HT-Net: A Hybrid Transformer Network for Fundus Vessel Segmentation

Abstract

Doctors usually diagnose a disease by evaluating the pattern of abnormal blood vessels in the fundus. At present, the segmentation of fundus blood vessels based on deep learning has achieved great success, but it still faces the problems of low accuracy and capillary rupture. A good vessel segmentation method can guide the early diagnosis of eye diseases, so we propose a novel hybrid Transformer network (HT-Net) for fundus imaging analysis. HT-Net can improve the vessel segmentation quality by capturing detailed local information and implementing long-range information interactions, and it mainly consists of the following blocks. The feature fusion block (FFB) is embedded in the shallow levels, and FFB enriches the feature space. In addition, the feature refinement block (FRB) is added to the shallow position of the network, which solves the problem of vessel scale change by fusing multi-scale feature information to improve the accuracy of segmentation. Finally, HT-Net’s bottom-level position can capture remote dependencies by combining the Transformer and CNN. We prove the performance of HT-Net on the DRIVE, CHASE_DB1, and STARE datasets. The experiment shows that FFB and FRB can effectively improve the quality of microvessel segmentation by extracting multi-scale information. Embedding efficient self-attention mechanisms in the network can effectively improve the vessel segmentation accuracy. The HT-Net exceeds most existing methods, indicating that it can perform the task of vessel segmentation competently.

CPMF-Net: Multi-Feature Network Based on Collaborative Patches for Retinal Vessel Segmentation

“…In the past decade, accompanied by the rapid development of deep learning, convolutional neural networks (CNNs) have also been widely carried out in the field of image segmentation, including retinal vessel segmentation. Compared with retinal vessel segmentation methods based on classical classifiers such as support vector machine (SVM) and k-nearest neighbor (KNN), the retinal vessel segmentation methods [ 4 , 5 , 6 ] based on convolutional neural network can more effectively extract image features from fundus images. Motivated by the great potential of convolutional neural networks on image segmentation, researchers did a lot of work in this area and proposed quite valuable structures, such as fully convolutional networks (FCNs) [ 7 ].…”

Practical Village Planning Strategy of Different Types of Villages—A Case Study of 38 Villages in Shapingba District, Chongqing

“…As a typical architecture for deep image processing, the vision transformer (ViT) is frequently used for segmentation tasks in OCTA (Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Zhai, Unterthiner, Dehghani, Minderer, Heigold, Gelly et al, 2020). Shi, Li, Zou and Zhang (2023b) proposes an efficient Cross-Fusion transformer to achieve continuous vessel segmentation, addressing issues like vessel discontinuities or missing segments while maintaining linear computational complexity. OCT2Former is a hybrid Transformer-based approach for retinal OCTA vessel segmentation.…”