A new COVID-19 detection method from human genome sequences using CpG island features and KNN classifier DOI Creative Commons
Hilal Arslan, Hasan Arslan

Engineering Science and Technology an International Journal, Journal Year: 2021, Volume and Issue: 24(4), P. 839 - 847

Published: Jan. 12, 2021

Various viral epidemics have been detected such as the severe acute respiratory syndrome coronavirus and Middle East in last two decades. The disease 2019 (COVID-19) is a pandemic caused by novel betacoronavirus called coronavirus-2 (SARS-CoV-2). After rapid spread of COVID-19, many researchers investigated diagnosis treatment for this terrifying quickly. Identifying COVID-19 from other types coronaviruses difficult problem due to their genetic similarity. In study, we propose new efficient detection method based on K-nearest neighbors (KNN) classifier using complete genome sequences human dataset recorded Novel Coronavirus Resource. We also describe features CpG island that efficiently detect cases. Thus, including approximately 30,000 nucleotides can be represented only real numbers. KNN simple effective non-parametric technique solving classification problems. However, performance depends distance measure used. perform 19 metrics five categories improve algorithm. Some parameters are computed evaluate proposed method. achieves 98.4% precision, 99.2% recall, 98.8% F-measure, accuracy few seconds when any L1 type metric used KNN.

Language: Английский

A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images DOI Creative Commons

Md. Zabirul Islam,

Md. Milon Islam, Amanullah Asraf

et al.

Informatics in Medicine Unlocked, Journal Year: 2020, Volume and Issue: 20, P. 100412 - 100412

Published: Jan. 1, 2020

Nowadays, automatic disease detection has become a crucial issue in medical science due to rapid population growth. An framework assists doctors the diagnosis of and provides exact, consistent, fast results reduces death rate. Coronavirus (COVID-19) one most severe acute diseases recent times spread globally. Therefore, an automated system, as fastest diagnostic option, should be implemented impede COVID-19 from spreading. This paper aims introduce deep learning technique based on combination convolutional neural network (CNN) long short-term memory (LSTM) diagnose automatically X-ray images. In this CNN is used for feature extraction LSTM using extracted feature. A collection 4575 images, including 1525 images COVID-19, were dataset system. The experimental show that our proposed system achieved accuracy 99.4%, AUC 99.9%, specificity 99.2%, sensitivity 99.3%, F1-score 98.9%. desired currently available dataset, which can further improved when more available. help treat patients easily.

Language: Английский

Citations

568
Automated medical diagnosis of COVID-19 through EfficientNet convolutional neural network DOI Open Access
Gonçalo Marques, Deevyankar Agarwal, Isabel de la Torre Díez

et al.

Applied Soft Computing, Journal Year: 2020, Volume and Issue: 96, P. 106691 - 106691

Published: Aug. 30, 2020

Language: Английский

Citations

335
CNN-based transfer learning–BiLSTM network: A novel approach for COVID-19 infection detection DOI Open Access
Muhammet Fatih Aslan, Muhammed Fahri Ünlerşen, Kadir Sabancı

et al.

Applied Soft Computing, Journal Year: 2020, Volume and Issue: 98, P. 106912 - 106912

Published: Nov. 19, 2020

Language: Английский

Citations

315
A deep learning approach to detect Covid-19 coronavirus with X-Ray images DOI Open Access

Govardhan Jain,

Deepti Mittal,

Daksh Thakur

et al.

Journal of Applied Biomedicine, Journal Year: 2020, Volume and Issue: 40(4), P. 1391 - 1405

Published: Sept. 7, 2020

Language: Английский

Citations

294
Transfer learning techniques for medical image analysis: A review DOI
Padmavathi Kora, Chui Ping Ooi, Oliver Faust

et al.

Journal of Applied Biomedicine, Journal Year: 2021, Volume and Issue: 42(1), P. 79 - 107

Published: Dec. 13, 2021

Language: Английский

Citations

235
Applications of artificial intelligence in battling against covid-19: A literature review DOI Open Access

Mohammad-H. Tayarani N.

Chaos Solitons & Fractals, Journal Year: 2020, Volume and Issue: 142, P. 110338 - 110338

Published: Oct. 3, 2020

Language: Английский

Citations

196
Review of COVID-19 testing and diagnostic methods DOI Creative Commons
Olena Filchakova,

Dina Dossym,

Aisha Ilyas

et al.

