, licensed interface and conformance/acceptance evidence from both suppliers.
- Source review: 2026-11-06
- Broader product-family or vendor context. The exact AI release and system build pairing is not reviewed.
- Installed-system acceptance has not been performed.
- Public version baseline: 9.5; Public technical document; reviewed 2026-11-06.
- Highest version listed in Merge's public DICOM index. Regional availability and corrected patch/build need supplier confirmation.
- The reviewed FDA record identifies affected 9.5 software. Confirm the supplier's correction and exact build before acceptance.
- Reference baseline only. Installed build and AI compatibility remain to be established.
Merge PACS: AI integration and mammography context · Merge PACS 9.5 DICOM conformance statement · FDA Z-3004-2026: affected Merge 9.5 ultrasound measurements
Scanner/input support
- Conditional support
- AI version: MammoScreen 5; system version: not established
- Scope: exact submission; geography: United States labeling
- Configuration: FDA-labeled FFDM/DBT input from compatible GE equipment; a software build is not identified.
- Condition: Confirm the precise acquisition model, software, priors and supported scenarios against the release-specific labeling.
- Local test needed: Route representative labeled exams and verify study identity, findings, reporting and fallback review.
- Source review: 2026-11-06
- Source documentation describes this scope; local installed-system acceptance remains open.
- Installed-system acceptance has not been performed.
MammoScreen 5: K260714 clearance and 510(k) summary
Acquisition/source
Source context, not route validation: Compatible GE or Hologic FFDM or DBT screening exams, with optional priors; supplementary XCCM, XCCL and ML views are supported in specified scenarios.
Scope: Exact FDA submission.
Confirm scanner/model, protocol, series completeness and both software builds.
Field checked 2026-09-05 · MammoScreen 5: K260714 clearance and 510(k) summary
Routing
Source context, not route validation: Current MammoScreen family documentation describes a site virtual gateway, DICOM Secondary Capture and Structured Report output, and optional EMR/reporting API integration using HL7/FHIR.
Scope: Product family. Current family documentation, not evidence that every interface or package shipped with the cleared version.
Name gateways, destinations, transfer rules and failure visibility; a DICOM statement does not prove a route.
Field checked 2026-09-06 · MammoScreen integration
AI processing
Source context, not route validation: Current family documentation describes a site gateway with cloud computation and an on-premises option available on request.
Scope: Product family.
Confirm processing location, queue ownership, exclusions and exact AI build.
Field checked 2026-09-06 · MammoScreen integration
Returned objects
Source context, not route validation: Finding-, breast- and case-level scores from 1 to 10, locations and finding marks for masses, asymmetries, distortions and calcifications.
Scope: Exact FDA submission.
Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.
Field checked 2026-09-05 · MammoScreen 5: K260714 clearance and 510(k) summary
Viewer/worklist/report
Unresolved route: Finding-, breast- and case-level scores from 1 to 10, locations and finding marks for masses, asymmetries, distortions and calcifications.
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 · MammoScreen 5: K260714 clearance and 510(k) summary
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.
- 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.
Public pricing scope
Not publicly available · Checked 2026-09-06
No public price or contract for MammoScreen 5 was located in the reviewed vendor material.
Fictional quote inputs and gaps
Buyer-entered, not a verified public price · Scope not confirmed · saved not saved
- Offered module
- FICTIONAL scope placeholder, not a supplier offer
- Offered software version
- FICTIONAL release, not mapped to the FDA record
- Country or market
- Not stated
- Currency
- Not stated
- Quote date
- Not stated
- Valid until (if stated)
- Not stated
- Bundle and exclusions
- Not stated
- Volume and pricing basis
- Not stated
- Minimum commitment
- Not stated
- Support terms
- Not stated
- Upgrade terms
- Not stated
- Renewal terms
- Not stated
- Termination terms
- Not stated
- Exit and data handoff
- Not stated
- Conflicting terms or amounts
- Not stated
K260714 buyer-entered cost lines| K260714 · FICTIONAL quote inputs |
|---|
| Cost | Status | Amount | Billed unit | Scope/reason |
|---|
| Base license | Not confirmed | Amount not confirmed | Unit not stated | Not stated |
|---|
| Setup and implementation | Not confirmed | Amount not confirmed | Unit not stated | Not stated |
|---|
| Interfaces and gateways | Not confirmed | Amount not confirmed | Unit not stated | Not stated |
|---|
| Hardware and compute | Not confirmed | Amount not confirmed | Unit not stated | Not stated |
|---|
| Other recurring costs | Not confirmed | Amount not confirmed | Unit not stated | Not stated |
|---|
| Support charges | Not confirmed | Amount not confirmed | Unit not stated | Not stated |
|---|
| Upgrade charges | Not confirmed | Amount not confirmed | Unit not stated | Not stated |
|---|
| Exit and migration charges | Not confirmed | Amount not confirmed | Unit not stated | Not stated |
|---|
Quote issues remain before purchasing review.
