COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases From Chest CT Images DOI Creative Commons
Hayden Gunraj, Linda Wang, Alexander Wong

et al.

Frontiers in Medicine, Journal Year: 2020, Volume and Issue: 7

Published: Dec. 23, 2020

The coronavirus disease 2019 (COVID-19) pandemic continues to have a tremendous impact on patients and healthcare systems around the world. In fight against this novel disease, there is pressing need for rapid effective screening tools identify infected with COVID-19, end CT imaging has been proposed as one of key methods which may be used complement RT-PCR testing, particularly in situations where undergo routine scans non-COVID-19 related reasons, worsening respiratory status or developing complications that require expedited care, are suspected COVID-19-positive but negative test results. Early studies CT-based reported abnormalities chest images characteristic COVID-19 infection, these difficult distinguish from caused by other lung conditions. Motivated this, study we introduce COVIDNet-CT, deep convolutional neural network architecture tailored detection cases via machine-driven design exploration approach. Additionally, COVIDx-CT, benchmark image dataset derived data collected China National Center Bioinformation comprising 104,009 across 1,489 patient cases. Furthermore, interest reliability transparency, leverage an explainability-driven performance validation strategy investigate decision-making behavior doing so ensure COVIDNet-CT makes predictions based relevant indicators images. Both COVIDx-CT available general public open-source open access manner part COVID-Net initiative. While not yet production-ready solution, hope releasing model will encourage researchers, clinicians, citizen scientists alike build upon them.

Language: Английский

Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal DOI Creative Commons
Laure Wynants, Ben Van Calster, Gary S. Collins

et al.

BMJ, Journal Year: 2020, Volume and Issue: unknown, P. m1328 - m1328

Published: April 7, 2020

To review and appraise the validity usefulness of published preprint reports prediction models for diagnosing coronavirus disease 2019 (covid-19) in patients with suspected infection, prognosis covid-19, detecting people general population at increased risk covid-19 infection or being admitted to hospital disease.

Language: Английский

Citations

2836
Automated detection of COVID-19 cases using deep neural networks with X-ray images DOI Open Access
Tülin Öztürk, Muhammed Talo,

Eylul Azra Yildirim

et al.

Computers in Biology and Medicine, Journal Year: 2020, Volume and Issue: 121, P. 103792 - 103792

Published: April 28, 2020

Language: Английский

Citations

2514
Virology, Epidemiology, Pathogenesis, and Control of COVID-19 DOI Creative Commons
Yuefei Jin, Haiyan Yang, Wangquan Ji

et al.

Viruses, Journal Year: 2020, Volume and Issue: 12(4), P. 372 - 372

Published: March 27, 2020

The outbreak of emerging severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) disease (COVID-19) in China has been brought to global attention and declared a pandemic by the World Health Organization (WHO) on March 11, 2020. Scientific advancements since (SARS) 2002~2003 Middle East (MERS) 2012 have accelerated our understanding epidemiology pathogenesis SARS-CoV-2 development therapeutics treat viral infection. As no specific vaccines are available for control, epidemic COVID-19 is posing great threat public health. To provide comprehensive summary health authorities potential readers worldwide, we detail present introduce current state measures this review.

Language: Английский

Citations

1505
Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network DOI Creative Commons
Asmaa Abbas, Mohammed M. Abdelsamea, Mohamed Medhat Gaber

et al.

Applied Intelligence, Journal Year: 2020, Volume and Issue: 51(2), P. 854 - 864

Published: Sept. 5, 2020

Chest X-ray is the first imaging technique that plays an important role in diagnosis of COVID-19 disease. Due to high availability large-scale annotated image datasets, great success has been achieved using convolutional neural networks (CNN s) for recognition and classification. However, due limited medical images, classification images remains biggest challenge diagnosis. Thanks transfer learning, effective mechanism can provide a promising solution by transferring knowledge from generic object tasks domain-specific tasks. In this paper, we validate deep CNN, called Decompose, Transfer, Compose (DeTraC), chest images. DeTraC deal with any irregularities dataset investigating its class boundaries decomposition mechanism. The experimental results showed capability detection cases comprehensive collected several hospitals around world. High accuracy 93.1% (with sensitivity 100%) was normal, severe acute respiratory syndrome cases.

