{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T18:54:50Z","timestamp":1793300090892,"version":"4.5.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T00:00:00Z","timestamp":1703635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T00:00:00Z","timestamp":1703635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003542","name":"Ministerium f\u00fcr Wissenschaft, Forschung und Kunst Baden-W\u00fcrttemberg","doi-asserted-by":"publisher","award":["32-5400\/58\/3"],"award-info":[{"award-number":["32-5400\/58\/3"]}],"id":[{"id":"10.13039\/501100003542","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Helmholtz Imaging"},{"name":"Deutsches Krebsforschungszentrum (DKFZ)"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Objectives<\/jats:title>\n                <jats:p>To quantify regional manifestations related to COPD as anomalies from a modeled distribution of normal-appearing lung on chest CT using a deep learning (DL) approach, and to assess its potential to predict disease severity.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Materials and methods<\/jats:title>\n                <jats:p>Paired inspiratory\/expiratory CT and clinical data from COPDGene and COSYCONET cohort studies were included. COPDGene data served as training\/validation\/test data sets (<jats:italic>N<\/jats:italic> = 3144\/786\/1310) and COSYCONET as external test set (<jats:italic>N<\/jats:italic> = 446). To differentiate low-risk (healthy\/minimal disease, [GOLD 0]) from COPD patients (GOLD 1\u20134), the self-supervised DL model learned semantic information from 50 \u00d7 50 \u00d7 50 voxel samples from segmented intact lungs. An anomaly detection approach was trained to quantify lung abnormalities related to COPD, as regional deviations. Four supervised DL models were run for comparison. The clinical and radiological predictive power of the proposed anomaly score was assessed using linear mixed effects models (LMM).<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The proposed approach achieved an area under the curve of 84.3 \u00b1 0.3 (<jats:italic>p<\/jats:italic> &lt; 0.001) for COPDGene and 76.3 \u00b1 0.6 (<jats:italic>p<\/jats:italic> &lt; 0.001) for COSYCONET, outperforming supervised models even when including only inspiratory CT. Anomaly scores significantly improved fitting of LMM for predicting lung function, health status, and quantitative CT features (emphysema\/air trapping; <jats:italic>p<\/jats:italic> &lt; 0.001). Higher anomaly scores were significantly associated with exacerbations for both cohorts (<jats:italic>p<\/jats:italic> &lt; 0.001) and greater dyspnea scores for COPDGene (<jats:italic>p<\/jats:italic> &lt; 0.001).<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>Quantifying heterogeneous COPD manifestations as anomaly offers advantages over supervised methods and was found to be predictive for lung function impairment and morphology deterioration.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Clinical relevance statement<\/jats:title>\n                <jats:p>Using deep learning, lung manifestations of COPD can be identified as deviations from normal-appearing chest CT and attributed an anomaly score which is consistent with decreased pulmonary function, emphysema, and air trapping.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Key Points<\/jats:title>\n                <jats:p>\u2022 <jats:italic>A self-supervised DL anomaly detection method discriminated low-risk individuals and COPD subjects, outperforming classic DL methods on two datasets (COPDGene AUC = 84.3%, COSYCONET AUC = 76.3%).<\/jats:italic><\/jats:p>\n                <jats:p>\u2022 <jats:italic>Our contrastive task exhibits robust performance even without the inclusion of expiratory images, while voxel-based methods demonstrate significant performance enhancement when incorporating expiratory images, in the COPDGene dataset.<\/jats:italic><\/jats:p>\n                <jats:p>\u2022 <jats:italic>Anomaly scores improved the fitting of linear mixed effects models in predicting clinical parameters and imaging alterations (p &lt; 0.001) and were directly associated with clinical outcomes (p &lt; 0.001).