Abstract The coronavirus disease (COVID‐19) pandemic has led to a devastating effect on the global public health. Computed Tomography (CT) is an effective tool in the screening of COVID‐19. It is of great importance to rapidly and accurately segment COVID‐19 from CT to help diagnostic and patient monitoring. In this paper, we propose a U‐Net based segmentation network using attention mechanism. As not all the features extracted from the encoders are useful for segmentation, we propose to incorporate an attention mechanism including a spatial attention module and a channel attention module, to a U‐Net architecture to re‐weight the feature representation spatially and channel‐wise to capture rich contextual relationships for better feature representation. In addition, the focal Tversky loss is introduced to deal with small lesion segmentation. The experiment results, evaluated on a COVID‐19 CT segmentation dataset where 473 CT slices are available, demonstrate the proposed method can achieve an accurate and rapid segmentation result on COVID‐19. The method takes only 0.29 second to segment a single CT slice. The obtained Dice Score and Hausdorff Distance are 83.1% and 18.8, respectively.

中文翻译：

---

使用 U-Net 集成空间和通道注意机制的自动 COVID-19 CT 分割

摘要 冠状病毒病 (COVID-19) 大流行对全球公共卫生造成了破坏性影响。计算机断层扫描 (CT) 是筛查 COVID-19 的有效工具。从 CT 中快速准确地分割 COVID-19 以帮助诊断和患者监测非常重要。在本文中，我们提出了一种使用注意机制的基于 U-Net 的分割网络。由于并非所有从编码器中提取的特征都对分割有用，我们建议将包括空间注意模块和通道注意模块的注意机制结合到 U-Net 架构中，以在空间和通道方面重新加权特征表示捕获丰富的上下文关系以获得更好的特征表示。此外，还引入了焦点 Tversky 损失来处理小病灶分割。在有 473 个 CT 切片可用的 COVID-19 CT 分割数据集上评估的实验结果表明，所提出的方法可以在 COVID-19 上实现准确快速的分割结果。该方法仅需 0.29 秒即可分割单个 CT 切片。得到的 Dice Score 和 Hausdorff Distance 分别为 83.1% 和 18.8。