Language: Английский

Citations

832
COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images DOI Open Access
Ferhat Uçar, Deniz Korkmaz

Medical Hypotheses, Journal Year: 2020, Volume and Issue: 140, P. 109761 - 109761

Published: April 23, 2020

Language: Английский

Citations

753
COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images DOI Open Access
Parnian Afshar,

Shahin Heidarian,

Farnoosh Naderkhani

et al.

Pattern Recognition Letters, Journal Year: 2020, Volume and Issue: 138, P. 638 - 643

Published: Sept. 16, 2020

Language: Английский

Citations

676
Classification of COVID-19 patients from chest CT images using multi-objective differential evolution–based convolutional neural networks DOI Creative Commons
Dilbag Singh, Vijay Kumar,

Vaishali

et al.

European Journal of Clinical Microbiology & Infectious Diseases, Journal Year: 2020, Volume and Issue: 39(7), P. 1379 - 1389

Published: April 27, 2020

Early classification of 2019 novel coronavirus disease (COVID-19) is essential for cure and control. Compared with reverse-transcription polymerase chain reaction (RT-PCR), chest computed tomography (CT) imaging may be a significantly more trustworthy, useful, rapid technique to classify evaluate COVID-19, specifically in the epidemic region. Almost all hospitals have CT machines; therefore, images can utilized early COVID-19 patients. However, CT-based involves radiology expert considerable time, which valuable when infection growing at rate. Therefore, an automated analysis desirable save medical professionals' precious time. In this paper, convolutional neural networks (CNN) used COVID-19-infected patients as infected (+ve) or not (-ve). Additionally, initial parameters CNN are tuned using multi-objective differential evolution (MODE). Extensive experiments performed by considering proposed competitive machine learning techniques on images. shows that model good accuracy

Language: Английский

Citations

629
Explainable Deep Learning for Pulmonary Disease and Coronavirus COVID-19 Detection from X-rays DOI Open Access
Luca Brunese, Francesco Mercaldo, Alfonso Reginelli

et al.

Computer Methods and Programs in Biomedicine, Journal Year: 2020, Volume and Issue: 196, P. 105608 - 105608

Published: June 21, 2020

Language: Английский

Citations

577
Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets DOI Creative Commons
Stephanie A. Harmon,

Thomas Sanford,

Sheng Xu

et al.

Nature Communications, Journal Year: 2020, Volume and Issue: 11(1)

Published: Aug. 14, 2020

Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation scans differentiation findings from other entities. Here we show that series deep learning algorithms, trained diverse multinational cohort 1280 patients localize parietal pleura/lung parenchyma followed by classification pneumonia, can achieve up 90.8% accuracy, with 84% sensitivity and 93% specificity, evaluated an independent test set (not included training validation) 1337 patients. Normal controls chest CTs oncology, emergency, pneumonia-related indications. The false positive rate 140 laboratory confirmed (non COVID-19) pneumonias was 10%. AI-based algorithms readily identify well distinguish non-COVID related high specificity patient populations.

Language: Английский

Citations

538
The establishment of reference sequence for SARS‐CoV‐2 and variation analysis DOI Open Access

Changtai Wang,

Zhongping Liu,

Zixiang Chen

et al.

Journal of Medical Virology, Journal Year: 2020, Volume and Issue: 92(6), P. 667 - 674

Published: March 13, 2020

Starting around December 2019, an epidemic of pneumonia, which was named COVID-19 by the World Health Organization, broke out in Wuhan, China, and is spreading throughout world. A new coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Coronavirus Study Group International Committee on Taxonomy Viruses soon found to be cause. At present, sensitivity clinical nucleic acid detection limited, it still unclear whether related genetic variation. In this study, we retrieved 95 full-length genomic sequences SARAS-CoV-2 strains from National Center for Biotechnology Information GISAID databases, established reference sequence conducting multiple alignment phylogenetic analyses, analyzed variations along SARS-CoV-2 genome. The homology among all viral generally high, them, 99.99% (99.91%-100%) at nucleotide level (99.79%-100%) amino level. Although overall variation open-reading frame (ORF) regions low, 13 sites 1a, 1b, S, 3a, M, 8, N were identified, positions nt28144 ORF 8 nt8782 1a showed mutation rate 30.53% (29/95) 29.47% (28/95), respectively. These findings suggested that there may selective mutations SARS-COV-2, necessary avoid certain when designing primers probes. Establishment could benefit not only biological study virus but also diagnosis, monitoring intervention infection future.

Language: Английский

Citations

516