<\/jats:italic><\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s00330-023-10540-3","type":"journal-article","created":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T05:02:00Z","timestamp":1703653320000},"page":"4379-4392","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Prediction of disease severity in COPD: a deep learning approach for anomaly-based quantitative assessment of chest CT"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4133-1194","authenticated-orcid":false,"given":"Silvia D.","family":"Almeida","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Norajitra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carsten T.","family":"L\u00fcth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tassilo","family":"Wald","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivienn","family":"Weru","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Nolden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul F.","family":"J\u00e4ger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oyunbileg","family":"von Stackelberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claus Peter","family":"Heu\u00dfel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver","family":"Weinheimer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Biederer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans-Ulrich","family":"Kauczor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Klaus","family":"Maier-Hein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,27]]},"reference":[{"key":"10540_CR1","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1016\/S2213-2600(21)00511-7","volume":"10","author":"D Adeloye","year":"2022","unstructured":"Adeloye D, Song P, Zhu Y, Campbell H, Sheikh A, Rudan I (2022) Global, regional, and national prevalence of, and risk factors for, chronic obstructive pulmonary disease (COPD) in 2019: a systematic review and modelling analysis. Lancet Respir Med 10:447\u2013458","journal-title":"Lancet Respir Med"},{"key":"10540_CR2","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1513\/AnnalsATS.201506-388OC","volume":"12","author":"CH Martinez","year":"2015","unstructured":"Martinez CH, Mannino DM, Jaimes FA et al (2015) Undiagnosed obstructive lung disease in the United States. Associated factors and long-term mortality. Ann Am Thorac Soc 12:1788\u20131795","journal-title":"Ann Am Thorac Soc"},{"key":"10540_CR3","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1038\/s41533-017-0062-6","volume":"27","author":"E Andreeva","year":"2017","unstructured":"Andreeva E, Pokhaznikova M, Lebedev A, Moiseeva I, Kuznetsova O, Degryse JM (2017) Spirometry is not enough to diagnose COPD in epidemiological studies: a follow-up study. NPJ Prim Care Resp Med 27:62","journal-title":"NPJ Prim Care Resp Med"},{"key":"10540_CR4","first-page":"384","volume":"6","author":"KE Lowe","year":"2019","unstructured":"Lowe KE, Regan EA, Anzueto A et al (2019) COPDGene\u00ae 2019: redefining the diagnosis of chronic obstructive pulmonary disease. Chronic Obstr Pulm Dis 6:384\u2013399","journal-title":"Chronic Obstr Pulm Dis"},{"key":"10540_CR5","doi-asserted-by":"publisher","first-page":"683","DOI":"10.3348\/kjr.2018.0391","volume":"20","author":"HJ Koo","year":"2019","unstructured":"Koo HJ, Lee SM, Seo JB et al (2019) Prediction of pulmonary function in patients with chronic obstructive pulmonary disease: correlation with quantitative CT parameters. Korean J Radiol 20:683","journal-title":"Korean J Radiol"},{"key":"10540_CR6","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1148\/radiol.2018172294","volume":"288","author":"DA Lynch","year":"2018","unstructured":"Lynch DA, Moore CM, Wilson C et al (2018) CT-based visual classification of emphysema: association with mortality in the COPDGene Study. Radiology 288:859\u2013866","journal-title":"Radiology"},{"key":"10540_CR7","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1164\/rccm.201705-0860OC","volume":"197","author":"G Gonz\u00e1lez","year":"2018","unstructured":"Gonz\u00e1lez G, Ash SY, Vegas-S\u00e1nchez-Ferrero G et al (2018) Disease staging and prognosis in smokers using deep learning in chest computed tomography. Am J Respir Crit Care Med 197:193\u2013203","journal-title":"Am J Respir Crit Care Med"},{"key":"10540_CR8","doi-asserted-by":"publisher","first-page":"e259","DOI":"10.1016\/S2589-7500(20)30064-9","volume":"2","author":"LYW Tang","year":"2020","unstructured":"Tang LYW, Coxson HO, Lam S, Leipsic J, Tam RC, Sin DD (2020) Towards large-scale case-finding: training and validation of residual networks for detection of chronic obstructive pulmonary disease using low-dose CT. Lancet Digit Health 2:e259\u2013e267","journal-title":"Lancet Digit Health"},{"key":"10540_CR9","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1002\/mp.14673","volume":"48","author":"S Singla","year":"2021","unstructured":"Singla S, Gong M, Riley C, Sciurba F, Batmanghelich K (2021) Improving clinical disease subtyping and future events prediction through a chest CT-based deep learning approach. Med Phys 48:1168\u20131181","journal-title":"Med