2021
DOI: 10.48550/arxiv.2104.06176
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

COVID-19 detection using chest X-rays: is lung segmentation important for generalization?

Abstract: We evaluated the generalization capability of deep neural networks (DNNs), trained to classify chest X-rays as COVID-19, normal or pneumonia, using a relatively small and mixed dataset.We proposed a DNN architecture to perform lung segmentation and classification. It stacks a segmentation module (U-Net), an original intermediate module and a classification module (DenseNet201). We compared it to a DenseNet201.To evaluate generalization, we tested the DNNs with an external dataset (from distinct localities) and… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 23 publications
0
2
0
Order By: Relevance
“…Bassi and Attux [28] present segmentation and classification methods using deep neural networks (DNNs) to classify chest X-rays as COVID-19, normal, or pneumonia. U-Net architecture was used for the segmentation and DenseNet201 for classification.…”
Section: Related Workmentioning
confidence: 99%
“…Bassi and Attux [28] present segmentation and classification methods using deep neural networks (DNNs) to classify chest X-rays as COVID-19, normal, or pneumonia. U-Net architecture was used for the segmentation and DenseNet201 for classification.…”
Section: Related Workmentioning
confidence: 99%
“…The approach achieved an average accuracy of 97.1 per cent, 97. Another research (Bassi & Attux, 2021) Here Also, researchers (Teixeira et al, 2021) However (Štifanić et al, 2021).This study used DeepLabv3+ with Xception 65, MobileNetV2, and ResNet101 for lung segmentation. The recommended strategy generated an average IoU of 0.910.…”
Section: Related Workmentioning
confidence: 99%