期刊
PHYSICS IN MEDICINE AND BIOLOGY
卷 65, 期 5, 页码 -出版社
IOP Publishing Ltd
DOI: 10.1088/1361-6560/ab5745
关键词
breast cancer; mammogram; segmentation; deep learning
资金
- National Natural Science Foundation of China [61601450, 61871371, 81830056]
- Key-Area Research and Development Program of Guangdong Province [2018B010109009]
- Science and Technology Planning Project of Guangdong Province [2017B020227012]
- Basic Research Program of Shenzhen [JCYJ20180507182400762]
- Youth Innovation Promotion Association Program of Chinese Academy of Sciences [2019351]
- National Nature Science Foundation of China [61903227, 11801313]
- Shandong Provincial Natural Science Foundation [ZR2019QA007]
Mammography is one of the most commonly applied tools for early breast cancer screening. Automatic segmentation of breast masses in mammograms is essential but challenging due to the low signal-to-noise ratio and the wide variety of mass shapes and sizes. Existing methods deal with these challenges mainly by extracting mass-centered image patches manually or automatically. However, manual patch extraction is time-consuming and automatic patch extraction brings errors that could not be compensated in the following segmentation step. In this study, we propose a novel attention-guided dense-upsampling network (AUNet) for accurate breast mass segmentation in whole mammograms directly. In AUNet, we employ an asymmetrical encoder-decoder structure and propose an effective upsampling block, attention-guided dense-upsampling block (AU block). Especially, the AU block is designed to have three merits. Firstly, it compensates the information loss of bilinear upsampling by dense upsampling. Secondly, it designs a more effective method to fuse high- and low-level features. Thirdly, it includes a channel-attention function to highlight rich-information channels. We evaluated the proposed method on two publicly available datasets, CBIS-DDSM and INbreast. Compared to three state-of-the-art fully convolutional networks, AUNet achieved the best performances with an average Dice similarity coefficient of 81.8% for CBIS-DDSM and 79.1% for INbreast.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据