Motivated by the recent advances in medical image segmentation using a fully convolutional network (FCN) called U-Net and its modified variants, we propose a novel improved FCN architecture called RefineU-Net. The proposed RefineU-Net consists of three modules: encoding module (EM), global refinement module (GRM) and local refinement module (LRM). EM is backboned by pretrained VGG-16 using ImageNet. GRM is proposed to generate intermediate layers in the skip connections in U-Net. It progressively upsamples the top side output of EM and fuses the resulted upsampled features with the side outputs of EM at each resolution level. Such fused features combine the global context information in shallow layers and the semantic information in deep layers for global refinement. Subsequently, to facilitate local refinement, LRM is proposed using residual attention gate (RAG) to generate discriminative attentive features to be concatenated with the decoded features in the expansive path of U-Net. Three modules are trained jointly in an end-to-end manner thereby both global and local refinement are performed complementarily. Extensive experiments conducted on four public datasets of polyp and skin lesion segmentation show the superiority of the proposed RefineU-Net to multiple state-of-the-art related methods.

基于使用称为U-Net的全卷积网络（FCN）及其改进的变体的医学图像分割的最新进展，我们提出了一种新颖的改进的FCN体系结构，称为RefineU-Net。拟议的RefineU-Net由三个模块组成：编码模块（EM），全局优化模块（GRM）和局部优化模块（LRM）。EM由使用ImageNet的预训练VGG-16支撑。建议使用GRM在U-Net的跳过连接中生成中间层。它会逐步对EM的顶部输出进行升采样，并在每个分辨率级别上将得到的升采样后的功能与EM的侧输出融合在一起。这种融合的功能将浅层的全局上下文信息和深层的语义信息组合在一起，以进行全局优化。随后，为促进本地优化，提出了使用残差注意门（RAG）生成判别性注意力特征并将其与U-Net扩展路径中的已解码特征连接起来的LRM。以端到端的方式联合培训三个模块，从而全面和局部地进行补充完善。对息肉和皮肤病变分割的四个公共数据集进行的广泛实验表明，所提出的RefineU-Net优于多种最新技术。