AUTHOR=Tian Geng , Wang Ziwei , Wang Chang , Chen Jianhua , Liu Guangyi , Xu He , Lu Yuankang , Han Zhuoran , Zhao Yubo , Li Zejun , Luo Xueming , Peng Lihong 

TITLE=A deep ensemble learning-based automated detection of COVID-19 using lung CT images and Vision Transformer and ConvNeXt

JOURNAL=Frontiers in Microbiology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2022.1024104

DOI=10.3389/fmicb.2022.1024104

ISSN=1664-302X

ABSTRACT=Since the outbreak of COVID-19, hundreds of millions of people have been infected, caused millions losses of life, and result in heavy impact on the daily life of countless people. Accurately identifying patients and taking timely isolation measures are necessary ways to stop the spread of COVID-19. Besides nucleic acid test, lung CT images detection is also a path to quickly identify COVID-19 patients. The deep learning technology can help radiologists identify COVID-19 patients from CT images rapidly. In this paper, we propose a deep learning ensemble framework called VitCNX which combining Vision Transformer and ConvNeXt for COVID-19 CT images identification. We compared our proposed model VitCNX with EfficientNetV2, DenseNet, ResNet-50 and Swin-Transformer which are state-of-the-art deep learning models in the field of image classification, and two individual models which we used for ensemble (Vision Transformer and ConvNeXt) in binary classification and three-classification experiments. In binary classification experiment, VitCNX achieves the best recall of 0.9907, accuracy of 0.9821, F1-score of 0.9855, AUC of 0.9985 and AUPR of 0.9991，which outperforms six other models. While in three-classification experiment, VitCNX computes the best precision of 0.9668, accuracy of 0.9696 and F1-score of 0.9631, further demonstrating its excellent image classification capability. We hope our proposed VitCNX model could contribute to the recognition of the COVID-19 patients.