{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T05:27:00Z","timestamp":1788499620133,"version":"build-2803163510"},"reference-count":47,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T00:00:00Z","timestamp":1666828800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32060234"],"award-info":[{"award-number":["32060234"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004775","name":"Natural Science Foundation of Gansu Province","doi-asserted-by":"crossref","award":["China, 21JR7RA164"],"award-info":[{"award-number":["China, 21JR7RA164"]}],"id":[{"id":"10.13039\/501100004775","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["China, 31920210084"],"award-info":[{"award-number":["China, 31920210084"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>The global health crisis due to the fast spread of coronavirus disease (Covid-19) has caused great danger to all aspects of healthcare, economy, and other aspects. The highly infectious and insidious nature of the new coronavirus greatly increases the difficulty of outbreak prevention and control. The early and rapid detection of Covid-19 is an effective way to reduce the spread of Covid-19. However, detecting Covid-19 accurately and quickly in large populations remains to be a major challenge worldwide. In this study, A CNN-transformer fusion framework is proposed for the automatic classification of pneumonia on chest X-ray. This framework includes two parts: data processing and image classification. The data processing stage is to eliminate the differences between data from different medical institutions so that they have the same storage format; in the image classification stage, we use a multi-branch network with a custom convolution module and a transformer module, including feature extraction, feature focus, and feature classification sub-networks. Feature extraction subnetworks extract the shallow features of the image and interact with the information through the convolution and transformer modules. Both the local and global features are extracted by the convolution module and transformer module of feature-focus subnetworks, and are classified by the feature classification subnetworks. The proposed network could decide whether or not a patient has pneumonia, and differentiate between Covid-19 and bacterial pneumonia. This network was implemented on the collected benchmark datasets and the result shows that accuracy, precision, recall, and F1 score are 97.09%, 97.16%, 96.93%, and 97.04%, respectively. Our network was compared with other researchers\u2019 proposed methods and achieved better results in terms of accuracy, precision, and F1 score, proving that it is superior for Covid-19 detection. With further improvements to this network, we hope that it will provide doctors with an effective tool for diagnosing Covid-19.<\/jats:p>","DOI":"10.1371\/journal.pone.0276758","type":"journal-article","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T17:33:41Z","timestamp":1666892021000},"page":"e0276758","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":17,"title":["A CNN-transformer fusion network for COVID-19 CXR image classification"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5263-3182","authenticated-orcid":true,"given":"Kai","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6705-114X","authenticated-orcid":true,"given":"Tao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanlin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Limeng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"pone.0276758.ref001","article-title":"A Healthcare System for COVID19 Classification Using Multi-Type Classical Features Selection","author":"MA Khan","year":"2023","journal-title":"Comput Mater Contin"},{"key":"pone.0276758.ref002","first-page":"2560388","article-title":"A Rapid Artificial Intelligence-Based Computer-Aided Diagnosis System for COVID-19 Classification from CT Images","volume":"2021","author":"HH Syed","year":"2021","journal-title":"Behav Neurol [Internet]"},{"key":"pone.0276758.ref003","unstructured":"World Health Organization. WHO: Statement on the second meeting of the international health regulations (2005) emergency committee regarding the outbreak of novel coronavirus (2019-ncov) (2020). functions. [Internet]. Available from: https:\/\/www.who.int\/."},{"key":"pone.0276758.ref004","unstructured":"World Health Organization. WHO: WHO director-general\u2019s opening remarks at the media briefing on Covid-19 (2020). [Internet]. Available from: https:\/\/www.who.int."},{"key":"pone.0276758.ref005","unstructured":"World Health Organization. WHO: Coronavirus disease (COVID-19) Weekly Epidemiological Update and Weekly Operational Update, 2022. [Internet]. Available from: https:\/\/www.who.int\/emergencies\/diseases\/novel-coronavirus-2019\/situation-reports."