Zhao Peng, Zhang Jindi, Fang Weijia, Deng Shuiguang
First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
College of Computer Science and Technology, Zhejiang University, Hangzhou, China.
Front Bioeng Biotechnol. 2020 Jul 3;8:670. doi: 10.3389/fbioe.2020.00670. eCollection 2020.
With the development of medical technology, image semantic segmentation is of great significance for morphological analysis, quantification, and diagnosis of human tissues. However, manual detection and segmentation is a time-consuming task. Especially for biomedical image, only experts are able to identify tissues and mark their contours. In recent years, the development of deep learning has greatly improved the accuracy of computer automatic segmentation. This paper proposes a deep learning image semantic segmentation network named Spatial-Channel Attention U-Net (SCAU-Net) based on current research status of medical image. SCAU-Net has an encoder-decoder-style symmetrical structure integrated with spatial and channel attention as plug-and-play modules. The main idea is to enhance local related features and restrain irrelevant features at the spatial and channel levels. Experiments on the gland dataset GlaS and CRAG show that the proposed SCAU-Net model is superior to the classic U-Net model in image segmentation task, with 1% improvement on Dice score and 1.5% improvement on Jaccard score.
随着医学技术的发展，图像语义分割对于人体组织的形态分析、量化和诊断具有重要意义。然而，手动检测和分割是一项耗时的任务。特别是对于生物医学图像，只有专家才能识别组织并标记其轮廓。近年来，深度学习的发展大大提高了计算机自动分割的准确性。本文基于医学图像的当前研究现状，提出了一种名为空间通道注意力U-Net（SCAU-Net）的深度学习图像语义分割网络。SCAU-Net具有编码器-解码器风格的对称结构，并集成了空间和通道注意力作为即插即用模块。其主要思想是在空间和通道层面增强局部相关特征并抑制无关特征。在腺体数据集GlaS和CRAG上的实验表明，所提出的SCAU-Net模型在图像分割任务中优于经典的U-Net模型，在Dice分数上提高了1%，在Jaccard分数上提高了1.5%。
