基于粗糙注意力融合机制与Group Transformer的视网膜血管分割网络

扫码查看

原文链接

万方数据
维普

中文摘要：视网膜血管的形态学变化对早期眼科疾病的诊断具有重要意义，除眼科疾病外，糖尿病、心血管疾病等同样可以通过视网膜血管的形态判别疾病进展。然而，视网膜血管本身具有复杂的组织结构，且易受到光线等因素的影响，对其准确分割并不容易。针对上述问题，提出了一种视网膜血管分割网络。该网络中首先设计了粗糙注意力融合模块(rough attention fusion module，RAFM)，该模块基于粗糙集上下近似理论，利用全局最大池化与全局平均池化对注意力系数进行上下限描述，并串行融合通道注意力机制与空间注意力机制;然后，将粗糙注意力融合模块融入Group Transformer U network(GT U-Net)，构建一种基于粗糙注意力融合机制与Group Transformer的视网膜血管分割网络;最后，基于公开DRIVE彩色眼底图像数据集进行对比实验，该网络结构在测试集上的准确率、F1分数、A UC值分别达到了 0。963 1、0。848 8和0。981 2，与GT U-Net模型相比，F1分数、4UC值分别提升了 0。35％、0。21％;与其他当前主流的视网膜血管分割网络进行对比，具有一定优势。

外文标题：Retinal vessel segmentation network based on rough attention fusion mechanism and Group Transformer

外文摘要：The morphological changes in retinal vessels play a crucial role in the diagnosis of early ophthalmic dis-eases.Beyond eye diseases,conditions such as diabetes and cardiovascular diseases can also be identified through the morphology of retinal vessels.However,retinal vessels possess a complex tissue structure and are easily influenced by factors such as lighting,making their accurate segmentation challenging.To address these issues,a retinal vessel seg-mentation network that initially incorporates a rough attention fusion module(RAFM)is proposed.This module is based on the theory of rough set upper and lower approximations,employing global max pooling and global average pooling to describe the upper and lower bounds of attention coefficients,and sequentially integrates channel attention mechanisms with spatial attention mechanisms.Subsequently,the RAFM is integrated into the Group Transformer U network(GT U-Net),constructing a retinal vessel segmentation network based on the rough attention fusion mecha-nism and Group Transformer.Finally,comparative experiments conducted on the publicly available DRIVE color fun-dus image dataset demonstrate that the network achieves an accuracy,F1 score,and AUC of 0.963 1,0.848 8,and 0.981 2,respectively,on the test set.Compared to the GT U-Net model,theF1score and AUC were improved by 0.35％and 0.21％,respectively;and when compared to other contemporary mainstream retinal vessel segmentation networks,it exhibits certain advantages.

外文关键词：

rough setattention mechanismfundus retinal blood vesselsimage segmentationTransformer

作者：

王海鹏、高自强、董佳俊、胡军、陈奕帆、丁卫平

展开 >

作者单位：

南通大学信息科学技术学院,江苏南通 226019

关键词：

粗糙集注意力机制眼底视网膜血管图像分割 Transformer

基金：

国家自然科学基金面上项目江苏省自然科学基金面上项目江苏省高等学校重大自然科学基金江苏省研究生科研与实践创新计划国家级大学生创新创业训练计划

项目编号：

61976120BK2023133721KJA510004SJCX22_1615202210304030Z

出版年：

2024

DOI：

10.12194/j.ntu.20230306001

南通大学学报(自然科学版)

南通大学

南通大学学报(自然科学版)

影响因子：0.292

ISSN：1673-2340

年,卷(期)：2024.23(1)

参考文献量29