Digital breast tomosynthesis and reading with artificial intelligence.
Authors
Affiliations (11)
Affiliations (11)
- Clinic for Radiology and Reference Center for Mammography Münster, University of Münster Faculty of Medicine, Münster, Germany.
- Dresden-Radebeul, Radiological Site, Radebeul, Germany.
- Unit of General Radiology and Paediatric Radiology, Medical University of Vienna Department of Biomedical Imaging and Image-guided Therapy, Vienna, Austria.
- Diagnostic and Interventional Radiology, Hannover Medical School, Hannover, Germany.
- Diagnostic and Interventional Radiology, University Hospital Tübingen, Tübingen, Germany.
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany.
- Berlin, Reference Centre for Mammography, Berlin, Germany.
- München, Radiological Site, München, Germany.
- Radiology, Friedrich Alexander University Erlangen Nuremberg Faculty of Medicine, Erlangen, Germany.
- Diagnostic and Interventional Radiology, University Hospital Freiburg Department of Radiology, Freiburg, Germany.
- Institute and Polyclinic for Diagnostic and Interventional Radiology, University Hospital Carl Gustav Carus at the Technische Universität Dresden, Dresden, Germany.
Abstract
Digital breast tomosynthesis (DBT) increases sensitivity and specificity compared to digital mammography (DM) in the early detection of breast cancer. The potential of artificial intelligence (AI) for mammographic interpretation resulting in workload reduction is increasingly being reported.Presentation of the current evidence on the efficacy of DBT versus DM in population-based breast cancer screening and its support by AI. Narrative review with topic-led literature search of comparative studies of DBT and DM and review of the use of AI in PubMed from 01/2016 to 09/2025.In 42 international studies, the breast cancer detection rate was significantly higher with DBT + DM (6.4‰) and DBT + synthetic mammography (SM) (7.4‰) than with DM (4.7‰). Concordantly, the randomized TOSYMA study reported a higher invasive breast cancer detection rate with DBT + SM (7.1‰) versus DM (4.8‰) with a lower false-positive recall rate (first round -15.6‰). The positive predictive value (PPV) of recall was - consistent with meta-analyses - higher (+4.9%), as was the reading time. With a smaller number of AI studies on DBT than DM, a DBT meta-analysis reported a higher sensitivity of AI alone (89%) than by readers (78%), with a lower specificity of AI. DBT with AI-assisted reading compared to human reading alone increased the detection rate in a prospective study by +3.8‰ without a marked change in the recall rate (+0.8%).DBT increases breast cancer detection compared to DM with more favorable process parameters. AI reporting strategies can further increase sensitivity and reduce human workload. The influence of DBT and AI on reducing the interval cancer rate as a measure of efficiency has not yet been proven. · DBT implementation in population-based breast cancer screening is being reviewed internationally.. · In case of DM replacement, AI reading concepts will become more important.. · Evidence of the long-term effectiveness of DBT and AI is limited.. · Weigel S, Wunderlich P, Sommer A et al. Digital breast tomosynthesis and reading with artificial intelligence. Rofo 2026; DOI 10.1055/a-2796-5225.