Attention-inception-based U-Net for retinal vessel segmentation with advanced residual
Attention-inception-based U-Net for retinal vessel segmentation with advanced residual
复制标题
基于注意力感知的 U-Net，用于具有高级残差的视网膜血管分割
DOI：
10.1016/j.compeleceng.2021.107670
复制
发表时间：
2022-01-06
影响因子：
4.3
通讯作者：
Luo, Xiaonan
中科院分区：
文献类型：
--
作者：
Wang, Huadeng;Xu, Guang;Luo, Xiaonan
基于 U-Net 的方法已广泛应用于视网膜血管分割任务。但仍有一些障碍需要跨越，例如血管末端微血管细节的丢失，以及病变产生的硬渗出物的干扰。为了解决这些问题，本文提出了一种新颖的 AR-SA U-Net 模型，该模型将残差块与扩张卷积、初始模块和基于 scSE 的注意力机制集成在一起。该模型还通过结合双线性插值和转置卷积来动态更新其权重，从而优化了原始 U-Net 的上采样。在三个视网膜血管图像数据集上的实验结果表明，该模型能够消除病变产生的硬性渗出物对分割结果的影响，分割结果细节清晰、性能较高。所提出的模型在DRIVE、STARE和CHASE_DB1上的准确率分别为96.11%、97.78%和96.79%，比原始U-Net提高了1.07%、1.06%和1.29%。所提出的模型在非眼底医学图像数据集中也表现出很强的泛化能力。
U-Net based methods have been widely used in retinal vessel segmentation tasks. But there are still some obstacles needing to be crossed, such as the loss of microvasculature details at the end of vessels, as well as the interference of the hard exudate produced by lesions. To address these issues, this paper proposes a novel AR-SA U-Net model that integrates residual block with dilated convolution, inception module and an scSE-based attention mechanism. The model also optimizes the upsampling of original U-Net by combining bilinear interpolation and transpose convolution to update their weights dynamically. The experimental results on three retinal vessel image datasets show that the proposed model can eliminate the influence of hard exudate produced by the lesions in the segmentation results, and the segmentation results are clear in detail with high performance. The accuracy of the proposed model on DRIVE, STARE and CHASE_DB1 is 96.11%, 97.78% and 96.79% respectively, which is 1.07%, 1.06% and 1.29% higher than that of original U-Net. The proposed model also shows strong generalization ability in non-fundus medical image datasets.