COVID-WideNet—A capsule network for COVID-19 detection

Gupta, Praveen; Siddiqui, Mohammad Khubeb; Huang, Xiaodi; Panwar, Harsh; Terashima-Marín, Hugo; Wajid, Mohammad Saif

doi:10.1016/j.asoc.2022.108780

Cited by 29 publications

(11 citation statements)

References 47 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following section presents four novel approaches for detecting and controlling the spread of the COVID-19 pandemic [18][19][20]22 . Tai et al 18 presented a novel approach based on the extended reality and the internet of medical things technology for the telemedicine diagnostic of COVID-19.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid deep learning approach for COVID-19 detection based on genomic image processing techniques

Hammad

Ghoneim

Mabrouk

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) pandemic has been spreading quickly, threatening the public health system. Consequently, positive COVID-19 cases must be rapidly detected and treated. Automatic detection systems are essential for controlling the COVID-19 pandemic. Molecular techniques and medical imaging scans are among the most effective approaches for detecting COVID-19. Although these approaches are crucial for controlling the COVID-19 pandemic, they have certain limitations. This study proposes an effective hybrid approach based on genomic image processing (GIP) techniques to rapidly detect COVID-19 while avoiding the limitations of traditional detection techniques, using whole and partial genome sequences of human coronavirus (HCoV) diseases. In this work, the GIP techniques convert the genome sequences of HCoVs into genomic grayscale images using a genomic image mapping technique known as the frequency chaos game representation. Then, the pre-trained convolution neural network, AlexNet, is used to extract deep features from these images using the last convolution (conv5) and second fully-connected (fc7) layers. The most significant features were obtained by removing the redundant ones using the ReliefF and least absolute shrinkage and selection operator (LASSO) algorithms. These features are then passed to two classifiers: decision trees and k-nearest neighbors (KNN). Results showed that extracting deep features from the fc7 layer, selecting the most significant features using the LASSO algorithm, and executing the classification process using the KNN classifier is the best hybrid approach. The proposed hybrid deep learning approach detected COVID-19, among other HCoV diseases, with 99.71% accuracy, 99.78% specificity, and 99.62% sensitivity.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…Gupta et al 20 presented a deep-learning model called COVID-WideNet based on a capsule neural network (CapNet) for detecting COVID-19 using X-ray images. CapNets are composed of a network of neurons that accepts and outputs vectors instead of the scaler values in CNN models.…”

Section: Literature Reviewmentioning

confidence: 99%

A hybrid deep learning approach for COVID-19 detection based on genomic image processing techniques

Hammad

Ghoneim

Mabrouk

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Finally, the outputs of these classifiers were pooled to create an ensemble of classifiers – Shukla et al ( 2021 ) 2021 Transfer Learning—AlexNet; Tuning Hyper parameter—multi objective genetic algorithm – Haque and Abdelgawad ( 2020 ) 2020 Sequential CNN model is used. Model 1–4 convolution layer; Model 2–3 convolution Layer, Model 3–5 convolution layer The model's potential to perform in a multi-class scenario has not been investigated and it is recommended to train it on larger datasets Kiziloluk and Sert ( 2022 ) 2022 Using the gradient-based optimizer (GBO) algorithm, CNN-COVID-CCD-Net classification was improved – Kiziloluk and Sert ( 2022 ) 2022 The architecture of a lightweight shallow convolutional neural network (CNN) is proposed The model should train on large dataset Jalali et al ( 2022 ) 2022 The MCSO-CNN Deep Neuro Evolution (DNE) algorithm is proposed There are three powerful evolutionary operators to consider: (1) Evolutionary border constraint management, (2)Cauchy mutation (3) a tumultuous map The last CNN layer with Soft max activation is replaced by a KNN Classifier to improve the accuracy of the proposed system – Ahmadian et al ( 2021 ) 2021 DNE Algorithm is proposed named boosted SSA-CNN (BSSA-CNN) 2 effective optimization operators are included (1) opposition-based learning, (2)chaotic maps Hyper parameter Tuning-boosted salp swarm algorithm (BSSA);Classifier-SVM (1) The study is limited to a single deep neural network model (2) The effectiveness of the model may decline if optimal values of hyperparameters are not obtained Gupta et al ( 2022 ) 2022 Capsule network called COVID-Wide Net is proposed – Ortiz et al ( 2022 ) ...…”

Section: Literature Surveymentioning

confidence: 99%

A comprehensive review of analyzing the chest X-ray images to detect COVID-19 infections using deep learning techniques

Subramaniam¹,

Palanisamy²,

Sinnaswamy³

et al. 2023

Soft Comput

View full text Add to dashboard Cite

COVID-19, a highly infectious respiratory disease a used by SARS virus, has killed millions of people across many countries. To enhance quick and accurate diagnosis of COVID-19, chest X-ray (CXR) imaging methods were commonly utilized. Identifying the infection manually by radio imaging, on the other hand, was considered, extremely difficult due to the time commitment and significant risk of human error. Emerging artificial intelligence (AI) techniques promised exploration in the development of precise and as well as automated COVID-19 detection tools. Convolution neural networks (CNN), a well performing deep learning strategy tends to gain substantial favors among AI approaches for COVID-19 classification. The preprints and published studies to diagnose COVID-19 with CXR pictures using CNN and other deep learning methodologies are reviewed and critically assessed in this research. This study focused on the methodology, algorithms, and preprocessing techniques used in various deep learning architectures, as well as datasets and performance studies of several deep learning architectures used in prediction and diagnosis. Our research concludes with a list of future research directions in COVID-19 imaging categorization.

show abstract

“…Recently, capsule networks have been exploited for COVID-19 diagnosis [ 40 , 41 ]. Gupta et al [ 42 ] proposed the COVID-WideNet for detecting COVID-19 from non-COVID-19 cases based on a capsule network with two convolutional layers and three capsule layers with less-trainable parameters. Li and his colleagues [ 43 ] proposed a novel capsule network with a non-iterative and parameterized multi-head attention routing algorithm to replace the traditional iterative dynamic routing process.…”

Section: Related Workmentioning

confidence: 99%

Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans

et al. 2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

COVID-WideNet—A capsule network for COVID-19 detection

Cited by 29 publications

References 47 publications

A hybrid deep learning approach for COVID-19 detection based on genomic image processing techniques

A hybrid deep learning approach for COVID-19 detection based on genomic image processing techniques

A comprehensive review of analyzing the chest X-ray images to detect COVID-19 infections using deep learning techniques

Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans

Contact Info

Product

Resources

About