{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T14:48:58Z","timestamp":1794408538445,"version":"4.9.0"},"reference-count":52,"publisher":"IOP Publishing","issue":"24","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82072008"],"award-info":[{"award-number":["82072008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key R&D Program Guidance Projects in Liaoning Province","award":["2019JH8\/10300051"],"award-info":[{"award-number":["2019JH8\/10300051"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["N2124006-3"],"award-info":[{"award-number":["N2124006-3"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2021,12,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . Emphysema is characterized by the destruction and permanent enlargement of the alveoli in the lung. According to visual CT appearance, emphysema can be divided into three subtypes: centrilobular emphysema (CLE), panlobular emphysema (PLE), and paraseptal emphysema (PSE). Automating emphysema classification can help precisely determine the patterns of lung destruction and provide a quantitative evaluation.\n                    <jats:italic>Approach<\/jats:italic>\n                    . We propose a vision transformer (ViT) model to classify the emphysema subtypes via CT images. First, large patches (61\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mo>\u00d7<\/mml:mo>\n                        <mml:mspace width=\".25em\"\/>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    61) are cropped from CT images which contain the area of normal lung parenchyma, CLE, PLE, and PSE. After resizing, the large patch is divided into small patches and these small patches are converted to a sequence of patch embeddings by flattening and linear embedding. A class embedding is concatenated to the patch embedding, and the positional embedding is added to the resulting embeddings described above. Then, the obtained embedding is fed into the transformer encoder blocks to generate the final representation. Finally, the learnable class embedding is fed to a softmax layer to classify the emphysema.\n                    <jats:italic>Main results<\/jats:italic>\n                    . To overcome the lack of massive data, the transformer encoder blocks (pre-trained on ImageNet) are transferred and fine-tuned in our ViT model. The average accuracy of the pre-trained ViT model achieves 95.95% in our lab\u2019s own dataset, which is higher than that of AlexNet, Inception-V3, MobileNet-V2, ResNet34, and ResNet50. Meanwhile, the pre-trained ViT model outperforms the ViT model without the pre-training. The accuracy of our pre-trained ViT model is higher than or comparable to that by available methods for the public dataset.\n                    <jats:italic>Significance<\/jats:italic>\n                    . The results demonstrated that the proposed ViT model can accurately classify the subtypes of emphysema using CT images. The ViT model can help make an effective computer-aided diagnosis of emphysema, and the ViT method can be extended to other medical applications.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ac3dc8","type":"journal-article","created":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T17:22:45Z","timestamp":1637947365000},"page":"245016","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":88,"title":["A vision transformer for emphysema classification using CT images"],"prefix":"10.1088","volume":"66","author":[{"given":"Yanan","family":"Wu","sequence":"first","affiliation":[{"name":"Northeastern University"},{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-1939","authenticated-orcid":true,"given":"Shouliang","family":"Qi","sequence":"additional","affiliation":[{"name":"Northeastern University"},{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Sun","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuyue","family":"Xia","sequence":"additional","affiliation":[{"name":"Respiratory Department, Central Hospital Affiliated to Shenyang Medical College, Shenyang, 110024,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudong","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Qian","sequence":"additional","affiliation":[{"name":"University of Texas at El Paso"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,12,15]]},"reference":[{"key":"pmbac3dc8bib50","first-page":"4190\u201397","type":"conference-proceedings","article-title":"Quantifying attention flow in transformers","author":"Abnar","year":"2020"},{"key":"pmbac3dc8bib42","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1109\/ICCES51350.2021.9489033","type":"conference-proceedings","article-title":"Lung cancer detection and classification based on alexnet CNN","author":"Agarwal","year":"2021"},{"key":"pmbac3dc8bib31","doi-asserted-by":"publisher","first-page":"3286","DOI":"10.1109\/ICCV.2019.00338","type":"conference-proceedings","article-title":"Attention augmented convolutional networks","author":"Bello","year":"2019"},{"key":"pmbac3dc8bib5","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1109\/ISBI.2018.8363629","type":"conference-proceedings","article-title":"Emphysema classification using a multi-view convolutional network","author":"Bermejo-Pel\u00e1ez","year":"2018"},{"key":"pmbac3dc8bib27","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","type":"conference-proceedings","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"pmbac3dc8bib21","doi-asserted-by":"publisher","first-page":"121-5","DOI":"10.1109\/LSP.2020.3044547","type":"journal-article","article-title":"Non-autoregressive transformer for speech recognition","volume":"28","author":"Chen","year":"2020","journal-title":"IEEE Signal Process Lett."