Deep Learning-Based Approach for Diagnosis of COVID-19 Patients from CT Lung Images ☆

COVID-19 is currently one of the most life-threatening problems around the world. The fast and accurate detection of the COVID-19 infection plays an important role in identifying, making better decisions as well as ensuring treatment for the patients. In this study, we propose an approach to identify COVID-19 patients via deep learning methods. The proposed approach includes two steps: segmentation of lung and classification of patients via analyzing the segmented images. Especially, in the first step, the attention gate is integrated into Unet neural network structure, which can help increase the accuracy of the segmentation tasks. In the second step, the EfficientNet-B4 is applied to classify COVID-19 patients. By using EfficientNet, the performance of the classification process as well as the size of the model are improved. We apply the proposed approach for the database including 130 patients. Experimental results show the desired performances of the proposed approach.