{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1360580229807500544.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1007/s11548-022-02813-x"}},{"identifier":{"@type":"URI","@value":"https://link.springer.com/content/pdf/10.1007/s11548-022-02813-x.pdf"}},{"identifier":{"@type":"URI","@value":"https://link.springer.com/article/10.1007/s11548-022-02813-x/fulltext.html"}},{"identifier":{"@type":"DOI","@value":"10.48550/arxiv.2212.09276"}},{"identifier":{"@type":"PMID","@value":"36538184"}},{"identifier":{"@type":"HANDLE","@value":"2115/90979"}}],"resourceType":"学術雑誌論文(journal article)","dc:title":[{"@value":"COVID-19 detection based on self-supervised transfer learning using chest X-ray images"}],"description":[{"notation":[{"@value":"Purpose: Considering several patients screened due to COVID-19 pandemic, computer-aided detection has strong potential in assisting clinical workflow efficiency and reducing the incidence of infections among radiologists and healthcare providers. Since many confirmed COVID-19 cases present radiological findings of pneumonia, radiologic examinations can be useful for fast detection. Therefore, chest radiography can be used to fast screen COVID-19 during the patient triage, thereby determining the priority of patient's care to help saturated medical facilities in a pandemic situation. Methods: In this paper, we propose a new learning scheme called self-supervised transfer learning for detecting COVID-19 from chest X-ray (CXR) images. We compared six self-supervised learning (SSL) methods (Cross, BYOL, SimSiam, SimCLR, PIRL-jigsaw, and PIRL-rotation) with the proposed method. Additionally, we compared six pretrained DCNNs (ResNet18, ResNet50, ResNet101, CheXNet, DenseNet201, and InceptionV3) with the proposed method. We provide quantitative evaluation on the largest open COVID-19 CXR dataset and qualitative results for visual inspection. Results: Our method achieved a harmonic mean (HM) score of 0.985, AUC of 0.999, and four-class accuracy of 0.953. We also used the visualization technique Grad-CAM++ to generate visual explanations of different classes of CXR images with the proposed method to increase the interpretability. Conclusions: Our method shows that the knowledge learned from natural images using transfer learning is beneficial for SSL of the CXR images and boosts the performance of representation learning for COVID-19 detection. Our method promises to reduce the incidence of infections among radiologists and healthcare providers."}]},{"notation":[{"@value":"Published as a journal paper at Springer IJCARS"}]}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1380580229807500419","@type":"Researcher","foaf:name":[{"@value":"Guang Li"}]},{"@id":"https://cir.nii.ac.jp/crid/1420001326212280960","@type":"Researcher","personIdentifier":[{"@type":"KAKEN_RESEARCHERS","@value":"60840395"},{"@type":"NRID","@value":"1000060840395"},{"@type":"NRID","@value":"9000412336189"},{"@type":"NRID","@value":"9000403959046"},{"@type":"NRID","@value":"9000317557128"},{"@type":"NRID","@value":"9000408668783"},{"@type":"NRID","@value":"9000406034210"},{"@type":"NRID","@value":"9000412315660"},{"@type":"NRID","@value":"9000412230423"},{"@type":"NRID","@value":"9000413741372"},{"@type":"NRID","@value":"9000398292600"},{"@type":"NRID","@value":"9000405860482"},{"@type":"NRID","@value":"9000405632969"},{"@type":"NRID","@value":"9000398646662"},{"@type":"NRID","@value":"9000405632974"},{"@type":"RESEARCHMAP","@value":"https://researchmap.jp/r-togo"}],"foaf:name":[{"@value":"Ren Togo"}]},{"@id":"https://cir.nii.ac.jp/crid/1380580229807500545","@type":"Researcher","foaf:name":[{"@value":"Takahiro Ogawa"}]},{"@id":"https://cir.nii.ac.jp/crid/1380580229807500424","@type":"Researcher","foaf:name":[{"@value":"Miki Haseyama"}]}],"publication":{"publicationIdentifier":[{"@type":"EISSN","@value":"18616429"}],"prism:publicationName":[{"@value":"International Journal of Computer Assisted Radiology and Surgery"}],"dc:publisher":[{"@value":"Springer Science and Business Media LLC"}],"prism:publicationDate":"2022-12-20","prism:volume":"18","prism:number":"4","prism:startingPage":"715","prism:endingPage":"722"},"reviewed":"false","dc:rights":["https://www.springernature.com/gp/researchers/text-and-data-mining","https://www.springernature.com/gp/researchers/text-and-data-mining"],"url":[{"@id":"https://link.springer.com/content/pdf/10.1007/s11548-022-02813-x.pdf"},{"@id":"https://link.springer.com/article/10.1007/s11548-022-02813-x/fulltext.html"}],"createdAt":"2022-12-20","modifiedAt":"2023-03-25","foaf:topic":[{"@id":"https://cir.nii.ac.jp/all?q=FOS:%20Computer%20and%20information%20sciences","dc:title":"FOS: