File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification

TitleArtificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification
Authors
Keywordsbone suppression
chest X-ray (CXR)
Coronavirus disease 2019 (COVID-19)
super-resolution
Issue Date1-Jan-2023
PublisherAME Publishing
Citation
Quantitative Imaging in Medicine and Surgery, 2023, v. 13, n. 1, p. 394-416 How to Cite?
Abstract

Background: The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification.

Methods: Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models.

Results: Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images.

Conclusions: The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.


Persistent Identifierhttp://hdl.handle.net/10722/338910
ISSN
2023 Impact Factor: 2.9
2023 SCImago Journal Rankings: 0.746
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorSun, HF-
dc.contributor.authorRen, G-
dc.contributor.authorTeng, XZ-
dc.contributor.authorSong, LM-
dc.contributor.authorLi, K-
dc.contributor.authorYang, JH-
dc.contributor.authorHu, XF-
dc.contributor.authorZhan, YF-
dc.contributor.authorWan, SBN-
dc.contributor.authorWong, MFE-
dc.contributor.authorChan, KK-
dc.contributor.authorTsang, HCH-
dc.contributor.authorXu, L-
dc.contributor.authorWu, TC-
dc.contributor.authorKong, FMS-
dc.contributor.authorWang, YXJ-
dc.contributor.authorQin, J-
dc.contributor.authorChan, WCL-
dc.contributor.authorYing, M-
dc.contributor.authorCai, J-
dc.date.accessioned2024-03-11T10:32:28Z-
dc.date.available2024-03-11T10:32:28Z-
dc.date.issued2023-01-01-
dc.identifier.citationQuantitative Imaging in Medicine and Surgery, 2023, v. 13, n. 1, p. 394-416-
dc.identifier.issn2223-4292-
dc.identifier.urihttp://hdl.handle.net/10722/338910-
dc.description.abstract<p><strong>Background: </strong>The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification.</p><p><strong>Methods: </strong>Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models.</p><p><strong>Results: </strong>Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images.</p><p><strong>Conclusions: </strong>The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.</p>-
dc.languageeng-
dc.publisherAME Publishing-
dc.relation.ispartofQuantitative Imaging in Medicine and Surgery-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectbone suppression-
dc.subjectchest X-ray (CXR)-
dc.subjectCoronavirus disease 2019 (COVID-19)-
dc.subjectsuper-resolution-
dc.titleArtificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification-
dc.typeArticle-
dc.identifier.doi10.21037/qims-22-610-
dc.identifier.scopuseid_2-s2.0-85145985361-
dc.identifier.volume13-
dc.identifier.issue1-
dc.identifier.spage394-
dc.identifier.epage416-
dc.identifier.eissn2223-4306-
dc.identifier.isiWOS:000885028700001-
dc.identifier.issnl2223-4306-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats