@inbook{1d501e10e4854f26ad68c96a391764a7,
title = "Artificial Intelligence in Breast Imaging",
abstract = "The development and implementation of artificial intelligence (AI) for breast imaging have been ongoing for several decades and have played an important role in clinical practice. With the emergence and maturity of deep learning (DL) algorithms, the application of AI technology in medical imaging has gradually moved to a higher level and broader range. It may break the performance bottleneck of traditional computer-aided detection/diagnosis (CAD) systems. This chapter reviews the three domains of clinical use cases for AI techniques in breast imaging, including risk assessment for screening, breast cancer detection and classification for diagnosis, and therapy selection and outcome prediction for interventions. As for future directions, it is necessary to improve the AI-based system{\textquoteright}s interpretability and performance in a clinical application and maximize its clinical impact.",
author = "Xin Wang and Nikita Moriakov and Yuan Gao and Tianyu Zhang and Luyi Han and Mann, {Ritse M.}",
note = "Publisher Copyright: {\textcopyright} 2022, Springer Nature Switzerland AG.",
year = "2022",
month = jan,
day = "1",
doi = "10.1007/978-3-030-94918-1_20",
language = "English",
series = "Medical radiology",
publisher = "U. S. Joint Publications Research Service",
pages = "435--453",
editor = "Fuchsjager, {Michael } and Morris, {Elizabeth } and Thomas Helbich",
booktitle = "Breast Imaging",
address = "United States",
}