COVID-19 Detection from X-ray Images using Multi-Kernel-Size Spatial-Channel Attention Network

[摘要] A B S T R A C T Novel coronavirus 2019 (COVID-19) has spread rapidly around the world and is threatening the health and lives of people worldwide. Early detection of COVID-19 positive patients and timely isolation of the patients are essential to prevent its spread. Chest X-ray images of COVID-19 patients often show the characteristics of multifocality, bilateral hairy glass turbidity, patchy network turbidity, etc. It is crucial to design a method to automatically identify COVID-19 from chest X-ray images to help diagnosis and prog-nosis. Existing studies for the classification of COVID-19 rarely consider the role of attention mechanisms on the classification of chest X-ray images and fail to capture the cross-channel and cross-spatial interre-lationships in multiple scopes. This paper proposes a multi-kernel-size spatial-channel attention method to detect COVID-19 from chest X-ray images. Our proposed method consists of three stages. The first stage is feature extraction. The second stage contains two parallel multi-kernel-size attention modules: multi-kernel-size spatial attention and multi-kernel-size channel attention. The two modules capture the cross-channel and cross-spatial interrelationships in multiple scopes using multiple 1D and 2D convo-lutional kernels of different sizes to obtain channel and spatial attention feature maps. The third stage is the classification module. We integrate the chest X-ray images from three public datasets: COVID-19 Chest X-ray Dataset Initiative, ActualMed COVID-19 Chest X-ray Dataset Initiative, and COVID-19 radiog-raphy database for evaluation. Experimental results demonstrate that the proposed method improves the performance of COVID-19 detection and achieves an accuracy of 98.2%. (c) 2021 Elsevier Ltd. All rights reserved.

[发布日期] 2021-11-01

[关键词] Deep learning Attention;Coronavirus;X-ray images;Multi-scale