},{"issue":"11","key":"pone.0276758.ref006","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1001\/jama.2020.1585","article-title":"Clinical Characteristics of 138 Hospitalized Patients With 2019 Novel Coronavirus\u2013Infected Pneumonia in Wuhan, China","volume":"323","author":"D Wang","year":"2020","journal-title":"JAMA"},{"issue":"2","key":"pone.0276758.ref007","doi-asserted-by":"crossref","first-page":"E115","DOI":"10.1148\/radiol.2020200432","article-title":"Sensitivity of Chest CT for COVID-19: Comparison to RT-PCR.","volume":"296","author":"Y Fang","year":"2020","journal-title":"Radiology [Internet]."},{"key":"pone.0276758.ref008","doi-asserted-by":"crossref","first-page":"108386","DOI":"10.1016\/j.compeleceng.2022.108386","article-title":"Brain MRI analysis using deep neural network for medical of internet things applications","volume":"103","author":"M Masood","year":"2022","journal-title":"Comput Electr Eng [Internet]"},{"key":"pone.0276758.ref009","first-page":"1465173","article-title":"BrainNet: Optimal Deep Learning Feature Fusion for Brain Tumor Classification","volume":"2022","author":"U Zahid","year":"2022","journal-title":"Comput Intell Neurosci [Internet]"},{"issue":"1","key":"pone.0276758.ref010","doi-asserted-by":"crossref","first-page":"e1","DOI":"10.1002\/mp.13264","article-title":"Deep learning in medical imaging and radiation therapy.","volume":"46","author":"B Sahiner","year":"2019","journal-title":"Med Phys [Internet]"},{"issue":"3","key":"pone.0276758.ref011","doi-asserted-by":"crossref","first-page":"200463","DOI":"10.1148\/radiol.2020200463","article-title":"Chest CT Findings in Coronavirus Disease-19 (COVID-19): Relationship to Duration of Infection","volume":"295","author":"A Bernheim","year":"2020","journal-title":"Radiology [Internet]."},{"key":"pone.0276758.ref012","article-title":"Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal","author":"L Wynants","year":"2020","journal-title":"BMJ [Internet]"},{"key":"pone.0276758.ref013","first-page":"1","article-title":"Lung X-Ray Image Segmentation Using Heuristic Red Fox Optimization Algorithm","volume":"2022","author":"A Jaszcz","year":"2022","journal-title":"Sci Program [Internet]"},{"key":"pone.0276758.ref014","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"G Litjens","year":"2017","journal-title":"Med Image Anal [Internet]"},{"key":"pone.0276758.ref015","volume-title":"Advances in Neural Information Processing Systems [Internet]","author":"A Krizhevsky","year":"2012"},{"key":"pone.0276758.ref016","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition.","author":"K Simonyan","year":"2015","journal-title":"ArXiv14091556 Cs [Internet]"},{"key":"pone.0276758.ref017","article-title":"Going Deeper with Convolutions.","author":"C Szegedy","year":"2014","journal-title":"ArXiv14094842 Cs [Internet]."},{"key":"pone.0276758.ref018","article-title":"Deep Residual Learning for Image Recognition.","author":"K He","year":"2015","journal-title":"ArXiv151203385 Cs [Internet]"},{"key":"pone.0276758.ref019","article-title":"Densely Connected Convolutional Networks.","author":"G Huang","year":"2018","journal-title":"ArXiv160806993 Cs [Internet]"},{"key":"pone.0276758.ref020","article-title":"Squeeze-and-Excitation Networks.","author":"J Hu","year":"2019","journal-title":"ArXiv170901507 Cs [Internet]"},{"key":"pone.0276758.ref021","first-page":"6105","volume-title":"Proceedings of the 36th International Conference on Machine Learning [Internet]","author":"M Tan","year":"2019"},{"issue":"13","key":"pone.0276758.ref022","doi-asserted-by":"crossref","first-page":"4640","DOI":"10.3390\/app10134640","article-title":"Deep Learning System for COVID-19 Diagnosis Aid Using X-ray Pulmonary Images.","volume":"10","author":"J Civit-Masot","year":"2020","journal-title":"Appl Sci [Internet]"},{"key":"pone.0276758.ref023","doi-asserted-by":"crossref","first-page":"103792","DOI":"10.1016\/j.compbiomed.2020.103792","article-title":"Automated detection of COVID-19 cases using deep neural networks with X-ray images","volume":"121","author":"T Ozturk","year":"2020","journal-title":"Comput Biol Med [Internet]"},{"key":"pone.0276758.ref024","first-page":"6","author":"Apostolopoulos ID","year":"2020","journal-title":"Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks"},{"key":"pone.0276758.ref025","doi-asserted-by":"crossref","first-page":"427","DOI":"10.3389\/fmed.2020.00427","article-title":"Deep Learning-Based Decision-Tree Classifier for COVID-19 Diagnosis From Chest X-ray Imaging.","volume":"7","author":"SH Yoo","year":"2020","journal-title":"Front Med [Internet]"},{"issue":"4","key":"pone.0276758.ref026","first-page":"643","article-title":"Detection of coronavirus Disease (COVID-19) based on Deep Features and Support Vector Machine","volume":"5","author":"PK Sethy","year":"2020","journal-title":"Int J Math Eng Manag Sci [Internet]"},{"key":"pone.0276758.ref027","doi-asserted-by":"crossref","first-page":"101794","DOI":"10.1016\/j.media.2020.101794","article-title":"Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning","volume":"65","author":"S Minaee","year":"2020","journal-title":"Med Image Anal [Internet]"},{"issue":"1","key":"pone.0276758.ref028","doi-asserted-by":"crossref","first-page":"19549","DOI":"10.1038\/s41598-020-76550-z","article-title":"COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images","volume":"10","author":"L