DPF-Net: A Dual-Path Progressive Fusion Network for Retinal Vessel Segmentation

doi:10.1109/TIM.2023.3277946

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	DPF-Net: A Dual-Path Progressive Fusion Network for Retinal Vessel Segmentation
	Li, Jianyong 2; Gao, Ge 2; Yang, Lei 1; Bian, Guibin 1,3; Liu, Yanhong 1
刊名	IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
	2023
卷号	72 页码:17
关键词	Feature extraction Image segmentation Retinal vessels Biomedical imaging Blood vessels Convolutional neural networks Task analysis Deep network progressive fusion strategy retinal vessel segmentation semantic segmentation U-shape network
ISSN号	0018-9456
DOI	10.1109/TIM.2023.3277946
通讯作者	Yang, Lei(leiyang2019@zzu.edu.cn)
英文摘要	Precise segmentation of retinal vessels from fundus images is essential for intervention in numerous diseases and is helpful in preventing and treating blindness. Deep convolutional neural network (DCNN)-based approaches have achieved excellent success in the automatic segmentation of retinal vessels. However, a single convolutional neural network (CNN) structure can only capture limited local features and lack the ability to extract global contexts. Meanwhile, the strategies used for the feature fusion of low-level detail information with high-level semantic information fail to handle the phenomenon of the semantic gap issue between the encoder and the decoder validly. Therefore, high-precision segmentation of retinal vessels still remains a challenging task. In this article, a dual-path progressive fusion network, named DPF-Net, is proposed for accurate and end-to-end segmentation of retinal vessels from fundus images. To detect rich feature formation, a dual-path encoder is proposed for effective feature representation, which contains a CNN path for detecting local features and a recurrent convolutional path for extracting contextual information. It could acquire sufficient detailed information and rich contextual information at the same time. In addition, a progressive fusion strategy is proposed for effective feature aggregation at the same scale, adjacent scales, and all scales, which is composed of an interactive fusion (IF) block, a cross-layer fusion (CLF) block, and a scale feature fusion (SFF) block. Combined with the feature maps from different paths at the same scale, an IF block is proposed to fuse detailed features with contextual features to obtain fusion features. Meanwhile, a CLF block is proposed to fuse features between adjacent scales to guide low-level feature representation through high-level features. Finally, an SFF block is proposed to recalculate the weights of all scales to realize effective feature aggregation from all scales. Extensive experiments have been conducted on three publicly available retinal datasets [DRIVE, CHASEDB1, and structured analysis of the retina (STARE)]. Experimental results show that the proposed DPF-Net could achieve better segmentation results compared to other state-of-the-art methods, especially the proposed progressive fusion strategy that indeed promotes feature fusion and significantly boosts the segmentation performance.
资助项目	National Key Research and Development Project of China[2020YFB1313701] ; National Natural Science Foundation of China[62003309] ; Outstanding Foreign Scientist Support Project in Henan Province of China[GZS2019008]
WOS关键词	BLOOD-VESSELS ; MATCHED-FILTER ; IMAGES
WOS研究方向	Engineering ; Instruments & Instrumentation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001018616800009
资助机构	National Key Research and Development Project of China ; National Natural Science Foundation of China ; Outstanding Foreign Scientist Support Project in Henan Province of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53597]
专题	多模态人工智能系统全国重点实验室
通讯作者	Yang, Lei
作者单位	1.Zhengzhou Univ, Sch Elect & Informat Engn, Zhengzhou 450001, Henan, Peoples R China 2.Zhengzhou Univ Light Ind, Coll Comp & Commun Engn, Zhengzhou 450002, Peoples R China 3.Chinese Acad Sci CASIA, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Jianyong,Gao, Ge,Yang, Lei,et al. DPF-Net: A Dual-Path Progressive Fusion Network for Retinal Vessel Segmentation[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2023,72:17.
APA	Li, Jianyong,Gao, Ge,Yang, Lei,Bian, Guibin,&Liu, Yanhong.(2023).DPF-Net: A Dual-Path Progressive Fusion Network for Retinal Vessel Segmentation.IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,72,17.
MLA	Li, Jianyong,et al."DPF-Net: A Dual-Path Progressive Fusion Network for Retinal Vessel Segmentation".IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 72(2023):17.