Talanta, Journal Year: 2022, Volume and Issue: 244, P. 123409 - 123409

Published: April 1, 2022

More than six billion tests for COVID-19 has been already performed in the world. The testing SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus-2) virus and corresponding human antibodies is essential not only diagnostics treatment of infection by medical institutions, but also as a pre-requisite major semi-normal economic social activities such international flights, off line work study offices, access to malls, sport events. Accuracy, sensitivity, specificity, time results cost per test are parameters those even minimal improvement any them may have noticeable impact on life many countries We described, analyzed compared methods detection, while representing their 22 tables. Also, we performance some FDA approved kits with clinical non-FDA just described scientific literature. RT-PCR still remains golden standard detection virus, pressing need alternative less expensive, more rapid, point care evident. Those that eventually get developed satisfy this explained, discussed, quantitatively compared. review bioanalytical chemistry prospective, it be interesting broader circle readers who interested understanding testing, helping leave pandemic past.

Language: Английский

Citations

182
Review on Diagnosis of COVID-19 from Chest CT Images Using Artificial Intelligence DOI Open Access
İlker Özşahin, Boran Şekeroğlu, Musa Sani Musa

et al.

Computational and Mathematical Methods in Medicine, Journal Year: 2020, Volume and Issue: 2020, P. 1 - 10

Published: Sept. 26, 2020

The COVID-19 diagnostic approach is mainly divided into two broad categories, a laboratory-based and chest radiography approach. last few months have witnessed rapid increase in the number of studies use artificial intelligence (AI) techniques to diagnose with computed tomography (CT). In this study, we review diagnosis by using CT toward AI. We searched ArXiv, MedRxiv, Google Scholar terms “deep learning”, “neural networks”, “COVID-19”, “chest CT”. At time writing (August 24, 2020), there been nearly 100 30 among them were selected for review. categorized based on classification tasks: COVID-19/normal, COVID-19/non-COVID-19, COVID-19/non-COVID-19 pneumonia, severity. sensitivity, specificity, precision, accuracy, area under curve, F1 score results reported as high 100%, 99.62, 99.87%, 99.5%, respectively. However, presented should be carefully compared due different degrees difficulty tasks.

Language: Английский

Citations

174
DenseNet Convolutional Neural Networks Application for Predicting COVID-19 Using CT Image DOI Creative Commons
Najmul Hasan, Yukun Bao, Ashadullah Shawon

et al.

SN Computer Science, Journal Year: 2021, Volume and Issue: 2(5)

Published: July 23, 2021

Language: Английский

Citations

125
IoT enabled depthwise separable convolution neural network with deep support vector machine for COVID-19 diagnosis and classification DOI Creative Commons
Dac‐Nhuong Le, Velmurugan Subbiah Parvathy, Deepak Gupta

et al.

International Journal of Machine Learning and Cybernetics, Journal Year: 2021, Volume and Issue: 12(11), P. 3235 - 3248

Published: Jan. 2, 2021

At present times, the drastic advancements in 5G cellular and internet of things (IoT) technologies find useful different applications healthcare sector. same time, COVID-19 is commonly spread from animals to persons, but today it transmitting among persons by adapting structure. It a severe virus inappropriately resulted global pandemic. Radiologists utilize X-ray or computed tomography (CT) images diagnose disease. essential identify classify disease through use image processing techniques. So, new intelligent diagnosis model need COVID-19. In this view, paper presents novel IoT enabled Depthwise separable convolution neural network (DWS-CNN) with Deep support vector machine (DSVM) for classification. The proposed DWS-CNN aims detect both binary multiple classes incorporating set processes namely data acquisition, Gaussian filtering (GF) based preprocessing, feature extraction, Initially, patient will be collected acquisition stage using devices sent cloud server. Besides, GF technique applied remove existence noise that exists image. Then, employed replacing default automatic extraction. Finally, DSVM determine class labels diagnostic outcome tested against Chest (CXR) dataset results are investigated interms distinct performance measures. experimental ensured superior attaining maximum classification accuracy 98.54% 99.06% on multiclass respectively.

Language: Английский

Citations

116