MammoScreen helps radiologists to identify findings on screening mammograms and assess their level of suspicion. MammoScreen® uses a color coded MammoScreen Score™ to provide an at a glance level-of-suspicion scoring for screening mammograms; confirming the lowest and highest scores (the green and red cases, respectively for the lowest and highest suspicion categories), and emphasizing those that require deeper scrutiny (the yellow cases, for the indeterminate category).
Product specifications Information source: Vendor
Last updated: March 5, 2023
Product name MammoScreen®
Company Therapixel
Subspeciality Breast
Modality Mammography
Disease targeted Breast cancer
Key-features Lesion detection and characterization, level-of-suspicion score
Suggested use During: perception aid (prompting all abnormalities/results/heatmaps)
Data characteristics
Population Screening mammography
Input Screening DBT & FFDM, prior images if available
Input format DICOM
Output Visual report with detected and assessed lesions
Output format Web interface or DICOM SC or DICOM SR.
Integration Integration via AI marketplace or distribution platform, Stand-alone webbased
Deployment Cloud-based
Trigger for analysis Automatically, right after the image acquisition
Processing time
Certified, Class IIa , MDD
510(k) cleared, Class II
Market presence
On market since FFDM FDA 05-2020 FFDM CE 12-2020 DBT CE 11-2021 DBT FDA 11-2021
Distribution channels Ferrum Health, Softway Medical, Osimis,, others on demand
Countries present (clinical, non-research use)
Paying clinical customers (institutes)
Research/test users (institutes)
Pricing model Subscription
Based on
Peer reviewed papers on performance

  • Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms (read)

  • Improving Breast Cancer Detection Accuracy of Mammography with the Concurrent Use of an Artificial Intelligence Tool (read)

Non-peer reviewed papers on performance

  • Breast screening and artificial intelligence: an independent evaluation of two different software carried out at Valenciennes hospital (read)

Other relevant papers