基于多尺度一致性与注意力机制的视网膜血管分割网络

针对现有的视网膜血管分割方法存在对微血管和毛细血管的分割能力不足，导致血管断连和末端血管漏分，造成视网膜血管分割性能不佳的问题，本文提出一种基于多尺度一致性与注意力机制的视网膜血管分割网络(multi-scale consistency and attention mechanism U-Net, MCAU-Net)。首先，该网络在瓶颈特征层嵌入注意力细化模块(attention refinement module, ARM),能有效细化瓶颈层冗余的特征，抑制背景等无关像素的权值。其次，将上下文特征融合模块(context fusion module, CFM)与传统的跳跃连接相结合，以此补充在特征提取过程中逐渐丢失的信息，加强网络对微血管和毛细血管的构建能力。最后，基于网络的多尺度输出设计了一种多尺度一致性的训练方式，以增强网络对不同尺度特征的敏感性。在DRIVE和CHASE＿DB1公开数据集上进行的对比实验表明本文网络具有良好的分割性能。

Retinal vessel segmentation network based on multi-scale consistency and attention mechanism

Due to the limitation of the existing retinal vessel segmentation methods that have insufficient segmentation ability for microvessels and capillaries,which leads to vessel disconnections and end vessel misses,resulting in poor retinal vessel segmentation performance, a multi-scale consistency and attention mechanism U-Net (MCAU-Net) is proposed.Firstly,the network embeds an attention refinement module (ARM) in the bottleneck feature layer,which can effectively refine the redundant features in the bottleneck layer and suppress the weights of irrelevant pixels,such as the background pixels.Moreover,the context fusion module (CFM) is combined with the traditional skip connection as a way to supplement the information gradually lost during the phase of feature extraction and strengthen the network′s ability to construct microvessels and capillaries.Finally,a multi-scale consistent training method is designed based on the multi-scale output of the network to enhance the sensitivity of the network to different scale features.The comparison experiments on DRIVE and CHASE_DB1 public datasets show that the network in this paper has good segmentation performance.