MammoScreen® 5 is an AI-powered software device that assists radiologists in reading screening mammograms by detecting and scoring suspicious soft-tissue lesions and calcifications. It provides graphical marks and detailed lesion information to support interpretation and is intended to be used alongside a physician's judgment.
MammoScreen® 5 is a concurrent reading and reporting aid for physicians interpreting screening mammograms. It is intended for use with compatible full-field digital mammography and digital breast tomosynthesis systems. It can also use prior compatible exams in analysis. Output includes graphical marks of findings with suspicion scores and lesion characterization (mass/asymmetry, distortion, calcifications) to assist physicians.
MammoScreen 5 is software-only AI medical device using deep learning algorithms trained on large biopsy-proven datasets. It detects and scores suspicious lesions and calcifications in mammograms. The device is compatible with 2D FFDM and 3D DBT images including from GE and Hologic systems, and optionally prior mammograms. It outputs graphical marks, suspicion scores (1-10), lesion type classifications, and location information to assist radiologists.
MammoScreen 5 underwent rigorous non-clinical testing per recognized consensus standards (IEC 62304, IEC 62366-1) covering software lifecycle, integration, verification, hazard evaluation and mitigation. Performance testing demonstrated non-inferior cancer detection accuracy compared to predicate (MammoScreen 4) across various mammography and tomosynthesis scenarios. Clinical validation data from prior MammoScreen versions supports safety and effectiveness; no new clinical studies were conducted. Usability testing from prior versions remains applicable.
No predicate devices specified
Subscribe to join 11k+ 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.