TY - GEN
T1 - AttentionNet
T2 - 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
AU - Li, Hang
AU - Cheng, Jie Zhi
AU - Chou, Yi Hong
AU - Qin, Jing
AU - Huang, Shan
AU - Lei, Baiying
N1 - Funding Information:
This work was supported partly by National Key Program of China (2016YFC0104700).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/4
Y1 - 2019/4
N2 - The main challenges of the anatomical segmentation of automated whole breast ultrasound (AWBUS) image are shadow effect, blurred boundary, low contrast and large target. To tackle them, a novel and effective framework named AttentionNet is developed via self-attention mechanism during both feature extraction and up-sampling phase. Specifically, features are firstly extracted based on ResNeXt-50 to explore the information of intra-channels. With the goal of extracting features and utilizing channel information effectively, a module named spatial attention refinement (SAR) is devised using the basic ResNeXt-50 module (a.k.a., ResNeXt-SAR). Then, a weighted up-sampling block (WUB) module for precise pixel localization is designed by introducing high-level semantic concept during up-sampling phase, playing an important role in guiding the low-level features by the category information. The extensive experiments are conducted on AWBUS image for multi-class image segmentation. Our proposed AttentionNet achieves the superior results over the state-of-the-art approaches and may help to assist the calculation of breast density.
AB - The main challenges of the anatomical segmentation of automated whole breast ultrasound (AWBUS) image are shadow effect, blurred boundary, low contrast and large target. To tackle them, a novel and effective framework named AttentionNet is developed via self-attention mechanism during both feature extraction and up-sampling phase. Specifically, features are firstly extracted based on ResNeXt-50 to explore the information of intra-channels. With the goal of extracting features and utilizing channel information effectively, a module named spatial attention refinement (SAR) is devised using the basic ResNeXt-50 module (a.k.a., ResNeXt-SAR). Then, a weighted up-sampling block (WUB) module for precise pixel localization is designed by introducing high-level semantic concept during up-sampling phase, playing an important role in guiding the low-level features by the category information. The extensive experiments are conducted on AWBUS image for multi-class image segmentation. Our proposed AttentionNet achieves the superior results over the state-of-the-art approaches and may help to assist the calculation of breast density.
KW - Automated whole breast ultrasound
KW - Breast segmentation
KW - Deep convolutional neural network
KW - Self-attention mechanism
UR - http://www.scopus.com/inward/record.url?scp=85073909440&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2019.8759241
DO - 10.1109/ISBI.2019.8759241
M3 - Conference article published in proceeding or book
AN - SCOPUS:85073909440
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1078
EP - 1081
BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
PB - IEEE Computer Society
Y2 - 8 April 2019 through 11 April 2019
ER -