2021
DOI: 10.1002/ima.22544
|View full text |Cite
|
Sign up to set email alerts
|

A deep learning model for mass screening of COVID‐19

Abstract: The objective of this research is to develop a convolutional neural network model ‘COVID‐Screen‐Net’ for multi‐class classification of chest X‐ray images into three classes viz. COVID‐19, bacterial pneumonia, and normal. The model performs the automatic feature extraction from X‐ray images and accurately identifies the features responsible for distinguishing the X‐ray images of different classes. It plots these features on the GradCam. The authors optimized the number of convolution and activation layers accor… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
8
1

Relationship

2
7

Authors

Journals

citations
Cited by 23 publications
(7 citation statements)
references
References 22 publications
0
7
0
Order By: Relevance
“…These features include regional volumes and cortical thickness segmented from brain regions known to be involved/implicated with memory loss and accelerated neurodegeneration that accompany Alzheimer’s disease 17 19 . Newer machine learning methods based on deep convolutional neural networks (CNNs) make it possible to extract features directly from image data in a data-driven fashion 20 26 . These methods have been shown to outperform traditional techniques based on predefined features in most image processing and computer vision tasks 27 , 28 .…”
Section: Introductionmentioning
confidence: 99%
“…These features include regional volumes and cortical thickness segmented from brain regions known to be involved/implicated with memory loss and accelerated neurodegeneration that accompany Alzheimer’s disease 17 19 . Newer machine learning methods based on deep convolutional neural networks (CNNs) make it possible to extract features directly from image data in a data-driven fashion 20 26 . These methods have been shown to outperform traditional techniques based on predefined features in most image processing and computer vision tasks 27 , 28 .…”
Section: Introductionmentioning
confidence: 99%
“…Coronavirus is an animal-origin pathogen that can cause disease in humans [ 31 , 32 ]. A model for phenotype identification of notorious disease is urgently needed to be developed [ 33 , 34 ]. In the paper, we present a deep learning model of cross-species coronavirus infection that combines a one-dimensional convolutional neural network with a bidirectional gated recurrent unit network.…”
Section: Discussionmentioning
confidence: 99%
“…In this section, the authors present the architectures, training parameters, and working of the CNN and LSTM based multi-modal. The multi-modal comprises the ‘GenomeSimilarityPredictor’ and COVID-Screen-Net [ 29 ]. The ‘GenomeSimilarityPredictor’ is applied for the prediction of the genomic similarity of ‘SARS-CoV-2’ with other viruses and the classification of genomes into infected and non-infected.…”
Section: Methodsmentioning
confidence: 99%
“…The ‘GenomeSimilarityPredictor’ is applied for the prediction of the genomic similarity of ‘SARS-CoV-2’ with other viruses and the classification of genomes into infected and non-infected. Whereas, the architecture of COVID-Screen-Net is adopted from the work presented in [ 29 ] to classify the chest radiographs into healthy, bacterial pneumonia, and COVID-19.…”
Section: Methodsmentioning
confidence: 99%