{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:04:21Z","timestamp":1787313861047,"version":"build-2736575974"},"reference-count":57,"publisher":"European Respiratory Society (ERS)","issue":"3","license":[{"start":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T00:00:00Z","timestamp":1626307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.ersjournals.com\/user-licence"}],"funder":[{"DOI":"10.13039\/501100008980","name":"Soci\u00e9t\u00e9 Fran\u00e7aise de Radiologie","doi-asserted-by":"publisher","award":["Alain Rahmouni 2019-2020"],"award-info":[{"award-number":["Alain Rahmouni 2019-2020"]}],"id":[{"id":"10.13039\/501100008980","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IdEx Bordeaux","award":["IdEx, ANR-10-IDEX-03-02"],"award-info":[{"award-number":["IdEx, ANR-10-IDEX-03-02"]}]}],"content-domain":{"domain":["publications.ersnet.org"],"crossmark-restriction":true},"short-container-title":["Eur Respir J"],"accepted":{"date-parts":[[2021,7,2]]},"published-print":{"date-parts":[[2022,3]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Chest computed tomography (CT) remains the imaging standard for demonstrating cystic fibrosis (CF) airway structural disease\n                      <jats:italic>in vivo<\/jats:italic>\n                      . However, visual scoring systems as an outcome measure are time consuming, require training and lack high reproducibility. Our objective was to validate a fully automated artificial intelligence (AI)-driven scoring system of CF lung disease severity.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Data were retrospectively collected in three CF reference centres, between 2008 and 2020, in 184 patients aged 4\u201354\u2005years. An algorithm using three 2D convolutional neural networks was trained with 78 patients\u2019 CT scans (23\u200a530 CT slices) for the semantic labelling of bronchiectasis, peribronchial thickening, bronchial mucus, bronchiolar mucus and collapse\/consolidation. 36 patients\u2019 CT scans (11\u200a435 CT slices) were used for testing\n                      <jats:italic>versus<\/jats:italic>\n                      ground-truth labels. The method's clinical validity was assessed in an independent group of 70 patients with or without lumacaftor\/ivacaftor treatment (n=10 and n=60, respectively) with repeat examinations. Similarity and reproducibility were assessed using the Dice coefficient, correlations using the Spearman test, and paired comparisons using the Wilcoxon rank test.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The overall pixelwise similarity of AI-driven\n                      <jats:italic>versus<\/jats:italic>\n                      ground-truth labels was good (Dice 0.71). All AI-driven volumetric quantifications had moderate to very good correlations to a visual imaging scoring (p&lt;0.001) and fair to good correlations to forced expiratory volume in 1\u2005s % predicted at pulmonary function tests (p&lt;0.001). Significant decreases in peribronchial thickening (p=0.005), bronchial mucus (p=0.005) and bronchiolar mucus (p=0.007) volumes were measured in patients with lumacaftor\/ivacaftor. Conversely, bronchiectasis (p=0.002) and peribronchial thickening (p=0.008) volumes increased in patients without lumacaftor\/ivacaftor. The reproducibility was almost perfect (Dice &gt;0.99).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI allows fully automated volumetric quantification of CF-related modifications over an entire lung. The novel scoring system could provide a robust disease outcome in the era of effective CF transmembrane conductance regulator modulator therapy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1183\/13993003.00844-2021","type":"journal-article","created":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T12:10:20Z","timestamp":1626351020000},"page":"2100844","update-policy":"https:\/\/doi.org\/10.1183\/ers-crossmark-policy","source":"Crossref","is-referenced-by-count":46,"title":["Artificial intelligence in computed tomography for quantifying lung changes in the era of CFTR modulators"],"prefix":"10.1183","volume":"59","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0251-6639","authenticated-orcid":false,"given":"Gael","family":"Dournes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chase S.","family":"Hall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4356-9622","authenticated-orcid":false,"given":"Matthew M.","family":"Willmering","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan S.","family":"Brody","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julie","family":"Macey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephanie","family":"Bui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baudouin","family":"Denis de