Hybrid dilation and attention residual U-Net for medical image segmentation

Abstract

Medical image segmentation is a typical task in medical image processing and critical foundation in medical image analysis. U-Net is well-liked in medical image segmentation, but it doesn't fully explore useful features of the channel and capitalize on the contextual information. Therefore, we present an improved U-Net with residual connections, adding a plug-and-play, very portable channel attention (CA) block and a hybrid dilated attention convolutional (HDAC) layer to perform medical image segmentation for different tasks accurately and effectively, and call it HDA-ResUNet, in which we fully utilize advantages of U-Net, attention mechanism and dilated convolution. In contrast to the simple copy splicing of U-Net in the skip connection, the channel attention block is inserted into the extracted feature map of the encoding path before decoding operation. Since this block is lightweight, we can apply it to multiple layers in the backbone network to optimize the channel effect of this layer's coding operation. In addition, the convolutional layer at the bottom of the “U"-shaped network is replaced by a hybrid dilated attention convolutional (HDAC) layer to fuse information from different sizes of receptive fields. The proposed HDA-ResUNet is evaluated on four datasets: liver and tumor segmentation (LiTS 2017), lung segmentation (Lung dataset), nuclear segmentation in microscope images (DSB 2018) and neuron structure segmentation (ISBI 2012). The dice global scores of liver and tumor segmentation (LiTS 2017) reach 0.949 and 0.799. The dice coefficients of lung segmentation and nuclear segmentation are 0.9797 and 0.9081 respectively, and the information theoretic score for the last one is 0.9703. The segmentation results are all more accurate than U-Net with fewer parameters, and the problem of slow convergence speed of U-Net on DBS 2018 is solved.