},{"key":"pmbac3dc8bib35","first-page":"1724-34","type":"conference-proceedings","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"pmbac3dc8bib23","first-page":"2978-88","type":"conference-proceedings","article-title":"Transformer-xl: Attentive language models beyond a fixed-length context","author":"Dai","year":"2019"},{"key":"pmbac3dc8bib24","doi-asserted-by":"publisher","first-page":"4171-86","DOI":"10.18653\/v1\/N19-1423","type":"conference-proceedings","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"Devlin","year":"2018"},{"key":"pmbac3dc8bib7","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","type":"preprint"},{"key":"pmbac3dc8bib34","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115519","type":"journal-article","article-title":"Detection of tuberculosis from chest x-ray images: Boosting the performance with vision transformer and transfer learning","volume":"184","author":"Duong","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"pmbac3dc8bib19","doi-asserted-by":"publisher","first-page":"38907","DOI":"10.1109\/ACCESS.2020.2974617","type":"journal-article","article-title":"Identification of COPD from multi-view snapshots of 3D lung airway tree via deep CNN","volume":"8","author":"Du","year":"2020","journal-title":"IEEE Access"},{"key":"pmbac3dc8bib47","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","type":"journal-article","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"pmbac3dc8bib41","first-page":"770","type":"conference-proceedings","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"pmbac3dc8bib30","article-title":"Generative adversarial transformers","author":"Hudson","year":"2021","type":"preprint"},{"key":"pmbac3dc8bib14","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1148\/radiol.2019191022","type":"journal-article","article-title":"Deep learning enables automatic classification of emphysema pattern at CT","volume":"294","author":"Humphries","year":"2020","journal-title":"Radiology"},{"key":"pmbac3dc8bib8","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/BMEI.2015.7401464","type":"conference-proceedings","article-title":"Analysis of scale variations of local features for accurate classification of Emphysema images","author":"Ibrahim","year":"2015"},{"key":"pmbac3dc8bib10","doi-asserted-by":"publisher","first-page":"16","DOI":"10.5430\/jbei.v4n1P16","type":"journal-article","article-title":"Identification of emphysema patterns in high resolution computed tomography images","volume":"4","author":"Ibrahim","year":"2018a","journal-title":"J. Biomed. Eng. Inform."},{"key":"pmbac3dc8bib11","doi-asserted-by":"publisher","first-page":"70-8","DOI":"10.11648\/j.ijmi.20170506.12","type":"journal-article","article-title":"On feature selection methods for accurate classification and analysis of emphysema ct images","volume":"5","author":"Ibrahim","year":"2018b","journal-title":"Int. J. Med. Imaging"},{"key":"pmbac3dc8bib16","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1109\/ELECO.2015.7394441","type":"conference-proceedings","article-title":"Emphysema discrimination from raw HRCT images by convolutional neural networks","author":"Karabulut","year":"2015"},{"key":"pmbac3dc8bib37","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1145\/3065386","type":"journal-article","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"pmbac3dc8bib13","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.23919\/Eusipco47968.2020.9287761","type":"conference-proceedings","article-title":"Robust Texture Features For Emphysema Classification In CT Images","author":"Li","year":"2021"},{"key":"pmbac3dc8bib52","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1109\/JSTARS.2020.2971763","type":"journal-article","article-title":"A CNN-Transformer hybrid approach for crop classification using multitemporal multisensor images","volume":"13","author":"Li","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Observations Remote Sens."},{"key":"pmbac3dc8bib51","article-title":"Convtransformer: A convolutional transformer network for video frame synthesis","author":"Liu","year":"2020","type":"preprint"},{"key":"pmbac3dc8bib43","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1145\/3483207.3483215","type":"conference-proceedings","article-title":"Lung Cancer Detection using a Dilated CNN with VGG16","author":"Lu","year":"2021"},{"key":"pmbac3dc8bib1","doi-asserted-by":"publisher","first-page":"219-33","DOI":"10.2147\/copd.2006.1.3.219","type":"journal-article","article-title":"Changing the burden of COPD mortality","volume":"1","author":"Mannino","year":"2006","journal-title":"Int. J. Chronic Obstructive Pulmonary Dis."},{"key":"pmbac3dc8bib3","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1109\/ISBI.2012.6235587","type":"conference-proceedings","article-title":"Emphysema quantification in a multi-scanner HRCT cohort using local intensity distributions","author":"Mendoza","year":"2012"},{"key":"pmbac3dc8bib49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/EHB.2015.7391573","type":"conference-proceedings","article-title":"Feature ensemble for quantitative analysis of emphysema in CT imaging","author":"Nava","year":"2015"},{"key":"pmbac3dc8bib15","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1007\/978-3-319-22879-2_42","type":"conference-proceedings","article-title":"Emphysema classification using convolutional neural networks","author":"Pei","year":"2015"},{"key":"pmbac3dc8bib6","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1109\/JBHI.2018.2890045","type":"journal-article","article-title":"Classification and quantification of emphysema using a multi-scale residual network","volume":"23","author":"Peng","year":"2019a","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pmbac3dc8bib17","doi-asserted-by":"publisher","first-page":"2327","DOI":"10.1109\/JBHI.2019.2963195","type":"journal-article","article-title":"Semi-supervised