- Country or market
- Currency
- Quote date
- Bundle and exclusions
- Volume and pricing basis
- Minimum commitment
- Support terms
- Upgrade terms
- Renewal terms
- Termination terms
- Exit and data handoff
- Exact offer applicability
- Quote/contract conflict check
- Base license: confirm whether charged, included or not applicable
- Setup and implementation: confirm whether charged, included or not applicable
- Interfaces and gateways: confirm whether charged, included or not applicable
- Hardware and compute: confirm whether charged, included or not applicable
- Other recurring costs: confirm whether charged, included or not applicable
- Support charges: confirm whether charged, included or not applicable
- Upgrade charges: confirm whether charged, included or not applicable
- Exit and migration charges: confirm whether charged, included or not applicable
Captured sources
Transpara (2.1.0)
K241831 · ScreenPoint Medical B.V. · Mammography/DBT · FDA-cleared · FDA decision 2024-11-25
Commercial module/version and current availability require supplier confirmation. FDA record identity does not establish the current offer.
Live profile (may change) · FDA decision sourceClinical fit and evidence limits
Anatomy
Available · Exact FDA submission · Checked 2026-09-04
Breast; regions suspicious for cancer on screening mammography and digital breast tomosynthesis
Authorized population
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Women undergoing screening mammography or digital breast tomosynthesis.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Label age limits
Not established · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
No numerical age bound or explicit all-ages statement in the reviewed labeling sections. Study ages do not establish authorized age limits.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Documented care setting
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Healthcare facility or hospital.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Modality and protocol
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Screening FFDM and DBT exams from compatible FFDM and DBT systems.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Labeled anatomy
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Breast mammography.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Acquisition constraints
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Requires compatible FFDM and DBT systems; system compatibility is specific to the exact record.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Exclusions and human review
Source-reviewed label constraint · Exact FDA submission. Public labeling, not patient-level eligibility. · Checked 2026-11-09
Adjunct tool, not a replacement for a physician's own mammogram review. Patient management decisions must not be based solely on Transpara.
Agent transcription of selected public-label constraints, not exhaustive labeling, clinical acceptance, patient-level eligibility or a medical recommendation. Read the original labeling and confirm the exact version and protocol.
Separate study result: Sensitivity at the FDA-reported operating point (percent)
Admitted source result · Reported tested version only, not current offer or local outcome. · Check date not established
FFDM sensitivity at 70% specificity: 97.4 percent. Endpoint: Sensitivity at the FDA-reported operating point. Threshold: not reported. Population: 5,730 FFDM exams, including 750 with biopsy-proven cancer, from a multicenter test set representative of screening and diagnostic breast imaging practice. Sample: 5730. Tested version: Transpara 2.1.0. Confidence interval: 96.3-98.5%.
Not directly comparable: matching endpoint, unit and complete study context is not established for the other records. A shared metric name, related brand or sample count is insufficient.
Separate study result: Sensitivity at the FDA-reported operating point (percent)
Admitted source result · Reported tested version only, not current offer or local outcome. · Check date not established
DBT sensitivity at 70% specificity: 96.9 percent. Endpoint: Sensitivity at the FDA-reported operating point. Threshold: not reported. Population: 4,477 DBT exams, including 600 with biopsy-proven cancer, from a multicenter test set representative of screening and diagnostic breast imaging practice. Sample: 4477. Tested version: Transpara 2.1.0. Confidence interval: 95.5-98.3%.
Not directly comparable: matching endpoint, unit and complete study context is not established for the other records. A shared metric name, related brand or sample count is insufficient.
