MammoScreen 2.0

K211541

Therapixel · cleared 2021-11-26 · product code QDQ · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.6)

“MammoScreen is a software-only device.”

Algorithmmedical image processing and machine learning techniques, 'deep learning' modules

source quote (p.8)

“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)

Reader study (MRMC)

n=240 cases

endpoints: Area Under the Receiver Operating Characteristic (ROC) Curve (AUC)

standards: IEC 62304:2006/A1:2016, IEC 62366-1:2015+AMD1:2020

Reader study (MRMC)

n=240 cases

endpoints: Area Under the Receiver Operating Characteristic (ROC) Curve (AUC)

standards: IEC 62304:2006/A1:2016, IEC 62366-1:2015+AMD1:2020

Reported performance (4 observations)

aurocas written: “auc”0.84

source quote (p.7)

“The performance of the standalone MammoScreen on DBT (AUC = 0.84) was found to be superior to the average performance of unaided radiologists (AUC = 0.79).”

aurocas written: “AUC (FFDM, Aided)”0.8

source quote (p.7)

“The performance of radiologists taking part in the clinical study was improved when using MammoScreen 2.0, with the average AUC going from 0.77 to 0.80.”

aurocas written: “AUC (FFDM, Standalone)”0.79

source quote (p.7)

“The performance of the standalone MammoScreen on FFDM (AUC = 0.79) was found to be non-inferior to the average performance of unaided radiologists (AUC = 0.77).”

aurocas written: “AUC (DBT, Aided)”0.83

source quote (p.7)

“The performance of radiologists taking part in the clinical study was improved when using MammoScreen 2.0, with the average AUC going from 0.79 to 0.83.”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

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

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).