Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends

ABSTRACT The high‐resolution three‐dimensional (3D) images generated with digital breast tomosynthesis (DBT) in the screening of breast cancer offer new possibilities for early disease diagnosis. Early detection is especially important as the incidence of breast cancer increases. However, DBT also p...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruoyun Wang, Fanxuan Chen, Haoman Chen, Chenxing Lin, Jincen Shuai, Yutong Wu, Lixiang Ma, Xiaoqu Hu, Min Wu, Jin Wang, Qi Zhao, Jianwei Shuai, Jingye Pan
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:MedComm
Subjects:
Online Access:https://doi.org/10.1002/mco2.70247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849339913374269440
author Ruoyun Wang
Fanxuan Chen
Haoman Chen
Chenxing Lin
Jincen Shuai
Yutong Wu
Lixiang Ma
Xiaoqu Hu
Min Wu
Jin Wang
Qi Zhao
Jianwei Shuai
Jingye Pan
author_facet Ruoyun Wang
Fanxuan Chen
Haoman Chen
Chenxing Lin
Jincen Shuai
Yutong Wu
Lixiang Ma
Xiaoqu Hu
Min Wu
Jin Wang
Qi Zhao
Jianwei Shuai
Jingye Pan
author_sort Ruoyun Wang
collection DOAJ
description ABSTRACT The high‐resolution three‐dimensional (3D) images generated with digital breast tomosynthesis (DBT) in the screening of breast cancer offer new possibilities for early disease diagnosis. Early detection is especially important as the incidence of breast cancer increases. However, DBT also presents challenges in terms of poorer results for dense breasts, increased false positive rates, slightly higher radiation doses, and increased reading times. Deep learning (DL) has been shown to effectively increase the processing efficiency and diagnostic accuracy of DBT images. This article reviews the application and outlook of DL in DBT‐based breast cancer screening. First, the fundamentals and challenges of DBT technology are introduced. The applications of DL in DBT are then grouped into three categories: diagnostic classification of breast diseases, lesion segmentation and detection, and medical image generation. Additionally, the current public databases for mammography are summarized in detail. Finally, this paper analyzes the main challenges in the application of DL techniques in DBT, such as the lack of public datasets and model training issues, and proposes possible directions for future research, including large language models, multisource domain transfer, and data augmentation, to encourage innovative applications of DL in medical imaging.
format Article
id doaj-art-4e899ff362db437d9054a013e466aa3c
institution Kabale University
issn 2688-2663
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series MedComm
spelling doaj-art-4e899ff362db437d9054a013e466aa3c2025-08-20T03:44:01ZengWileyMedComm2688-26632025-06-0166n/an/a10.1002/mco2.70247Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future TrendsRuoyun Wang0Fanxuan Chen1Haoman Chen2Chenxing Lin3Jincen Shuai4Yutong Wu5Lixiang Ma6Xiaoqu Hu7Min Wu8Jin Wang9Qi Zhao10Jianwei Shuai11Jingye Pan12Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision, and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou ChinaOujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision, and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou ChinaOujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision, and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou ChinaOujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision, and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou ChinaUCSC Baskin School of Engineering University of California Santa Cruz California USAWenzhou Medical University Wenzhou ChinaDepartment of Anatomy Histology & Embryology School of Basic Medical Sciences Fudan University Shanghai ChinaWenzhou Medical University Wenzhou ChinaOujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision, and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou ChinaOujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision, and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou ChinaOujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision, and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou ChinaOujiang Laboratory (Zhejiang Lab for Regenerative Medicine, Vision, and Brain Health) Wenzhou Institute University of Chinese Academy of Sciences Wenzhou ChinaKey Laboratory of Intelligent Treatment and Life Support for Critical Diseases of Zhejiang Province Wenzhou ChinaABSTRACT The high‐resolution three‐dimensional (3D) images generated with digital breast tomosynthesis (DBT) in the screening of breast cancer offer new possibilities for early disease diagnosis. Early detection is especially important as the incidence of breast cancer increases. However, DBT also presents challenges in terms of poorer results for dense breasts, increased false positive rates, slightly higher radiation doses, and increased reading times. Deep learning (DL) has been shown to effectively increase the processing efficiency and diagnostic accuracy of DBT images. This article reviews the application and outlook of DL in DBT‐based breast cancer screening. First, the fundamentals and challenges of DBT technology are introduced. The applications of DL in DBT are then grouped into three categories: diagnostic classification of breast diseases, lesion segmentation and detection, and medical image generation. Additionally, the current public databases for mammography are summarized in detail. Finally, this paper analyzes the main challenges in the application of DL techniques in DBT, such as the lack of public datasets and model training issues, and proposes possible directions for future research, including large language models, multisource domain transfer, and data augmentation, to encourage innovative applications of DL in medical imaging.https://doi.org/10.1002/mco2.70247early breast cancer screeningdigital breast tomosynthesisdeep learningpublic databasemedical image analysis
spellingShingle Ruoyun Wang
Fanxuan Chen
Haoman Chen
Chenxing Lin
Jincen Shuai
Yutong Wu
Lixiang Ma
Xiaoqu Hu
Min Wu
Jin Wang
Qi Zhao
Jianwei Shuai
Jingye Pan
Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends
MedComm
early breast cancer screening
digital breast tomosynthesis
deep learning
public database
medical image analysis
title Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends
title_full Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends
title_fullStr Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends
title_full_unstemmed Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends
title_short Deep Learning in Digital Breast Tomosynthesis: Current Status, Challenges, and Future Trends
title_sort deep learning in digital breast tomosynthesis current status challenges and future trends
topic early breast cancer screening
digital breast tomosynthesis
deep learning
public database
medical image analysis
url https://doi.org/10.1002/mco2.70247
work_keys_str_mv AT ruoyunwang deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT fanxuanchen deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT haomanchen deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT chenxinglin deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT jincenshuai deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT yutongwu deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT lixiangma deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT xiaoquhu deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT minwu deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT jinwang deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT qizhao deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT jianweishuai deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends
AT jingyepan deeplearningindigitalbreasttomosynthesiscurrentstatuschallengesandfuturetrends