文献类型：会议论文

英文题名：Multi-MedVit: a deep learning approach for the diagnosis of COVID-19 with the CT images

作者：Cai, Yunjie[1,2];Zheng, Zeqi[1];Nie, Shanling[1];Guo, Yue[1];Zhang, Ruijie[3];Yang, Hai[1]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Key Lab Comp Software Evaluating & Testi, Shanghai, Peoples R China;[3]Univ Southampton, Sch Elect & Comp Sci, Southampton, Hants, England

会议论文集：2022 International Conference on Bioinformatics and Biomedicine-BIBM-Annual

会议日期：DEC 06-08, 2022

会议地点：Las Vegas, NV

语种：英文

外文关键词：COVID-19; CT; image classification; Transformer; ViT

摘要：The grim situation of novel coronavirus pneumonia 2019 (COVID-19) and its terrible spreading speed have already constituted a severe risk to human life, so it is ultimately essential to rapidly and accurately diagnose for COVID-19 pneumonia. Based on this study's 746 lung CT images, we propose Multi-MedVit, a novel auxiliary COVID-19 diagnosis framework based on the multi-input Transformer. We compare Multi-MedVit with state-of-the-art deep learning methods, such as CNN, VGG16, and ResNet50. Multi-MedVit outperformed the other methods on the benchmark dataset and proved that multiscale data input for data augmentation helped enhance model stability. Based on an interpretable analysis of the input and output of Multi-MedVit, we found that with the support of the training set data, the model has been possible to accurately focus on the lesion area for diagnosis of COVID-19 without expert annotations, which can provide initial references containing more potential information to doctors more precisely and fleetly.