MammoScreen BD is an AI-powered software that helps radiologists evaluate breast tissue density in mammograms and digital breast tomosynthesis. It provides breast density categories based on established ACR BI-RADS standards. The tool offers supplementary information to aid radiologists in assessing breast density, supporting better screening decisions for women aged 40 and older. It processes DICOM images and integrates with clinical systems to assist interpretation without replacing physician judgment.
MammoScreen BD is a software application intended for use with compatible full field digital mammography and digital breast tomosynthesis systems, providing ACR BI-RADS 5th Edition breast density category assessment in asymptomatic women aged 40 and older undergoing screening mammography.
MammoScreen BD is a software-only medical device using AI deep learning algorithms to analyze mammograms and tomosynthesis images to output breast density classification per ACR BI-RADS 5th Edition, operating on DICOM image inputs and delivering results in JSON format or DICOM Structured Reports compatible with clinical PACS and reporting software.
Performance testing on retrospective mammography datasets (922 exams from U.S. and France sites) measured accuracy, agreement with radiologist consensus, and reproducibility across imaging views and modalities, achieving high weighted Cohen's kappa scores (~89 for four-category and ~84.5 for binary breast density classification). Subgroup analyses by image modality, patient age, breast thickness, and race showed consistent performance without bias. The software complies with IEC 62304 lifecycle standards and demonstrated non-inferiority to predicate device.
No predicate devices specified
Submission
5/31/2024
FDA Approval
10/2/2024
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.