Global Transformer and Dual Local Attention Network via Deep-Shallow Hierarchical Feature Fusion for Retinal Vessel Segmentation

Abstract

Clinically, retinal vessel segmentation is a significant step in the diagnosis of fundus diseases. However, recent methods generally neglect the difference of semantic information between deep and shallow features, which fail to capture the global and local characterizations in fundus images simultaneously, resulting in the limited segmentation performance for fine vessels. In this paper, a global transformer and dual local attention network via deep-shallow hierarchical feature fusion (GT-DLA-dsHFF) are investigated to solve the above limitations. First, the global transformer (GT) is developed to integrate the global information in the retinal image, which effectively captures the long-distance dependence between pixels, alleviating the discontinuity of blood vessels in the segmentation results. Second, the dual local attention (DLA), which is constructed using dilated convolutions with varied dilation rates, unsupervised edge detection, and squeeze-excitation block, is proposed to extract local vessel information, consolidating the edge details in the segmentation result. Finally, a novel deepshallow hierarchical feature fusion (dsHFF) algorithm is studied to fuse the features in different scales in the deep learning framework respectively, which can mitigate the attenuation of valid information in the process of feature fusion. We verified the GT-DLA-dsHFF on four typical fundus image datasets. The experimental results demonstrate our GT-DLA-dsHFF achieves superior performance against the current methods and detailed discussions verify the efficacy of the proposed three modules. Segmentation results on diseased images show the robustness of our proposed GT-DLA-dsHFF. Our codes will be available on https://github.com/YangLibuaa/GT-DLA-dsHFF.

Artificial Intelligence-Based Algorithms in Medical Image Scan Segmentation and Intelligent Visual Content Generation—A Concise Overview

“…The image segmentation process can be categorized into semantic segmentation, which involves assigning a label or category to each pixel, instance segmentation, which entails identifying and separating individual objects in an image and assigning a label to each, and panoptic segmentation, which encompasses more complex tasks combining both semantic and instance segmentation methods [83,84]. The application of AI enables increased efficiency and speed of these processes [90]. In Table 1, a comparison of the AI-based algorithms applied in medical image scan segmentation, taking into account the neuron model, the type of neural network, learning rule, and biological plausibility, is shown.…”

A Thangka cultural element classification model based on self-supervised contrastive learning and MS Triplet Attention

“…Le et al[31] propose an improved dual attention module containing a spatial attention submodule that uses bidirectional parallelism, which they plug into the back of the Densenet and use it for pollen classification. et al design a framework, called global transformer (GT) and dual local attention (DLA) network, where DLA is constructed using the dilated convolutions with varied dilation rates, unsupervised edge detection method, and squeeze-excitation block, thus integrating edge details [32].…”

A Cross-Scale Transformer and Triple-View Attention Based Domain-Rectified Transfer Learning for EEG Classification in RSVP Tasks

“…The multi-scale features obtained through cross-scale multihead attention [22] are fused through the concatenation function and the feed-forward network after linear transformation. The formulas for CST to obtain multi-scale temporal features are as follows:…”