Senneville","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4702-0343","authenticated-orcid":false,"given":"Patrick","family":"Berger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"Laurent","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5953-9882","authenticated-orcid":false,"given":"Ilyes","family":"Benlala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason C.","family":"Woods","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"81","published-online":{"date-parts":[[2021,7,15]]},"reference":[{"key":"2024102102351918000_59.3.2100844.1","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/S2213-2600(19)30337-6","article-title":"The future of cystic fibrosis care: a global perspective","volume":"8","author":"Bell","year":"2020","journal-title":"Lancet Respir Med"},{"key":"2024102102351918000_59.3.2100844.2","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1016\/S2213-2600(16)30121-7","article-title":"Efficacy and safety of lumacaftor\/ivacaftor combination therapy in patients with cystic fibrosis homozygous for Phe508del CFTR by pulmonary function subgroup: a pooled analysis","volume":"4","author":"Elborn","year":"2016","journal-title":"Lancet Respir Med"},{"key":"2024102102351918000_59.3.2100844.3","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201606-1250PP"},{"key":"2024102102351918000_59.3.2100844.4","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1513\/AnnalsATS.202008-1054OC","article-title":"Effects of lumacaftor\u2013ivacaftor on lung clearance index, magnetic resonance imaging and airway microbiome in Phe508del homozygous patients with cystic fibrosis","volume":"18","author":"Graeber","year":"2021","journal-title":"Ann Am Thorac Soc"},{"key":"2024102102351918000_59.3.2100844.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.prrv.2006.04.002"},{"key":"2024102102351918000_59.3.2100844.6","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2014-205499"},{"key":"2024102102351918000_59.3.2100844.7","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1513\/pats.200611-183HT","article-title":"Use of lung imaging studies as outcome measures for development of new therapies in cystic fibrosis","volume":"4","author":"Ramsey","year":"2007","journal-title":"Proc Am Thorac Soc"},{"key":"2024102102351918000_59.3.2100844.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2004.02.038"},{"key":"2024102102351918000_59.3.2100844.9","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.179.3.2027992"},{"key":"2024102102351918000_59.3.2100844.10","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.213.2.r99nv04537"},{"key":"2024102102351918000_59.3.2100844.11","doi-asserted-by":"publisher","DOI":"10.1007\/s00247-013-2867-y"},{"key":"2024102102351918000_59.3.2100844.12","doi-asserted-by":"publisher","DOI":"10.1097\/01.rti.0000203937.82276.ce"},{"key":"2024102102351918000_59.3.2100844.13","doi-asserted-by":"crossref","first-page":"e0240898","DOI":"10.1371\/journal.pone.0240898","article-title":"Chest computed tomography outcomes in a randomized clinical trial in cystic fibrosis: lessons learned from the first ataluren phase 3 study","volume":"15","author":"Tiddens","year":"2020","journal-title":"PLoS One"},{"key":"2024102102351918000_59.3.2100844.14","unstructured":"Radiological Society of North America . International radiological societies tackle radiologist shortage. 2020. www.rsna.org\/news\/2020\/february\/international-radiology-societies-and-shortage Date last accessed: 1 June 2021."},{"key":"2024102102351918000_59.3.2100844.15","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201501-0061OC"},{"key":"2024102102351918000_59.3.2100844.16","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1378\/chest.13-0588","article-title":"Automated CT scan scores of bronchiectasis and air trapping in cystic fibrosis","volume":"145","author":"DeBoer","year":"2014","journal-title":"Chest"},{"key":"2024102102351918000_59.3.2100844.17","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1097\/RTI.0000000000000387","article-title":"Deep learning applications in chest radiography and computed tomography: current state of the art","volume":"34","author":"Lee","year":"2019","journal-title":"J Thorac Imaging"},{"key":"2024102102351918000_59.3.2100844.18","doi-asserted-by":"crossref","first-page":"2021","DOI":"10.1007\/s00330-019-06564-3","article-title":"Deep learning: definition and perspectives for thoracic imaging","volume":"30","author":"Chassagnon","year":"2020","journal-title":"Eur Radiol"},{"key":"2024102102351918000_59.3.2100844.19","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020200029"},{"key":"2024102102351918000_59.3.2100844.20","doi-asserted-by":"crossref","first-page":"e191095","DOI":"10.1001\/jamanetworkopen.2019.1095","article-title":"Development and validation of a deep learning-based automated detection algorithm for major thoracic diseases on chest radiographs","volume":"2","author":"Hwang","year":"2019","journal-title":"JAMA Netw Open"},{"key":"2024102102351918000_59.3.2100844.21","doi-asserted-by":"crossref","unstructured":"Marques F , de Bruijne M , Dubost F , et al. Quantification of lung abnormalities in cystic fibrosis using deep networks. 