2021
DOI: 10.1016/j.patcog.2020.107613
|View full text |Cite
|
Sign up to set email alerts
|

Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays

Abstract: Highlights We proposed a novel framework, CHP-Net, to differentiate and localize COVID-19 from community acquired pneumonia. We used excessive data augmentation to extend the available dataset and optimize the CHP-Net generalization capability. Comparing to other ConvNet, CHP-Net works much more efficiently to extract feature information on chest X-Ray. All metrics, including categorical loss, accuracy, precision, recall and F1-score, pr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
110
0
7

Year Published

2021
2021
2023
2023

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 150 publications
(117 citation statements)
references
References 32 publications
0
110
0
7
Order By: Relevance
“…Most of these papers used off-the-shelf networks, including ResNet-18 or ResNet-50 16,17,20,26,29,32,37 , DenseNet-121 27,28,31,32,34 , VGG-16 or VGG-19 19,33,35 , Inception 21,38 and EfficientNet 30,39 , with three considering custom architectures 18,25,36 and three using hand-engineered features [22][23][24] . Most papers classified images into the three classes, that is, COVID-19, non-COVID-19 pneumonia and normal 16,19,21,23,25,26,28,30,[32][33][34][35][36][37] , while two considered an extra class by dividing non-COVID-19 pneumonia into viral and bacterial pneumonia 17,29 . ResNet and DenseNet architectures showed better performance than the others, with accuracies ranging from 0.88 to 0.99.…”
Section: Diagnostic Models For Covid-19 Diagnosis Models Using Cxrsmentioning
confidence: 99%
See 3 more Smart Citations
“…Most of these papers used off-the-shelf networks, including ResNet-18 or ResNet-50 16,17,20,26,29,32,37 , DenseNet-121 27,28,31,32,34 , VGG-16 or VGG-19 19,33,35 , Inception 21,38 and EfficientNet 30,39 , with three considering custom architectures 18,25,36 and three using hand-engineered features [22][23][24] . Most papers classified images into the three classes, that is, COVID-19, non-COVID-19 pneumonia and normal 16,19,21,23,25,26,28,30,[32][33][34][35][36][37] , while two considered an extra class by dividing non-COVID-19 pneumonia into viral and bacterial pneumonia 17,29 . ResNet and DenseNet architectures showed better performance than the others, with accuracies ranging from 0.88 to 0.99.…”
Section: Diagnostic Models For Covid-19 Diagnosis Models Using Cxrsmentioning
confidence: 99%
“…For the 33 papers that used private datasets, the COVID-19 diagnosis was due to either positive RT-PCR or antibody tests for 24/33 and have a low risk of bias. The other papers have a high (7/33) or unclear (2/33) risk of bias due to inconsistent diagnosis of COVID-19 40,82 , unclear definition of a control group 63,65 , ground truths being assigned using the images themselves 26,54,60,71 , using an unestablished reference to define outcome 74 or by combining public and private datasets 41,66,83 .…”
Section: Risks Of Biasmentioning
confidence: 99%
See 2 more Smart Citations
“…With the current spread rate of COVID-19, this is not acceptable. Further, the limited number of test kits exacerbates the situation [1] , [2] , [3] . Recent studies also show that the RT-PCR suffers from low sensitivity and accuracy, often requiring repeated entries [4] , [5] .…”
Section: Introductionmentioning
confidence: 99%