2020
DOI: 10.1371/journal.pone.0235187
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: COVID-19 is a worldwide epidemic, as announced by the World Health Organization (WHO) in March 2020. Machine learning (ML) methods can play vital roles in identifying COVID-19 patients by visually analyzing their chest x-ray images. In this paper, a new MLmethod proposed to classify the chest x-ray images into two classes, COVID-19 patient or non-COVID-19 person. The features extracted from the chest x-ray images using new Fractional Multichannel Exponent Moments (FrMEMs). A parallel multi-core computational f… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
206
0
1

Year Published

2020
2020
2023
2023

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 290 publications
(207 citation statements)
references
References 37 publications
0
206
0
1
Order By: Relevance
“…Hurt et al used a U-net CNN algorithm to predict pixel-wise probability maps for pneumonia on CXR on 10 COVID-19 patients (Hurt et al 2020) used an innovative feature selection algorithms and standard classifier to classify CXR between COVID-19 (N=216) and non- COVID-19 (N=1675). This method achieved accuracy rates of 96.09% and 98.09% for each of the respective datasets (Elaziz et al 2020). Note that patient…”
Section: Discussionmentioning
confidence: 95%
“…Hurt et al used a U-net CNN algorithm to predict pixel-wise probability maps for pneumonia on CXR on 10 COVID-19 patients (Hurt et al 2020) used an innovative feature selection algorithms and standard classifier to classify CXR between COVID-19 (N=216) and non- COVID-19 (N=1675). This method achieved accuracy rates of 96.09% and 98.09% for each of the respective datasets (Elaziz et al 2020). Note that patient…”
Section: Discussionmentioning
confidence: 95%
“… Apostolopoulos & Mpesiana (2020) used deep-learning algorithm to predict COVID-19 CXR with 98.66% sensitivity, 96.46% specificity, and 96.78% accuracy from a collection of 1,427 CXRs of which 224 were COVID-19 CXRs. Elaziz et al (2020) used an innovative feature selection algorithms and standard classifier to classify CXR between COVID-19 ( N = 216) and non-COVID-19 ( N = 1,675). This method achieved accuracy rates of 96.09% and 98.09% for each of the respective datasets.…”
Section: Discussionmentioning
confidence: 99%
“…Many AI algorithms based on deep-learning convolutional neural networks have been deployed for pCXR applications ( Harris et al, 2019 ; Heo et al, 2019 ; Mekov, Miravitlles & Petkov, 2020 ) and these algorithms can be readily repurposed for COVID-19 pandemic circumstances. While there are already many papers describing prevalence and radiographic features on pCXR of COVID-19 lung infection (see reviews ( Bao et al, 2020 )), there are a few AI papers ( Apostolopoulos & Mpesiana, 2020 ; Cohen et al, 2020 ; Elaziz et al, 2020 ; Hurt, Kligerman & Hsiao, 2020 ; Murphy et al, 2020 ; Ozturk et al, 2020 ; Pereira et al, 2020 ; Zhu et al, 2020a ) to classify CXRs of COVID-19 patients from CXR of normals or related lung infections. The full potential of AI applications of pCXR under COVID-19 pandemic circumstances is not yet fully realized.…”
Section: Introductionmentioning
confidence: 99%
“…To visualize the spatial location on the images that the CNN networks were paying attention to for classification, heatmaps of the COVID-19 versus normal pCXR are shown in non-COVID-19 (N=1675). This method achieved accuracy rates of 96.09% and 98.09% for each of the respective datasets (29). Note that patient cohorts were highly asymmetric.…”
Section: Heatmapsmentioning
confidence: 98%