Computer and information sciences"},{"@id":"https://cir.nii.ac.jp/all?q=Computer%20Science%20-%20Machine%20Learning","dc:title":"Computer Science - Machine Learning"},{"@id":"https://cir.nii.ac.jp/all?q=X-Rays","dc:title":"X-Rays"},{"@id":"https://cir.nii.ac.jp/all?q=Computer%20Vision%20and%20Pattern%20Recognition%20(cs.CV)","dc:title":"Computer Vision and Pattern Recognition (cs.CV)"},{"@id":"https://cir.nii.ac.jp/all?q=Image%20and%20Video%20Processing%20(eess.IV)","dc:title":"Image and Video Processing (eess.IV)"},{"@id":"https://cir.nii.ac.jp/all?q=Computer%20Science%20-%20Computer%20Vision%20and%20Pattern%20Recognition","dc:title":"Computer Science - Computer Vision and Pattern Recognition"},{"@id":"https://cir.nii.ac.jp/all?q=COVID-19","dc:title":"COVID-19"},{"@id":"https://cir.nii.ac.jp/all?q=006","dc:title":"006"},{"@id":"https://cir.nii.ac.jp/all?q=Electrical%20Engineering%20and%20Systems%20Science%20-%20Image%20and%20Video%20Processing","dc:title":"Electrical Engineering and Systems Science - Image and Video Processing"},{"@id":"https://cir.nii.ac.jp/all?q=Thorax","dc:title":"Thorax"},{"@id":"https://cir.nii.ac.jp/all?q=Machine%20Learning%20(cs.LG)","dc:title":"Machine Learning (cs.LG)"},{"@id":"https://cir.nii.ac.jp/all?q=Machine%20Learning","dc:title":"Machine Learning"},{"@id":"https://cir.nii.ac.jp/all?q=548","dc:title":"548"},{"@id":"https://cir.nii.ac.jp/all?q=FOS:%20Electrical%20engineering,%20electronic%20engineering,%20information%20engineering","dc:title":"FOS: Electrical engineering, electronic engineering, information engineering"},{"@id":"https://cir.nii.ac.jp/all?q=Humans","dc:title":"Humans"},{"@id":"https://cir.nii.ac.jp/all?q=Original%20Article","dc:title":"Original Article"},{"@id":"https://cir.nii.ac.jp/all?q=Pandemics","dc:title":"Pandemics"}],"project":[{"@id":"https://cir.nii.ac.jp/crid/1040566775682725120","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"20K19857"},{"@type":"JGN","@value":"JP20K19857"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-20K19857/"}],"notation":[{"@language":"ja","@value":"医用画像を対象とした機械学習に基づく逐次的データクレンジング技術の構築"},{"@language":"en","@value":"Development of a Sequential Data Cleansing Technique Based on Machine Learning for Medical Imaging"}]},{"@id":"https://cir.nii.ac.jp/crid/1040862776831613184","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"23K21676"},{"@type":"JGN","@value":"JP23K21676"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-23K21676/"}],"notation":[{"@language":"ja","@value":"エッジAI時代の超低演算量・低容量化を実現する汎用深層学習理論の構築"},{"@language":"en","@value":"General-purpose deep learning theory for ultra-low computational complexity and low capacity in the age of edge AI"}]}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1050869456403494784","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@language":"en","@value":"Compressed gastric image generation based on soft-label dataset distillation for medical data sharing"}]},{"@id":"https://cir.nii.ac.jp/crid/1360013170748308992","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images"}]},{"@id":"https://cir.nii.ac.jp/crid/1360013250195385728","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Machine Learning for COVID-19 needs global collaboration and data-sharing"}]},{"@id":"https://cir.nii.ac.jp/crid/1360013337830803456","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images"}]},{"@id":"https://cir.nii.ac.jp/crid/1360016868171363584","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey"}]},{"@id":"https://cir.nii.ac.jp/crid/1360016870036486912","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Exploring Simple Siamese Representation Learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360017285985483008","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"High-quality chest CT segmentation to assess the impact of COVID-19 disease"}]},{"@id":"https://cir.nii.ac.jp/crid/1360017286879042560","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Automated detection of COVID-19 using ensemble of transfer learning with deep convolutional neural network based on CT scans"}]},{"@id":"https://cir.nii.ac.jp/crid/1360017290178364544","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Explainable Deep Learning for Pulmonary Disease and Coronavirus COVID-19 Detection from X-rays"}]},{"@id":"https://cir.nii.ac.jp/crid/1360017290184564864","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Redesigning emergency department operations