learning for semantic segmentation of emphysema with partial annotations","volume":"24","author":"Peng","year":"2019b","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pmbac3dc8bib33","doi-asserted-by":"publisher","first-page":"68\u201380","DOI":"10.5555\/3454287.3454294","type":"conference-proceedings","article-title":"Stand-alone self-attention in vision models","volume":"32","author":"Ramachandran","year":"2019"},{"key":"pmbac3dc8bib40","first-page":"4510","type":"conference-proceedings","article-title":"Mobilenetv2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"pmbac3dc8bib38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","type":"preprint"},{"key":"pmbac3dc8bib4","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1109\/TMI.2009.2038575","type":"journal-article","article-title":"quantitative analysis of pulmonary emphysema using local binary patterns","volume":"29","author":"Sorensen","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbac3dc8bib46","doi-asserted-by":"publisher","DOI":"10.3390\/app11062751","type":"journal-article","article-title":"Classification and predictions of lung diseases from chest x-rays using MOBILENET V2","volume":"11","author":"Souid","year":"2021","journal-title":"Appl. Sci."},{"key":"pmbac3dc8bib48","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1109\/LSP.2014.2337313","type":"journal-article","article-title":"Fast implementation of De Long\u2019s algorithm for comparing the areas under correlated receiver operating characteristic curves","volume":"21","author":"Sun","year":"2014","journal-title":"IEEE Signal Process. Lett."},{"key":"pmbac3dc8bib36","first-page":"3104-12","type":"conference-proceedings","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014"},{"key":"pmbac3dc8bib39","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1109\/CVPR.2016.308","type":"conference-proceedings","article-title":"Rethinking the inception architecture for computer vision","volume":"vol 1","author":"Szegedy","year":"2016"},{"key":"pmbac3dc8bib25","first-page":"10347-57","type":"conference-proceedings","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020"},{"key":"pmbac3dc8bib28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-87193-2_4","type":"preprint","article-title":"Medical transformer: gated axial-attention for medical image segmentation","author":"Valanarasu","year":"2021"},{"key":"pmbac3dc8bib20","doi-asserted-by":"publisher","first-page":"6000-10","DOI":"10.5555\/3295222.3295349","type":"conference-proceedings","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"pmbac3dc8bib22","first-page":"1810-22","type":"conference-proceedings","article-title":"Learning deep transformer models for machine translation","author":"Wang","year":"2019a"},{"key":"pmbac3dc8bib44","doi-asserted-by":"publisher","first-page":"146533","DOI":"10.1109\/ACCESS.2019.2946000","type":"journal-article","article-title":"Pulmonary image classification based on inception-v3 transfer learning model","volume":"7","author":"Wang","year":"2019b","journal-title":"IEEE Access"},{"key":"pmbac3dc8bib2","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1016\/S0033-8389(22)01199-X","type":"journal-article","article-title":"High-resolution CT of the lung parenchyma","volume":"27","author":"Webb","year":"1989","journal-title":"Radiol. Clin. North Am."},{"key":"pmbac3dc8bib32","article-title":"Visual transformers: token-based image representation and processing for computer vision","author":"Wu","year":"2020","type":"preprint"},{"key":"pmbac3dc8bib45","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1109\/TMI.2018.2876510","type":"journal-article","article-title":"Knowledge-based collaborative deep learning for benign-malignant lung nodule classification on chest CT","volume":"38","author":"Xie","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbac3dc8bib18","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab857d","type":"journal-article","article-title":"DCT-MIL: deep CNN transferred multiple instance learning for COPD identification using CT images","volume":"65","author":"Xu","year":"2020","journal-title":"Phys. Med. Biol."},{"key":"pmbac3dc8bib9","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/EMBC.2016.7590939","type":"conference-proceedings","article-title":"Texton and sparse representation based texture classification of lung parenchyma in CT images","author":"Yang","year":"2016"},{"key":"pmbac3dc8bib12","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1007\/s10044-018-00771-2","type":"journal-article","article-title":"A novel binary feature descriptor to discriminate normal and abnormal chest CT images using dissimilarity measures","volume":"22","author":"Yelampalli","year":"2019","journal-title":"Pattern Anal. Appl."},{"key":"pmbac3dc8bib29","first-page":"6881","type":"conference-proceedings","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"Zheng","year":"2020"},{"key":"pmbac3dc8bib26","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","type":"preprint"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:56:01Z","timestamp":1778777761000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ac3dc8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":52,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2021,12,15]]},"published-print":{"date-parts":[[2021,12,21]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ac3dc8","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,15]]},"assertion":[{"value":"A vision transformer for emphysema classification using CT images","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2021-08-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-11-26","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-12-15","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}