Attention Residual Convolution Neural Network Based on U-Net for COVID-19 Lung Infection Segmentation

In 2021, the COVID-19 is still widespread around the world, whichhas a great impact on people’s daily lives. However, there is still a lack of researchon the fast segmentation of lung infections caused by COVID-19. The segmentationof the COVID-19- infected region from the lung CT is of great significancefor the diagnosis and care of patients. In this paper, attention gate residualU-Net (AGRU-Net) based on residual network and attention gates is proposedfor the segmentation. As COVID-19- infected regions varies greatly from one toanother, the deeper network is needed to extract segmentation features. The residualunit is an effective solution to the degradation problem of deeper network. Theaddition of attention gates to U-Net suppresses irrelevant areas in the image formore significant segmentation characteristics. In this paper, the experiments on apublic COVID-19CT dataset show that AGRU-Net has good performance in thesegmentation of COVID-19- infected region.