Wang","year":"2020","journal-title":"Sci Rep [Internet]"},{"key":"pone.0276758.ref029","doi-asserted-by":"crossref","first-page":"948205","DOI":"10.3389\/fpubh.2022.948205","article-title":"COVID-19 classification using chest X-ray images: A framework of CNN-LSTM and improved max value moth flame optimization.","volume":"10","author":"A Hamza","year":"2022","journal-title":"Front Public Health [Internet]"},{"key":"pone.0276758.ref030","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/4254631","article-title":"COVID-19 Classification from Chest X-Ray Images: A Framework of Deep Explainable Artificial Intelligence","volume":"2022","author":"MA Khan","year":"2022","journal-title":"Comput Intell Neurosci [Internet]"},{"key":"pone.0276758.ref031","first-page":"100138","article-title":"COVID-19 detection in X-ray images using convolutional neural networks.","volume":"6","author":"D Arias-Garz\u00f3n","year":"2021","journal-title":"Mach Learn Appl [Internet]"},{"key":"pone.0276758.ref032","first-page":"671","article-title":"Convid-Net: An Enhanced Convolutional Neural Network Framework for COVID-19 Detection from X-Ray Images","author":"S Ahmed","year":"2021","journal-title":"Proceedings of International Conference on Trends in Computational and Cognitive Engineering [Internet]. Singapore: Springer Singapore"},{"key":"pone.0276758.ref033","doi-asserted-by":"crossref","first-page":"100412","DOI":"10.1016\/j.imu.2020.100412","article-title":"A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images","volume":"20","author":"MdZ Islam","year":"2020","journal-title":"Inform Med Unlocked [Internet]"},{"key":"pone.0276758.ref034","article-title":"Attention Is All You Need.","author":"A Vaswani","year":"2017","journal-title":"ArXiv170603762 Cs [Internet]"},{"key":"pone.0276758.ref035","author":"A Dosovitskiy","year":"2020","journal-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale"},{"key":"pone.0276758.ref036","article-title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","author":"B Wu","year":"2020","journal-title":"ArXiv200603677 Cs Eess [Internet]"},{"key":"pone.0276758.ref037","first-page":"10347","volume-title":"International Conference on Machine Learning [Internet]","author":"H Touvron","year":"2021"},{"key":"pone.0276758.ref038","first-page":"558","author":"L Yuan","year":"2021","journal-title":"Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNet"},{"key":"pone.0276758.ref039","article-title":"End-to-End Object Detection with Transformers.","author":"N Carion","year":"2020","journal-title":"ArXiv200512872 Cs [Internet]"},{"key":"pone.0276758.ref040","doi-asserted-by":"crossref","first-page":"12294","DOI":"10.1109\/CVPR46437.2021.01212","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]","author":"H Chen","year":"2021"},{"key":"pone.0276758.ref041","doi-asserted-by":"crossref","first-page":"6877","DOI":"10.1109\/CVPR46437.2021.00681","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]","author":"S Zheng","year":"2021"},{"key":"pone.0276758.ref042","first-page":"15908","volume-title":"Advances in Neural Information Processing Systems [Internet]","author":"K Han","year":"2021"},{"key":"pone.0276758.ref043","article-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows.","author":"Z Liu","year":"2021","journal-title":"ArXiv210314030 Cs [Internet]"},{"key":"pone.0276758.ref044","article-title":"Labeled optical coherence tomography (OCT) and chest X-ray images for classification","author":"D Kermany","year":"2018","journal-title":"Mendeley Data V2 Httpsdoi Org1017632rscbjbr9sj Httpsnihcc App Box ComvChestXray-NIHCC"},{"issue":"7","key":"pone.0276758.ref045","first-page":"13","article-title":"\u2018Data from medical imaging data resource center (MIDRC)-RSNA international covid radiology database (RICORD) release 1C\u2014Chest X-ray, covid+(MIDRC-RICORD-1C)","volume":"6","author":"EB Tsai","year":"2021","journal-title":"Cancer Imaging Arch"},{"issue":"1","key":"pone.0276758.ref046","doi-asserted-by":"crossref","first-page":"E204","DOI":"10.1148\/radiol.2021203957","article-title":"The RSNA international COVID-19 open radiology database (RICORD)","volume":"299","author":"EB Tsai","year":"2021","journal-title":"Radiology"},{"issue":"6","key":"pone.0276758.ref047","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","article-title":"The cancer imaging archive (TCIA): maintaining and operating a public information repository","volume":"26","author":"K Clark","year":"2013","journal-title":"J Digit Imaging"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0276758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T17:34:41Z","timestamp":1666892081000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0276758"}},"subtitle":[],"editor":[{"given":"Robertas","family":"Dama\u0161evi\u010dius","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,10,27]]},"references-count":47,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,10,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0276758","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,27]]}}}