2783046

Question Can a curated, annotated, and publicly available data set of digital breast tomosynthesis (DBT) volumes be created for the development and validation of breast cancer computer-aided detection algorithms? Findings In this diagnostic study, a curated and annotated data set of DBT studies that contained 22 032 reconstructed DBT volumes from 5060 patients was made publicly available. A deep learning algorithm for breast cancer detection was developed and tested, with a sensitivity of 65% on a test set. Meaning In this study, the publicly available data set, alongside the deep learning model, could significantly advance the research on machine learning tools in breast cancer screening and medical imaging in general. Importance Breast cancer screening is among the most common radiological tasks, with more than 39 million examinations performed each year. While it has been among the most studied medical imaging applications of artificial intelligence, the development and evaluation of algorithms are hindered by the lack of well-annotated, large-scale publicly available data sets. Objectives To curate, annotate, and make publicly available a large-scale data set of digital breast tomosynthesis (DBT) images to facilitate the development and evaluation of artificial intelligence algorithms for breast cancer screening; to develop a baseline deep learning model for breast cancer detection; and to test this model using the data set to serve as a baseline for future research. Design, Setting, and Participants In this diagnostic study, 16 802 DBT examinations with at least 1 reconstruction view available, performed between August 26, 2014, and January 29, 2018, were obtained from Duke Health System and analyzed.