Separate study result: Exam-based discrimination (AUC)
Admitted source result · Reported tested version only, not current offer or local outcome. · Check date not established
FFDM exam-based AUC: 0.96 AUC. Endpoint: Exam-based discrimination. Threshold: not reported. Population: 5,730 FFDM exams, including 750 with biopsy-proven cancer, from a multicenter test set representative of screening and diagnostic breast imaging practice. Sample: 5730. Tested version: Transpara 2.1.0. Confidence interval: 0.953-0.966.
Not directly comparable: matching endpoint, unit and complete study context is not established for the other records. A shared metric name, related brand or sample count is insufficient.
Separate study result: Exam-based discrimination (AUC)
Admitted source result · Reported tested version only, not current offer or local outcome. · Check date not established
DBT exam-based AUC: 0.955 AUC. Endpoint: Exam-based discrimination. Threshold: not reported. Population: 4,477 DBT exams, including 600 with biopsy-proven cancer, from a multicenter test set representative of screening and diagnostic breast imaging practice. Sample: 4477. Tested version: Transpara 2.1.0. Confidence interval: 0.947-0.963.
Not directly comparable: matching endpoint, unit and complete study context is not established for the other records. A shared metric name, related brand or sample count is insufficient.
Purpose
Available · Exact FDA submission · Checked 2026-09-04
Transpara 2.1.0 is a concurrent reading aid for physicians interpreting screening full-field digital mammography and digital breast tomosynthesis, providing region and examination scores to support review of suspicious breast findings.
Workflow role
Available · Exact FDA submission · Checked 2026-09-04
Concurrent reading aid for screening mammography and DBT interpretation.
Required input
Available · Exact FDA submission · Checked 2026-09-04
DICOM full-field digital mammography and digital breast tomosynthesis examinations from compatible systems.
Output and clinician action
Available · Exact FDA submission · Checked 2026-09-04
DICOM mammography CAD results with marked calcification groups, soft-tissue regions, region scores, and an examination score.
Care setting
Available · Exact FDA submission · Checked 2026-09-04
Healthcare facilities performing screening mammography and digital breast tomosynthesis.
Intended users
Available · Exact FDA submission · Checked 2026-09-04
Physicians qualified to interpret screening mammography and digital breast tomosynthesis.
Limitations
Available · Exact FDA submission · Checked 2026-09-04
The FDA labeling states that the output is not the sole basis for patient management. Use is limited to compatible screening FFDM and DBT and requires physician review; the software does not replace interpretation.
Evidence summary
Available · Exact FDA submission · Checked 2026-09-04
K241831 FDA decision material reports the exact evidence metrics included below for Transpara 2.1.0; values are limited to the stated endpoint, population, and operating point.
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.
K241831 · agent source review 2026-11-12 · exact submission
Existing study anchor: K241831 FDA evidence package for Transpara (2.1.0). Tested version label: Transpara 2.1.0.
What was tested?
Transpara 2.1.0 standalone detection on FFDM and DBT, plus separate temporal-comparison and subgroup analyses.
Source section: 510(k) summary, section 7: Standalone performance tests, Tables 1-8
On which cases and versions?
The main test set had 10,207 exams including 1,350 biopsy-proven cancers, from multiple centers in seven European countries and the US. Prior-exam analyses and manufacturer combinations are separate subgroups.
Source section: 510(k) summary, section 7: Standalone performance tests, Tables 1-8
What changed?
The summary reports non-inferior and superior standalone performance versus Transpara 1.7.2 and improved performance with temporal comparison versus without. Sensitivity depends on operating point and modality; false-positive rates are regions per image in non-cancer exams.
Source section: 510(k) summary, section 7: Standalone performance tests, Tables 1-8
What does this not establish?
Standalone operating-point sensitivity is not an aided-reader outcome or a recall-rate guarantee. Subgroup and overlapping lesion classifications cannot be added. The existing separate literature study is not newly admitted or broadened by this card.
