SCOAT-Net: A novel network for segmenting COVID-19 lung opacification from CT images. (November 2021)

• Record Type: Journal Article
• Authors: Zhao, Shixuan; Li, Zhidan; Chen, Yang; Zhao, Wei; Xie, Xingzhi; Liu, Jun; Zhao, Di; Li, Yongjie
• Is Part Of: Pattern recognition. Volume 119(2021)
• Publication Date: 2021-11
• Subjects: COVID-19 -- Convolutional neural network -- Segmentation -- Lung opacification -- Attention mechanism; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108109
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a novel spatial- and channel-wise coarse-to-fine attention network (SCOAT-Net) for segmentation of COVID-19 lung opacification from CT images and achieves state-of-the-art performance. We use the attention mechanism so that the neural network can generate attention maps without external region of interest (ROI) supervision, increasing the interpretability of the neural network. The generalization ability and compatibility of the proposed SCOAT-Net are validated on two external datasets, showing that the proposed model has specific data migration capability. Abstract: Automatic segmentation of lung opacification from computed tomography (CT) images shows excellent potential for quickly and accurately quantifying the infection of Coronavirus disease 2019 (COVID-19) and judging the disease development and treatment response. However, some challenges still exist, including the complexity and variability features of the opacity regions, the small difference between the infected and healthy tissues, and the noise of CT images. Due to limited medical resources, it is impractical to obtain a large amount of data in a short time, which further hinders the training of deep learning models. To answer these challenges, we proposed a novel spatial- and channel-wise coarse-to-fine attention network (SCOAT-Net), inspired by the biological vision mechanism, for the segmentation of COVID-19 lung opacification from CT images. With the UNet++ as basic structure, our SCOAT-Net introduces the specially designed spatial-wise and channel-wise attention modules, which serve to collaboratively boost the attention learning of the network and extract the efficient features of the infected opacification regions at the pixel and channel levels. Experiments show that our proposed SCOAT-Net achieves better results compared to several state-of-the-art image segmentation networks and has acceptable generalization ability.