An Improved COVID-19 Lung X-Ray Image Classification Algorithm Based on ConvNeXt Network

Fuxiang Liu; Chen Zang; Junqi Shi; Weiyu He; Yupeng Liang; Lei Li

doi:10.1142/S0219467824500360

An Improved COVID-19 Lung X-Ray Image Classification Algorithm Based on ConvNeXt Network

Fuxiang Liu, Chen Zang, Junqi Shi, Weiyu He, Yupeng Liang, Lei Li^*

^*Corresponding author for this work

School of Aerospace Engineering

Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

Aiming at the new coronavirus that appeared in 2019, which has caused a large number of infected patients worldwide due to its high contagiousness, in order to detect the source of infection in time and cut off the chain of transmission, we developed a new Chest X-ray (CXR) image classification algorithm with high accuracy, simple operation and fast processing for COVID-19. The algorithm is based on ConvNeXt pure convolutional neural network, we adjusted the network structure and loss function, added some new Data Augmentation methods and introduced attention mechanism. Compared with other classical convolutional neural network classification algorithms such as AlexNet, ResNet-34, ResNet-50, ResNet-101, ConvNeXt-tiny, ConvNeXt-small and ConvNeXt-base, the improved algorithm has better performance on COVID dataset.

Original language	English
Article number	2450036
Journal	International Journal of Image and Graphics
DOIs	https://doi.org/10.1142/S0219467824500360
Publication status	Accepted/In press - 2023

Keywords

COVID-19
Chest X-ray (CXR)
ConvNeXt
attention mechanism
convolutional neural network
image classification

Access to Document

10.1142/S0219467824500360

Cite this

@article{2b944097c1b64f3bb4a89ad86cbb0233,

title = "An Improved COVID-19 Lung X-Ray Image Classification Algorithm Based on ConvNeXt Network",

abstract = "Aiming at the new coronavirus that appeared in 2019, which has caused a large number of infected patients worldwide due to its high contagiousness, in order to detect the source of infection in time and cut off the chain of transmission, we developed a new Chest X-ray (CXR) image classification algorithm with high accuracy, simple operation and fast processing for COVID-19. The algorithm is based on ConvNeXt pure convolutional neural network, we adjusted the network structure and loss function, added some new Data Augmentation methods and introduced attention mechanism. Compared with other classical convolutional neural network classification algorithms such as AlexNet, ResNet-34, ResNet-50, ResNet-101, ConvNeXt-tiny, ConvNeXt-small and ConvNeXt-base, the improved algorithm has better performance on COVID dataset.",

keywords = "COVID-19, Chest X-ray (CXR), ConvNeXt, attention mechanism, convolutional neural network, image classification",

author = "Fuxiang Liu and Chen Zang and Junqi Shi and Weiyu He and Yupeng Liang and Lei Li",

note = "Publisher Copyright: {\textcopyright} 2024 World Scientific Publishing Company.",

year = "2023",

doi = "10.1142/S0219467824500360",

language = "English",

journal = "International Journal of Image and Graphics",

issn = "0219-4678",

publisher = "World Scientific",

}

TY - JOUR

T1 - An Improved COVID-19 Lung X-Ray Image Classification Algorithm Based on ConvNeXt Network

AU - Liu, Fuxiang

AU - Zang, Chen

AU - Shi, Junqi

AU - He, Weiyu

AU - Liang, Yupeng

AU - Li, Lei

PY - 2023

Y1 - 2023

N2 - Aiming at the new coronavirus that appeared in 2019, which has caused a large number of infected patients worldwide due to its high contagiousness, in order to detect the source of infection in time and cut off the chain of transmission, we developed a new Chest X-ray (CXR) image classification algorithm with high accuracy, simple operation and fast processing for COVID-19. The algorithm is based on ConvNeXt pure convolutional neural network, we adjusted the network structure and loss function, added some new Data Augmentation methods and introduced attention mechanism. Compared with other classical convolutional neural network classification algorithms such as AlexNet, ResNet-34, ResNet-50, ResNet-101, ConvNeXt-tiny, ConvNeXt-small and ConvNeXt-base, the improved algorithm has better performance on COVID dataset.

AB - Aiming at the new coronavirus that appeared in 2019, which has caused a large number of infected patients worldwide due to its high contagiousness, in order to detect the source of infection in time and cut off the chain of transmission, we developed a new Chest X-ray (CXR) image classification algorithm with high accuracy, simple operation and fast processing for COVID-19. The algorithm is based on ConvNeXt pure convolutional neural network, we adjusted the network structure and loss function, added some new Data Augmentation methods and introduced attention mechanism. Compared with other classical convolutional neural network classification algorithms such as AlexNet, ResNet-34, ResNet-50, ResNet-101, ConvNeXt-tiny, ConvNeXt-small and ConvNeXt-base, the improved algorithm has better performance on COVID dataset.

KW - COVID-19

KW - Chest X-ray (CXR)

KW - ConvNeXt

KW - attention mechanism

KW - convolutional neural network

KW - image classification

UR - http://www.scopus.com/inward/record.url?scp=85163685715&partnerID=8YFLogxK

U2 - 10.1142/S0219467824500360

DO - 10.1142/S0219467824500360

M3 - Article

AN - SCOPUS:85163685715

SN - 0219-4678

JO - International Journal of Image and Graphics

JF - International Journal of Image and Graphics

M1 - 2450036

ER -

An Improved COVID-19 Lung X-Ray Image Classification Algorithm Based on ConvNeXt Network

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this