AttentionNet: Learning Where to Focus via Attention Mechanism for Anatomical Segmentation of Whole Breast Ultrasound Images

Hang Li, Jie-Zhi Cheng, Yi-Hong Chou, Jing Qin, Shan Huang, Baiying Lei

Abstract

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.
BibTeX
@inproceedings{li2019attentionnet,
  author = {Hang Li and Jie-Zhi Cheng and Yi-Hong Chou and Jing Qin and Shan Huang and Baiying Lei},
  title = {{AttentionNet: Learning Where to Focus via Attention Mechanism for Anatomical Segmentation of Whole Breast Ultrasound Images}},
  booktitle = {ISBI},
  year = {2019},
  doi = {10.1109/isbi.2019.8759241},
}

Loading related content...

Figure