Phys"},{"key":"10540_CR10","doi-asserted-by":"publisher","first-page":"5319","DOI":"10.1007\/s00330-022-08632-7","volume":"32","author":"J Sun","year":"2022","unstructured":"Sun J, Liao X, Yan Y et al (2022) Detection and staging of chronic obstructive pulmonary disease using a computed tomography\u2013based weakly supervised deep learning approach. Eur Radiol 32:5319\u20135329","journal-title":"Eur Radiol"},{"key":"10540_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2018\/9493504","volume":"2018","author":"J Gawlitza","year":"2018","unstructured":"Gawlitza J, Trinkmann F, Scheffel H et al (2018) Time to exhale: additional value of expiratory chest CT in chronic obstructive pulmonary disease. Can Respir J 2018:1\u20139","journal-title":"Can Respir J"},{"key":"10540_CR12","doi-asserted-by":"publisher","first-page":"761804","DOI":"10.3389\/fmed.2021.761804","volume":"8","author":"X Cao","year":"2021","unstructured":"Cao X, Gao X, Yu N et al (2021) Potential value of expiratory CT in quantitative assessment of pulmonary vessels in COPD. Front Med 8:761804","journal-title":"Front Med"},{"key":"10540_CR13","doi-asserted-by":"crossref","unstructured":"Almeida SD,\u00a0L\u00fcth CT,\u00a0Norajitra T\u00a0et al (2023) cOOpD: reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations. in Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023 (eds. Greenspan H et al) vol. 14224 33\u201343 (Springer Nature Switzerland)","DOI":"10.1007\/978-3-031-43904-9_4"},{"key":"10540_CR14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.3109\/15412550903499522","volume":"7","author":"EA Regan","year":"2011","unstructured":"Regan EA, Hokanson JE, Murphy JR et al (2011) Genetic Epidemiology of COPD (COPDGene) study design. COPD: J Chronic Obstructive Pulm Dis 7:32\u201343","journal-title":"COPD: J Chronic Obstructive Pulm Dis"},{"key":"10540_CR15","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.rmed.2016.03.008","volume":"114","author":"A Karch","year":"2016","unstructured":"Karch A, Vogelmeier C, Welte T et al (2016) The German COPD cohort COSYCONET: aims, methods and descriptive analysis of the study population at baseline. Respir Med 114:27\u201337","journal-title":"Respir Med"},{"key":"10540_CR16","unstructured":"GOLD (2020) GOLD 2020 Global Strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease. https:\/\/goldcopd.org\/wp-content\/uploads\/2019\/11\/GOLD-2020-REPORT-ver1.0wms.pdf"},{"key":"10540_CR17","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1093\/geronb\/gbn014","volume":"64B","author":"FD Wolinsky","year":"2009","unstructured":"Wolinsky FD, Malmstrom TK, Miller JP, Andresen EM, Schootman M, Miller DK (2009) Antecedents of global decline in health-related quality of life among middle-aged African Americans. J Gerontol B Psychol Sci Soc Sci 64B:290\u2013295","journal-title":"J Gerontol B Psychol Sci Soc Sci"},{"key":"10540_CR18","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1378\/chest.10-2869","volume":"140","author":"MK Han","year":"2011","unstructured":"Han MK, Curran-Everett D, Dransfield MT et al (2011) Racial differences in quality of life in patients with COPD. Chest 140:1169\u20131176","journal-title":"Chest"},{"key":"10540_CR19","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1378\/chest.130.1.108","volume":"130","author":"WM Chatila","year":"2006","unstructured":"Chatila WM, Hoffman EA, Gaughan J, Robinswood GB, Criner GJ, National Emphysema Treatment Trial Research Group (2006) Advanced emphysema in African-American and white patients. Chest 130:108\u2013118","journal-title":"Chest"},{"key":"10540_CR20","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1148\/radiol.2392041968","volume":"239","author":"WR Webb","year":"2006","unstructured":"Webb WR (2006) Thin-section CT of the secondary pulmonary lobule: anatomy and the image\u2014the 2004 Fleischner Lecture. Radiology 239:322\u2013338","journal-title":"Radiology"},{"key":"10540_CR21","doi-asserted-by":"publisher","first-page":"e0194557","DOI":"10.1371\/journal.pone.0194557","volume":"13","author":"P Konietzke","year":"2018","unstructured":"Konietzke P, Weinheimer O, Wielp\u00fctz MO\u00a0 et al (2018) Validation of automated lobe segmentation on paired inspiratory-expiratory chest CT in 8\u201314 year-old children with cystic fibrosis. PLoS One 13:e0194557","journal-title":"PLoS One"},{"key":"10540_CR22","doi-asserted-by":"publisher","first-page":"175346662211486","DOI":"10.1177\/17534666221148663","volume":"17","author":"K Kahnert","year":"2023","unstructured":"Kahnert K, J\u00f6rres RA, Kauczor HU et al (2023) Standardized airway wall thickness Pi10 from routine CT scans of COPD patients as imaging biomarker for disease severity, lung function decline, and mortality. Ther