Source section: 510(k) summary, section 7: Standalone performance tests, Tables 1-8
Study design, population and missing context
- evidence Role
- Standalone external-to-development test dataset and separate temporal-comparison analyses, not a reader workflow trial.
validation · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
- design
- Standalone algorithm evaluation against reference classification and the Transpara 1.7.2 predicate; test data not used for algorithm development.
validation · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
- setting
- Multiple clinical centers in seven European countries and the United States; test sources separate from development.
validation · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
- training Population
- Not established: The reviewed regulatory summary does not establish this field for this study context.
- evaluation Population
- 10,207 exams: 5,730 FFDM and 4,477 DBT; 1,350 biopsy-proven cancer exams, 270 benign and 8,587 normal.
validation · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
- reference Standard
- Biopsy-proven cancer; most normal exams had at least one year normal follow-up.
validation · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
- comparator
- Transpara 2.1.0 versus Transpara 1.7.2 for standalone processing; temporal analyses also compare processing with versus without priors.
validation · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
- sites
- Not established: The reviewed regulatory summary does not establish this field for this study context.
- scanner Protocol
- FFDM: Hologic, GE, Philips, Siemens and Fujifilm; DBT: Hologic, Siemens, GE and Fujifilm. Temporal-comparison combinations have a separate, narrower compatibility table.
validation · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
- sample Composition
- Cancer: 1,350/10,207 exams; benign: 270/10,207; normal: 8,587/10,207. Lesion-type and histology categories are not summed across overlapping classifications.
validation · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
- sponsor Involvement
- ScreenPoint submitted the regulatory standalone package. A held-out dataset does not by itself establish investigator independence.
regulatory summary · 510(k) summary, section 7: Standalone performance tests, Tables 1-8
IT implementation and exact system pairings
Deployment
Available · Exact FDA submission · Checked 2026-09-04
The FDA package describes a standalone processing appliance with a third-party workstation interface; current hosting, contracts, availability, security, and site configuration remain unknown.
Integration
Available · Exact FDA submission · Checked 2026-09-04
The FDA package describes DICOM mammography input and CAD output to a workstation, PACS, or RIS through a standalone processing appliance and third-party workstation interface.
Data hosting location: Not yet reviewed · check date not established
Data retention: Not yet reviewed · check date not established
Documented data use: Not yet reviewed · check date not established
Hardware requirements: Not yet reviewed · check date not established
Network requirements: Not yet reviewed · check date not established
Identity and access: Not yet reviewed · check date not established
Security
Available · Vendor-wide · Checked 2026-10-25
ScreenPoint Medical's security reporting page states its security program is aligned with ISO/IEC 27001 and describes a vulnerability reporting channel for Transpara. It states alignment, not certification; no controls are listed. Vendor-wide.
Vendor statement, not an attestation; exact-release scope is not established.
Installation timeline: Not yet reviewed · check date not established
Training
Available · Exact FDA submission · Checked 2026-09-04
Use by physicians qualified to interpret screening mammography and digital breast tomosynthesis. Follow the exact labeling, local training, supervision, and escalation requirements.
Monitoring
Available · Exact FDA submission · Checked 2026-09-04
Monitor labeled population, acquisition quality, exclusions, reviewer overrides, failures, and downstream workflow effects for K241831.
System: Merge PACS: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: Visage 7: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: Sectra IDS7
Not reviewed for this pairing · Scope: product family; geography: Geography not established for this exact pairing · Checked 2026-11-06
AI version: not established; system version: not established Scope: product family; geography: Geography not established for this exact pairing Configuration: Sectra lists Transpara results in IDS7, MG CAD SR/SC, overlays and worklist integration. The compatible PACS version must be confirmed. Condition: The marketplace listing does not bind Transpara 2.1.0 in K241831 to a named IDS7 build. Local test needed: Confirm the AI release, IDS7/Core build, licensed integration and region, then test marks, scores, workflow and failure handling. Source review: 2026-11-06 Broader product-family or vendor context. The exact AI release and system build pairing is not reviewed. Installed-system acceptance has not been performed. Public version baseline: 28.2; Announced version; availability unconfirmed; reviewed 2026-11-06. Sectra's public program names IDS7 28.2 for a December 8, 2026 webinar. This establishes an announced version, not general availability or a site build. The public March 2026 conformance statement covers 28.1. Reference baseline only. Installed build and AI compatibility remain to be established.
