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

被引:14
|
作者
Tian, Geng [1 ,2 ]
Wang, Ziwei [1 ]
Wang, Chang [1 ]
Chen, Jianhua [3 ]
Liu, Guangyi [1 ]
Xu, He [1 ]
Lu, Yuankang [1 ]
Han, Zhuoran [4 ]
Zhao, Yubo [5 ]
Li, Zejun [6 ]
Luo, Xueming [1 ]
Peng, Lihong [1 ,7 ]
机构
[1] Hunan Univ Technol, Sch Comp Sci, Zhuzhou, Peoples R China
[2] Geneis Beijing Co Ltd, Beijing, Peoples R China
[3] Hunan Storm Informat Technol Co Ltd, Changsha, Peoples R China
[4] Northeast Normal Univ, High Sch, Changchun, Peoples R China
[5] 2 Middle Sch Shijiazhuang, Shijiazhuang, Peoples R China
[6] Hunan Inst Technol, Sch Comp Sci, Hengyang, Peoples R China
[7] Hunan Univ Technol, Coll Life Sci & Chem, Zhuzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
COVID-19; CT scan image; deep ensemble; Vision Transformer; ConvNeXt;
D O I
10.3389/fmicb.2022.1024104
中图分类号
Q93 [微生物学];
学科分类号
071005 ; 100705 ;
摘要
Since the outbreak of COVID-19, hundreds of millions of people have been infected, causing millions of deaths, and resulting in a 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 the nucleic acid test, lung CT image detection is also a path to quickly identify COVID-19 patients. In this context, 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 combines Vision Transformer and ConvNeXt for COVID-19 CT image 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 the ensemble (Vision Transformer and ConvNeXt) in binary and three-classification experiments. In the 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 the other six models. Equally, in the three-classification experiment, VitCNX computes the best precision of 0.9668, an accuracy of 0.9696, and an F1-score of 0.9631, further demonstrating its excellent image classification capability. We hope our proposed VitCNX model could contribute to the recognition of COVID-19 patients.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Deep Learning-Based COVID-19 Detection Using Lung Parenchyma CT Scans
    Kaya, Zeynep
    Kurt, Zuhal
    Koca, Nizameddin
    Cicek, Sumeyye
    Isik, Sahin
    PROCEEDINGS OF INTERNATIONAL CONFERENCE ON COMPUTING AND COMMUNICATION NETWORKS (ICCCN 2021), 2022, 394 : 261 - 275
  • [2] A Deep Learning Ensemble Approach for Automated COVID-19 Detection from Chest CT Images
    Zazzaro, Gaetano
    Martone, Francesco
    Romano, Gianpaolo
    Pavone, Luigi
    JOURNAL OF CLINICAL MEDICINE, 2021, 10 (24)
  • [3] Deep transfer learning-based automated detection of COVID-19 from lung CT scan slices
    Ahuja, Sakshi
    Panigrahi, Bijaya Ketan
    Dey, Nilanjan
    Rajinikanth, Venkatesan
    Gandhi, Tapan Kumar
    APPLIED INTELLIGENCE, 2021, 51 (01) : 571 - 585
  • [4] Deep transfer learning-based automated detection of COVID-19 from lung CT scan slices
    Sakshi Ahuja
    Bijaya Ketan Panigrahi
    Nilanjan Dey
    Venkatesan Rajinikanth
    Tapan Kumar Gandhi
    Applied Intelligence, 2021, 51 : 571 - 585
  • [5] Deep Ensemble Learning-Based Models for Diagnosis of COVID-19 from Chest CT Images
    Mouhafid, Mohamed
    Salah, Mokhtar
    Yue, Chi
    Xia, Kewen
    HEALTHCARE, 2022, 10 (01)
  • [6] A Deep Learning-based Radiomics Approach for COVID-19 Detection from CXR Images using Ensemble Learning Model
    Costa, Marcus V. L.
    de Aguiar, Erikson J.
    Rodrigues, Lucas S.
    Ramos, Jonathan S.
    Traina, Caetano, Jr.
    Traina, Agma J. M.
    2023 IEEE 36TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS, CBMS, 2023, : 517 - 522
  • [7] Deep learning for COVID-19 detection based on CT images
    Zhao, Wentao
    Jiang, Wei
    Qiu, Xinguo
    SCIENTIFIC REPORTS, 2021, 11 (01)
  • [8] Deep learning for COVID-19 detection based on CT images
    Wentao Zhao
    Wei Jiang
    Xinguo Qiu
    Scientific Reports, 11
  • [9] Vision Transformer Based COVID-19 Detection Using Chest CT-scan images
    Sahoo, Pranab
    Saha, Sriparna
    Mondal, Samrat
    Gowda, Suraj
    2022 IEEE-EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL AND HEALTH INFORMATICS (BHI) JOINTLY ORGANISED WITH THE IEEE-EMBS INTERNATIONAL CONFERENCE ON WEARABLE AND IMPLANTABLE BODY SENSOR NETWORKS (BSN'22), 2022,
  • [10] Classification of COVID-19 Chest CT Images Based on Ensemble Deep Learning
    Li, Xiaoshuo
    Tan, Wenjun
    Liu, Pan
    Zhou, Qinghua
    Yang, Jinzhu
    JOURNAL OF HEALTHCARE ENGINEERING, 2021, 2021 (2021)