amidst a viral pandemic"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292621475068800","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles"}]},{"@id":"https://cir.nii.ac.jp/crid/1360298761838957696","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Identification of high-risk COVID-19 patients using machine learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360298761958243200","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Long-COVID diagnosis: From diagnostic to advanced AI-driven models"}]},{"@id":"https://cir.nii.ac.jp/crid/1360574095218528640","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Momentum Contrast for Unsupervised Visual Representation Learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360580236936956416","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Forecasting adverse surgical events using self-supervised transfer learning for physiological signals"}]},{"@id":"https://cir.nii.ac.jp/crid/1360580236957002496","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Chest X-ray image phase features for improved diagnosis of COVID-19 using convolutional neural network"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855567865740544","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep Residual Learning for Image Recognition"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855568616226560","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Densely Connected Convolutional Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1360857596654326144","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep learning approaches for COVID-19 detection based on chest X-ray images"}]},{"@id":"https://cir.nii.ac.jp/crid/1360857597479227392","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360861711916524160","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"COVID-19 detection in chest X-ray images using deep boosted hybrid learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360861712119508864","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"COVID‐19 and Oncology: Service transformation during pandemic"}]},{"@id":"https://cir.nii.ac.jp/crid/1360861713080944640","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Triplet Self-Supervised Learning for Gastritis Detection with Scarce Annotations"}]},{"@id":"https://cir.nii.ac.jp/crid/1360861713080949504","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Self-supervised Transfer Learning for Hand Mesh Recovery from Binocular Images"}]},{"@id":"https://cir.nii.ac.jp/crid/1360861714464890624","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Images"}]},{"@id":"https://cir.nii.ac.jp/crid/1360861714464891648","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"TriBYOL: Triplet BYOL for Self-Supervised Representation Learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360861715102851840","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Soft-Label Anonymous Gastric X-Ray Image Distillation"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418519657311872","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Rethinking the Inception Architecture for Computer Vision"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418520703556480","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks"}]},{"@id":"https://cir.nii.ac.jp/crid/1361699996490294912","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Self-Supervised Learning of Pretext-Invariant Representations"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981468459184256","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Models Genesis"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981469499696384","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Real-time RT-PCR in COVID-19 detection: issues affecting the results"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107369297144448","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Automated detection of COVID-19 cases using deep neural networks with X-ray images"}]},{"@id":"https://cir.nii.ac.jp/crid/1363670320867785088","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"ImageNet: A large-scale hierarchical image database"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233269186058624","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A Survey on Transfer Learning"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.1007/s11548-022-02813-x"},{"@type":"KAKEN","@value":"PRODUCT-24739933"},{"@type":"KAKEN","@value":"PRODUCT-24577867"},{"@type":"OPENAIRE","@value":"doi_dedup___::24074f567afcdd4c76825ed30c1dc41c"}]}