System: AGFA Enterprise Imaging: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: IntelePACS: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: GE FFDM/DBT input: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
System: Hologic FFDM/DBT input: Not reviewed for this pairing. Obtain exact AI and installed system builds; local acceptance has not been performed.
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
Existing route context (at most two)
Broader supplier context
- Not reviewed for this pairing
- AI version: not established; system version: not established
- Scope: product family; geography: Geography not established for this exact pairing
- Configuration: Sectra lists Transpara results in IDS7, MG CAD SR/SC, overlays and worklist integration. The compatible PACS version must be confirmed.
- Condition: The marketplace listing does not bind Transpara 2.1.0 in K241831 to a named IDS7 build.
- Local test needed: Confirm the AI release, IDS7/Core build, licensed integration and region, then test marks, scores, workflow and failure handling.
- Source review: 2026-11-06
- Broader product-family or vendor context. The exact AI release and system build pairing is not reviewed.
- Installed-system acceptance has not been performed.
- Public version baseline: 28.2; Announced version; availability unconfirmed; reviewed 2026-11-06.
- Sectra's public program names IDS7 28.2 for a December 8, 2026 webinar. This establishes an announced version, not general availability or a site build. The public March 2026 conformance statement covers 28.1.
- Reference baseline only. Installed build and AI compatibility remain to be established.
Sectra Amplifier Marketplace: Transpara Breast AI · Sectra IDS7 28.2 public webinar program · Sectra Workstation/Core 28.1 conformance, March 2026
Acquisition/source
Source context, not route validation: DICOM full-field digital mammography and digital breast tomosynthesis examinations from compatible systems.
Scope: Exact FDA submission.
Confirm scanner/model, protocol, series completeness and both software builds.
Field checked 2026-09-04 · FDA 510(k) decision material K241831: Transpara (2.1.0)
Routing
Source context, not route validation: The FDA package describes DICOM mammography input and CAD output to a workstation, PACS, or RIS through a standalone processing appliance and third-party workstation interface.
Scope: Exact FDA submission.
Name gateways, destinations, transfer rules and failure visibility; a DICOM statement does not prove a route.
Field checked 2026-09-04 · FDA 510(k) decision material K241831: Transpara (2.1.0)
AI processing
Source context, not route validation: The FDA package describes a standalone processing appliance with a third-party workstation interface; current hosting, contracts, availability, security, and site configuration remain unknown.
Scope: Exact FDA submission.
Confirm processing location, queue ownership, exclusions and exact AI build.
Field checked 2026-09-04 · FDA 510(k) decision material K241831: Transpara (2.1.0)
Returned objects
Source context, not route validation: DICOM mammography CAD results with marked calcification groups, soft-tissue regions, region scores, and an examination score.
Scope: Exact FDA submission.
Confirm object classes, units, references and whether findings, overlays or measurements reach their intended destination.
Field checked 2026-09-04 · FDA 510(k) decision material K241831: Transpara (2.1.0)
Viewer/worklist/report
Unresolved route: DICOM mammography CAD results with marked calcification groups, soft-tissue regions, region scores, and an examination score.
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 2026-09-04 · FDA 510(k) decision material K241831: Transpara (2.1.0)
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.
- 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.
Public pricing scope
Not publicly available · Checked 2026-09-04
No public list price or commercial contract for the exact submission and version was identified.
Fictional quote inputs and gaps
No private quote attached. Offered scope, costs and contract terms remain unconfirmed.
Quote issues remain before purchasing review.
- Offered module
- Offered software version
- Country or market
- Currency
- Quote date
- Bundle and exclusions
- Volume and pricing basis
- Minimum commitment
- Support terms
- Upgrade terms
- Renewal terms
- Termination terms
- Exit and data handoff
- Exact offer applicability
- Quote/contract conflict check
- Base license: confirm whether charged, included or not applicable
- Setup and implementation: confirm whether charged, included or not applicable
- Interfaces and gateways: confirm whether charged, included or not applicable
- Hardware and compute: confirm whether charged, included or not applicable
- Other recurring costs: confirm whether charged, included or not applicable
- Support charges: confirm whether charged, included or not applicable
- Upgrade charges: confirm whether charged, included or not applicable
- Exit and migration charges: confirm whether charged, included or not applicable
Captured sources