A COVID‐19 CXR image recognition method based on MSA‐DDCovidNet

Wang, Wei; Huang, Wendi; Wang, Xin; Zhang, Peng; Zhang, Nian

doi:10.1049/ipr2.12474

Cited by 7 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, the epidemic situation is still spreading all over the world. To some extent, the network proposed in this article can assist medical staff diagnose COVID-19 disease and prevent the continued spread of the epidemic [ 40 ]. In the period of global epidemic outbreak, scholars from all over the world have carried out in-depth research on it and achieved good results.…”

Section: Discussionmentioning

confidence: 99%

Detecting COVID-19 patients via MLES-Net deep learning models from X-Ray images

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background Corona Virus Disease 2019 (COVID-19) first appeared in December 2019, and spread rapidly around the world. COVID-19 is a pneumonia caused by novel coronavirus infection in 2019. COVID-19 is highly infectious and transmissible. By 7 May 2021, the total number of cumulative number of deaths is 3,259,033. In order to diagnose the infected person in time to prevent the spread of the virus, the diagnosis method for COVID-19 is extremely important. To solve the above problems, this paper introduces a Multi-Level Enhanced Sensation module (MLES), and proposes a new convolutional neural network model, MLES-Net, based on this module. Methods Attention has the ability to automatically focus on the key points in various information, and Attention can realize parallelism, which can replace some recurrent neural networks to a certain extent and improve the efficiency of the model. We used the correlation between global and local features to generate the attention mask. First, the feature map was divided into multiple groups, and the initial attention mask was obtained by the dot product of each feature group and the feature after the global pooling. Then the attention masks were normalized. At the same time, there were two scaling and translating parameters in each group so that the normalize operation could be restored. Then, the final attention mask was obtained through the sigmoid function, and the feature of each location in the original feature group was scaled. Meanwhile, we use different classifiers on the network models with different network layers. Results The network uses three classifiers, FC module (fully connected layer), GAP module (global average pooling layer) and GAPFC module (global average pooling layer and fully connected layer), to improve recognition efficiency. GAPFC as a classifier can obtain the best comprehensive effect by comparing the number of parameters, the amount of calculation and the detection accuracy. The experimental results show that the MLES-Net56-GAPFC achieves the best overall accuracy rate (95.27%) and the best recognition rate for COVID-19 category (100%). Conclusions MLES-Net56-GAPFC has good classification ability for the characteristics of high similarity between categories of COVID-19 X-Ray images and low intra-category variability. Considering the factors such as accuracy rate, number of network model parameters and calculation amount, we believe that the MLES-Net56-GAPFC network model has better practicability.

show abstract

Section: Discussionmentioning

confidence: 99%

Detecting COVID-19 patients via MLES-Net deep learning models from X-Ray images

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In comparison to some other methods, the network's structure and model's parameters are particularly heavy and vast, so more processing power is needed to accommodate these factors. Wang et al [42] relied on a lightweight CNN-based multi-scale spatial attention (MSA-DDCovidNet model) to detect COVID-19 and identify the affected lung tissues within patient chest X-ray images. The output feature map from the first DMFF (dual-path multiscale fusion) module is used in MSA-DDCovidNet to create a spatial attention map.…”

Section: Related Workmentioning

confidence: 99%

“…Wang et al. [42] relied on a lightweight CNN‐based multi‐scale spatial attention (MSA‐DDCovidNet model) to detect COVID‐19 and identify the affected lung tissues within patient chest X‐ray images. The output feature map from the first DMFF (dual‐path multi‐scale fusion) module is used in MSA‐DDCovidNet to create a spatial attention map.…”

Section: Related Workmentioning

confidence: 99%

Deep learning‐based COVID‐19 diagnosis using CT scans with laboratory and physiological parameters

Sameer

Mutlag

Gharghan

2023

IET Image Processing

View full text Add to dashboard Cite

The global economy has been dramatically impacted by COVID‐19, which has spread to be a pandemic. COVID‐19 virus affects the respiratory system, causing difficulty breathing in the patient. It is crucial to identify and treat infections as soon as possible. Traditional diagnostic reverse transcription‐polymerase chain reaction (RT‐PCR) methods require more time to find the infection. A high infection rate, slow laboratory analysis, and delayed test results caused the widespread and uncontrolled spread of the disease. This study aims to diagnose the COVID‐19 epidemic by leveraging a modified convolutional neural network (CNN) to quickly and safely predict the disease's appearance from computed tomography (CT) scan images and a laboratory and physiological parameters dataset. A dataset representing 500 patients was used to train, test, and validate the CNN model with results in detecting COVID‐19 having an accuracy, sensitivity, specificity, and F1‐score of 99.33%, 99.09%, 99.52%, and 99.24%, respectively. These experimental results suggest that our strategy performs better than previously published approaches.

show abstract

“…The channel assignment in the parallel network structure can be divided into two types: one is to compress the channel to a specified number by point convolution, and the other is to divide the channel into a specified number by channel split [ 30 ]. Compared with channel split, the method of applying point convolution for channel compression has more parameters.…”

Section: Related Workmentioning

confidence: 99%

“…In order to be able to learn key objects of different sizes within remote-sensing images and use less amount of parameters and calculation, this paper parallelizes equivalent large convolution kernels with local-window selfattention capturing local relations and global feature extraction. e channel assignment in the parallel network structure can be divided into two types: one is to compress the channel to a specified number by point convolution, and the other is to divide the channel into a specified number by channel split [30]. Compared with channel split, the method of applying point convolution for channel compression has more parameters.…”

Section: Transformer Parallel Structurementioning

confidence: 99%

CAW: A Remote-Sensing Scene Classification Network Aided by Local Window Attention

Wang

Wen

Wang

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

Remote-sensing image scene data contain a large number of scene images with different scales. Traditional scene classification algorithms based on convolutional neural networks are difficult to extract complex spatial distribution and texture information in images, resulting in poor classification results. In response to the above problems, we introduce the vision transformer network structure with strong global modeling ability into the remote-sensing image scene classification task. In this paper, the parallel network structure of the local-window self-attention mechanism and the equivalent large convolution kernel is used to realize the spatial-channel modeling of the network so that the network has better local and global feature extraction performance. Experiments on the RSSCN7 dataset and the WHU-RS19 dataset show that the proposed network can improve the accuracy of scene classification. At the same time, the effectiveness of the network structure in remote-sensing image classification tasks is verified through ablation experiments, confusion matrix, and heat map results comparison.

show abstract

A COVID‐19 CXR image recognition method based on MSA‐DDCovidNet

Cited by 7 publications

References 28 publications

Detecting COVID-19 patients via MLES-Net deep learning models from X-Ray images

Detecting COVID-19 patients via MLES-Net deep learning models from X-Ray images

Deep learning‐based COVID‐19 diagnosis using CT scans with laboratory and physiological parameters

CAW: A Remote-Sensing Scene Classification Network Aided by Local Window Attention

Contact Info

Product

Resources

About