Detection of Covid-19 on Localized Ct-scan Images Using Deep Learning Convolution Neural Network

Widodo, Sri; Sulistiyanti, Anik; Yudistira, Indra Agung

doi:10.51505/ijaemr.2022.7209

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A simple CNN model was examined with a 224x224 image input consisting of a non-COVID-19 COVID-19 label with 140 images to train the model and 160 images to test the model. The accuracy obtained is 95% in 20 iterations [10]. However, a transfer learning model has an input resolution constraint.…”

Section: Introductionmentioning

confidence: 91%

Reduction of Feature Extraction for COVID-19 CXR using Depthwise Separable Convolution Network

Iklima

Kadarina

Priambodo

2022

j.electron.electromedical.eng.med.inform

View full text Add to dashboard Cite

A Convolutional Neural Network (CNN) classifier is generally utilized to classify an image tensor according to the mapped labels. The simplification of the classifier causes CNN to be often used to classify images, especially in the biomedical field. Thus, CNN is widely used to classify computer tomography (CT) and chest X-ray (CXR) images against the mapped labels. Several transfer learning models were implemented to classify CXR images for preliminary detection of COVID-19 infection, e.g., ResNet, Inception, Xception, etc. However, a transfer learning model has a maximum and minimum input resolution. Thus, the computational cost tends to be huge and unable to be optimized. Therefore, A custom CNN model can be a solution to reduce computational costs by configuring the feature extraction layers. This study proposed an efficient reduction of feature extraction for COVID-19 CXR namely Depthwise Separable Convolution Network. Furthermore, numerous strategies were adopted to lower the computational cost while retaining accuracy, including customizing the Batch Normalization (BN) layer and replacing the convolution layer with a separable convolution layer. The proposed model successfully reduced the feature extraction represented by the decreases in trainable parameters from 28.640 trainable parameters to 4.640 trainable parameters. The depthwise separable convolution effectively retains the performance accuracy 72.96%, loss 12.43%, recall 74.67%, precision 77.67%, and F1-score 75.33%. The CXR augmentation is also successfully increase the performance accuracy 74.55%, loss 11.37%, recall 77.67%, precision 79.56%, and F1-score 78.33%.

show abstract

Section: Introductionmentioning

confidence: 91%

Reduction of Feature Extraction for COVID-19 CXR using Depthwise Separable Convolution Network

Iklima

Kadarina

Priambodo

2022

j.electron.electromedical.eng.med.inform

View full text Add to dashboard Cite

show abstract

“…manifestation, and multiple studies have provided evidence that the sera obtained from people who are infected with MERS-CoV or SARS-CoV have the ability to cross-react with SARS-CoV-2, and vice versa. [5][6][7][8][9][10][11] This cross-reactivity is thought to be caused by the high resemblance in the genes among the viruses.…”

mentioning

confidence: 99%

The role of cross-reactive immunity to emerging coronaviruses

Alturaiki

2023

SMJ

View full text Add to dashboard Cite

C oronaviruses are a large family of ribonucleic acid (RNA) viruses that can cause diseases in both humans and animals, and have caused significant public health concerns, and some human coronaviruses, such as OC43, NL63, 229E, and HKU1, can cause mild to moderate flu-like symptoms. 1,2 However, over the past twenty years, the world has faced 3 major pandemics of serious and lethal human coronaviruses, namely Severe Acute Respiratory Syndrome coronavirus (SARS-CoV) in 2003, Middle East respiratory syndrome coronavirus (MERS-CoV) in 2012, and the new coronavirus (SARS-CoV-2) which was found at the end of 2019 and has caused the ongoing outbreak of COVID-19 disease. [2][3][4] The appearances of these viruses have encouraged us to achieve a deeper understanding of their disease mechanisms, transmission modes, and host immune interactions, and particularly the role of cross-reactivity among them. Furthermore, despite their distinct nature, these coronaviruses share several similarities in their genomic structure, receptor usage, and clinical

show abstract

Detection of Covid-19 on Localized Ct-scan Images Using Deep Learning Convolution Neural Network

Cited by 2 publications

References 13 publications

Reduction of Feature Extraction for COVID-19 CXR using Depthwise Separable Convolution Network

Reduction of Feature Extraction for COVID-19 CXR using Depthwise Separable Convolution Network

The role of cross-reactive immunity to emerging coronaviruses

Contact Info

Product

Resources

About