Dual Encoding U-Net for Retinal Vessel Segmentation
文献类型:会议论文
作者 | Bo,Wang1,3; Shuang,Qiu3; Huiguang,He1,2,3 |
出版日期 | 2019-10 |
会议日期 | 2019-10-13 |
会议地点 | 中国深圳 |
英文摘要 | Retinal Vessel Segmentation is an essential step for the early diagnosis of eye-related diseases, such as diabetes and hypertension. Segmentation of blood vessels requires both sizeable receptive field and rich spatial information. In this paper, we propose a novel Dual Encoding U-Net (DEU-Net), which have two encoders: a spatial path with large kernel to preserve the spatial information and a context path with multiscale convolution block to capture more semantic information. On the top of the two paths, we introduce a feature fusion module to combine the different level of feature representation. Besides, we apply channel attention to select useful feature map in a skip connection. Furthermore, low-level and high-level prediction are combined in multiscale prediction module for a better accuracy. We evaluated this model on the digital retinal images for vessel extraction (DRIVE) dataset and the child heart and health study (CHASEDB1) dataset. Results show that the proposed DEU-Net model achieved the state-of-the-art retinal vessel segmentation accuracy on both datasets. |
源URL | [http://ir.ia.ac.cn/handle/173211/44913] |
专题 | 类脑智能研究中心_神经计算及脑机交互 |
通讯作者 | Huiguang,He |
作者单位 | 1.the School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences 3.Research Center for Brain-inspired Intelligence and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Bo,Wang,Shuang,Qiu,Huiguang,He. Dual Encoding U-Net for Retinal Vessel Segmentation[C]. 见:. 中国深圳. 2019-10-13. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。