TY - GEN
T1 - 2D Convolutional Neural Networks for 3D Digital Breast Tomosynthesis Classification
AU - Zhang, Yu
AU - Wang, Xiaoqin
AU - Blanton, Hunter
AU - Liang, Gongbo
AU - Xing, Xin
AU - Jacobs, Nathan
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Automated methods for breast cancer detection have focused on 2D mammography and have largely ignored 3D digital breast tomosynthesis (DBT), which is frequently used in clinical practice. The two key challenges in developing automated methods for DBT classification are handling the variable number of slices and retaining slice-to-slice changes. We propose a novel deep 2D convolutional neural network (CNN) architecture for DBT classification that simultaneously overcomes both challenges. Our approach operates on the full volume, regardless of the number of slices, and allows the use of pre-trained 2D CNNs for feature extraction, which is important given the limited amount of annotated training data. In an extensive evaluation on a real-world clinical dataset, our approach achieves 0.854 auROC, which is 28.80% higher than approaches based on 3D CNNs. We also find that these improvements are stable across a range of model configurations.
AB - Automated methods for breast cancer detection have focused on 2D mammography and have largely ignored 3D digital breast tomosynthesis (DBT), which is frequently used in clinical practice. The two key challenges in developing automated methods for DBT classification are handling the variable number of slices and retaining slice-to-slice changes. We propose a novel deep 2D convolutional neural network (CNN) architecture for DBT classification that simultaneously overcomes both challenges. Our approach operates on the full volume, regardless of the number of slices, and allows the use of pre-trained 2D CNNs for feature extraction, which is important given the limited amount of annotated training data. In an extensive evaluation on a real-world clinical dataset, our approach achieves 0.854 auROC, which is 28.80% higher than approaches based on 3D CNNs. We also find that these improvements are stable across a range of model configurations.
KW - Breast Cancer
KW - Convolutional Neural Networks
KW - Full-Field Digital Mammography
KW - Full-Volume Digital Breast Tomosynthesis
UR - https://www.scopus.com/pages/publications/85084332273
U2 - 10.1109/BIBM47256.2019.8983097
DO - 10.1109/BIBM47256.2019.8983097
M3 - Conference contribution
AN - SCOPUS:85084332273
T3 - Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019
SP - 1013
EP - 1017
BT - Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019
A2 - Yoo, Illhoi
A2 - Bi, Jinbo
A2 - Hu, Xiaohua Tony
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019
Y2 - 18 November 2019 through 21 November 2019
ER -