MammoScreen

K192854

Therapixel · cleared 2020-03-25 · product code QDQ · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“MammoScreen is a software-only device for aiding interpreting physicians in identifying focal findings suspicious for breast cancer in screening FFDM (full-field digital mammography) acquired with compatible mammography systems.”
Algorithmmedical image processing and machine learning techniques, deep learning modules
source quote (p.10)
“In MammoScreen, a range of medical image processing and machine learning techniques are implemented. The system includes 'deep learning' modules for recognition of suspicious calcifications and soft tissue lesions. These modules are trained with very large databases of biopsy-proven examples of breast cancer and normal tissue.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (2)

Standalone

n=240 images · 1 site(s)

endpoints: ROC AUC; Sensitivity; Specificity; LROC AUC; FROC Sensitivity; Average false marks

standards: IEC 62304 Edition 1.1 2015-06, IEC 62366-1 Edition 1.0 2015-02

Reader study (MRMC)

n=240 cases · 1 site(s)

endpoints: AUC under the ROC curve; Sensitivity; Specificity

standards: IEC 62304 Edition 1.1 2015-06, IEC 62366-1 Edition 1.0 2015-02

Reported performance (14 observations)

sensitivity0.847CI 0.829, 0.864
source quote (p.12)
“Sensitivity 0.847 (0.829, 0.864)”
specificity0.729CI 0.721, 0.737
source quote (p.12)
“Specificity 0.729 (0.721, 0.737)”
aurocas written: “auc”0.883CI 0.873, 0.892
source quote (p.12)
“ROC AUC 0.883 (0.873, 0.892)”
aurocas written: “ROC AUC (Breast level)”0.911CI 0.902, 0.919
source quote (p.13)
“ROC AUC 0.911 (0.902, 0.919)”
sensitivityas written: “Sensitivity (Breast level)”0.823CI 0.805, 0.841
source quote (p.13)
“Sensitivity 0.823 (0.805, 0.841)”
specificityas written: “Specificity (Breast level)”0.844CI 0.839, 0.849
source quote (p.13)
“Specificity 0.844 (0.839, 0.849)”
aurocas written: “LROC AUC (Soft tissue lesions)”0.877CI 0.862, 0.890
source quote (p.15)
“LROC AUC (primary) 0.877 (0.862, 0.890)”
sensitivityas written: “Sensitivity @ MS1 (Soft tissue lesions)”0.962CI 0.951, 0.973
source quote (p.15)
“Sensitivity @ MS1 0.962 (0.951, 0.973)”
specificityas written: “Specificity @ MS1 (Soft tissue lesions)”0.15CI 0.146, 0.155
source quote (p.15)
“Specificity @ MS1 0.150 (0.146, 0.155)”
sensitivityas written: “FROC Sensitivity @ MS1 (Soft tissue lesions)”0.93CI 0.918, 0.940
source quote (p.15)
“FROC Sensitivity @ MS1 0.930 (0.918, 0.940)”
aurocas written: “LROC AUC (Calcifications)”0.942CI 0.928, 0.954
source quote (p.16)
“LROC AUC (primary) 0.942 (0.928, 0.954)”
sensitivityas written: “Sensitivity @ MS1 (Calcifications)”0.978CI 0.964, 0.989
source quote (p.16)
“Sensitivity @ MS1 0.978 (0.964, 0.989)”
specificityas written: “Specificity @ MS1 (Calcifications)”0.619CI 0.613, 0.625
source quote (p.16)
“Specificity @ MS1 0.619 (0.613, 0.625)”
sensitivityas written: “FROC Sensitivity @ MS1 (Calcifications)”0.957CI 0.944, 0.969
source quote (p.16)
“FROC Sensitivity @ MS1 0.957 (0.944, 0.969)”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
5
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K243685 (decision 2025-08-22) from Therapixel for a matching device line ("MammoScreen BD") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K243685

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K243679 (decision 2025-07-03) from Therapixel for a matching device line ("MammoScreen® (4)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K243679

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K241561 (decision 2024-10-02) from Therapixel for a matching device line ("MammoScreen BD") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K241561

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K240301 (decision 2024-08-01) from Therapixel for a matching device line ("MammoScreen® (3)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K240301

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K211541 (decision 2021-11-26) from Therapixel for a matching device line ("MammoScreen 2.0") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K211541

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K192854