期刊
2019 IEEE 19TH INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOENGINEERING (BIBE)
卷 -, 期 -, 页码 439-444出版社
IEEE
DOI: 10.1109/BIBE.2019.00085
关键词
retinal segmentation; DropBlock; SD-Unet; U-Net; dropout
资金
- China Scholarship Council, China
- Stipendium Hungaricum Scholarship, Hungary
- National Natural Science Foundation of China [61602221, 61672150]
- Scientific Research Fund Project of Liaoning Provincial Department of Education [JYT19040]
- Liaoning Provincial Department of Science and Technology Natural Fund Guidance Program [2019-ZD-0234]
At present, artificial visual diagnosis of fundus diseases has low manual reading efficiency and strong subjectivity, which easily causes false and missed detections. Automatic segmentation of retinal blood vessels in fundus images is very effective for early diagnosis of diseases such as the hypertension and diabetes. In this paper, we utilize the U-shaped structure to exploit the local features of the retinal vessels and perform retinal vessel segmentation in an end-to-end manner. Inspired by the recently DropBlock, we propose a new method called Structured Dropout U-Net (SD-U-net), which abandons the traditional dropout for convolutional layers, and applies the structured dropout to regularize U-Net. Compared to the state-of-the-art methods, we demonstrate the superior performance of the proposed approach.
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