A high resolution representation network with multi-path scale for retinal vessel segmentation. (September 2021)

• Record Type: Journal Article
• Authors: Lin, Zefang; Huang, Jianping; Chen, Yingyin; Zhang, Xiao; Zhao, Wei; Li, Yong; Lu, Ligong; Zhan, Meixiao; Jiang, Xiaofei; Liang, Xiong
• Is Part Of: Computer methods and programs in biomedicine. Volume 208(2021)
• Publication Date: 2021-09
• Subjects: Retinal vessels segmentation -- Deep learning -- High resolution -- Multi-path scale; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106206
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We design an end-to-end network structure, MPS-Net which includes one high resolution main road and two low resolution branch road and performs repeated multi-scale fusions. We propose the multi-path scale module where different multi-scale paths are merged together to grasp much features of retinal image as possible. The range entropy is introduced to quantitatively analyse the effectiveness of the multi-path scale module. The hard-focused cross-entropy loss function is proposed to further improve the segmentation performance. Abstract: Background and objectives: Automatic retinal vessel segmentation (RVS) in fundus images is expected to be a vital step in the early image diagnosis of ophthalmologic diseases. However, it is a challenging task to detect the retinal vessel accurately mainly due to the vascular intricacies, lesion areas and optic disc edges in retinal fundus images. Methods: In this paper, we propose a high resolution representation network with multi-path scale (MPS-Net) for RVS aiming to improve the performance of extracting the retinal blood vessels. In the MPS-Net, there exist one high resolution main road and two lower resolution branch roads where the proposed multi-path scale modules are embedded to enhance the representation ability of network. Besides, in order to guide the network focus on learning the features of hard examples in retinal images, we design a hard-focused cross-entropy loss function. Results: We evaluate our network structure on DRIVE, STARE, CHASE and synthetic images and the quantitative comparisons with respect to the existing methods are presented. The experimental results show that our approach is superior to most methods in terms of F1-score, sensitivity, G-mean and Matthews correlation coefficient. Conclusions: The promising segmentation performances reveal that our method has potential in real-world applications and can be exploited for other medical images with further analysis.