Adv Respir Dis 17:175346662211486","journal-title":"Ther Adv Respir Dis"},{"key":"10540_CR23","doi-asserted-by":"publisher","first-page":"2502","DOI":"10.1007\/s00330-019-06577-y","volume":"30","author":"P Konietzke","year":"2020","unstructured":"Konietzke P, Wielp\u00fctz MO, Wagner WL et al (2020) Quantitative CT detects progression in COPD patients with severe emphysema in a 3-month interval. Eur Radiol 30:2502\u20132512","journal-title":"Eur Radiol"},{"key":"10540_CR24","doi-asserted-by":"publisher","first-page":"336","DOI":"10.2214\/AJR.11.7808","volume":"199","author":"OM Mets","year":"2012","unstructured":"Mets OM, Van Hulst RA, Jacobs C, Van Ginneken B, De Jong PA (2012) Normal range of emphysema and air trapping on CT in young men. AJR Am J Roentgenol 199:336\u2013340","journal-title":"AJR Am J Roentgenol"},{"key":"10540_CR25","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1378\/chest.08-0049","volume":"135","author":"A Busacker","year":"2009","unstructured":"Busacker A, Newell JD Jr, Keefe T et al (2009) A multivariate analysis of risk factors for the air-trapping asthmatic phenotype as measured by quantitative CT analysis. Chest 135:48\u201356","journal-title":"Chest"},{"key":"10540_CR26","doi-asserted-by":"publisher","first-page":"855640","DOI":"10.3389\/fmed.2022.855640","volume":"9","author":"R Lv","year":"2022","unstructured":"Lv R, Xie M, Jin H et al (2022) A preliminary study on the relationship between high-resolution computed tomography and pulmonary function in people at risk of developing chronic obstructive pulmonary disease. Front Med 9:855640","journal-title":"Front Med"},{"key":"10540_CR27","doi-asserted-by":"publisher","first-page":"2391","DOI":"10.1007\/s00330-009-1437-z","volume":"19","author":"CP Heussel","year":"2009","unstructured":"Heussel CP, Herth FJ, Kappes J et al (2009) Fully automatic quantitative assessment of emphysema in computed tomography: comparison with pulmonary function testing and normal values. Eur Radiol 19:2391\u20132402","journal-title":"Eur Radiol"},{"key":"10540_CR28","doi-asserted-by":"publisher","first-page":"e221488","DOI":"10.1148\/radiol.221488","volume":"307","author":"H Park","year":"2023","unstructured":"Park H, Yun J, Lee SM et al (2023) Deep learning\u2013based approach to predict pulmonary function at chest CT. Radiology 307:e221488","journal-title":"Radiology"},{"key":"10540_CR29","doi-asserted-by":"publisher","first-page":"4916","DOI":"10.1038\/s41598-021-84547-5","volume":"11","author":"F Li","year":"2021","unstructured":"Li F, Choi J, Zou C et al (2021) Latent traits of lung tissue patterns in former smokers derived by dual channel deep learning in computed tomography images. Sci Rep 11:4916","journal-title":"Sci Rep"},{"key":"10540_CR30","doi-asserted-by":"publisher","unstructured":"L\u00fcth CT,\u00a0 Zimmerer D, Koehler G et al (2023) CRADL: Contrastive Representations for Unsupervised Anomaly Detection and Localization. https:\/\/doi.org\/10.48550\/ARXIV.2301.02126","DOI":"10.48550\/ARXIV.2301.02126"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-023-10540-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-023-10540-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-023-10540-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T08:09:51Z","timestamp":1719562191000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-023-10540-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,27]]},"references-count":30,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["10540"],"URL":"https:\/\/doi.org\/10.1007\/s00330-023-10540-3","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,27]]},"assertion":[{"value":"5 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The scientific guarantor of this publication is Prof. Dr. Klaus Maier-Hein.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"One of the authors has significant statistical expertise: Vivienn Weru, Division of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, Germany.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was obtained from all subjects (patients) in this study.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The used cohorts (COPDGene and COSYCONET) are open access, therefore have been reported in several previous studies, including our own:Almeida, S.D. et al (2023). cOOpD: reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations. In: Greenspan, H., et al Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14224. Springer, Cham. .","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"value":"\u2022 retrospective\u2022 observational\u2022 multicenter study","order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}