2018. www.spiedigitallibrary.org\/conference-proceedings-of-spie\/10574\/2292188\/Quantification-of-lung-abnormalities-in-cystic-fibrosis-using-deep-networks\/10.1117\/12.2292188.full Date last accessed: 1 March 2021.","DOI":"10.1117\/12.2292188"},{"key":"2024102102351918000_59.3.2100844.22","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1007\/s11760-019-01447-y","article-title":"Lung HRCT pattern classification for cystic fibrosis using convolutional neural network","volume":"13","author":"Nezamabadi","year":"2019","journal-title":"SIViP"},{"key":"2024102102351918000_59.3.2100844.23","unstructured":"Ciompi F , Palaioroutas A , Loeve M , et al. Lung tissue classification in severe advanced cystic fibrosis from CT scans. 2011. www.lungworkshop.org\/2011\/resources\/Lung-Tissue-Classification-in-Severe-Advanced-Cystic-Fibrosis-from-CT-Scans.pdf Date last accessed: 19 August 2021."},{"key":"2024102102351918000_59.3.2100844.24","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.jcf.2019.04.016","article-title":"Deep learning to automate Brasfield chest radiographic scoring for cystic fibrosis","volume":"19","author":"Zucker","year":"2020","journal-title":"J Cyst Fibros"},{"key":"2024102102351918000_59.3.2100844.25","unstructured":"Temple RJ . A regulatory authority's opinion about surrogate endpoints. In: Nimmo WS , Tucker GT , eds. Clinical Measurement in Drug Evaluation. New York, Wiley, 1995; pp. 3\u201322."},{"key":"2024102102351918000_59.3.2100844.26","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/j.jcf.2018.02.006","article-title":"ECFS best practice guidelines: the 2018 revision","volume":"17","author":"Castellani","year":"2018","journal-title":"J Cyst Fibros"},{"key":"2024102102351918000_59.3.2100844.27","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.05.00034805"},{"key":"2024102102351918000_59.3.2100844.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcf.2014.03.010"},{"key":"2024102102351918000_59.3.2100844.29","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101860"},{"key":"2024102102351918000_59.3.2100844.30","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199409083311003"},{"key":"2024102102351918000_59.3.2100844.31","doi-asserted-by":"publisher","DOI":"10.1118\/1.4752209"},{"key":"2024102102351918000_59.3.2100844.32","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2462070712"},{"key":"2024102102351918000_59.3.2100844.33","doi-asserted-by":"crossref","unstructured":"Szegedy C , Ioffe S , Vanhoucke V , et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning. arXiv 2016; preprint [http:\/\/arxiv.org\/abs\/1602.07261].","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"2024102102351918000_59.3.2100844.34","doi-asserted-by":"crossref","unstructured":"Ronneberger O , Fischer P , Brox T . U-Net: convolutional networks for biomedical image segmentation. arXiv 2015; preprint [http:\/\/arxiv.org\/abs\/1505.04597].","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2024102102351918000_59.3.2100844.35","doi-asserted-by":"crossref","unstructured":"He K , Zhang X , Ren S , et al. Deep residual learning for image recognition. arXiv 2015; preprint [http:\/\/arxiv.org\/abs\/1512.03385].","DOI":"10.1109\/CVPR.2016.90"},{"key":"2024102102351918000_59.3.2100844.36","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.asoc.2015.02.043","article-title":"The use of vicinal-risk minimization for training decision trees","volume":"31","author":"Cao","year":"2015","journal-title":"Appl Soft Comput"},{"key":"2024102102351918000_59.3.2100844.37","doi-asserted-by":"crossref","unstructured":"Zhang H , Cisse M , Dauphin YN , et al. mixup: beyond empirical risk minimization. arXiv 2017; preprint [http:\/\/arxiv.org\/abs\/1710.09412].","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"2024102102351918000_59.3.2100844.38","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1109\/TBCAS.2019.2955641","article-title":"A fully embedded adaptive real-time hand gesture classifier leveraging HD-sEMG and deep learning","volume":"14","author":"Tam","year":"2020","journal-title":"IEEE Trans Biomed Circuits Syst"},{"key":"2024102102351918000_59.3.2100844.39","unstructured":"Haute Autorit\u00e9 de Sant\u00e9, France . Protocole National de Diagnostic et de Soin. [National Diagnostic and Care Protocol.] 2017. www.has-sante.fr\/portail\/upload\/docs\/application\/pdf\/2017-09\/pnds_2017_vf1.pdf Date last accessed: 1 March 2021."},{"key":"2024102102351918000_59.3.2100844.40","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-015-0068-x"},{"key":"2024102102351918000_59.3.2100844.41","doi-asserted-by":"publisher","DOI":"10.1177\/096228029900800204"},{"key":"2024102102351918000_59.3.2100844.42","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"2024102102351918000_59.3.2100844.43","unstructured":"Hinkle DE , Wiersma W , Jurs SG . Applied Statistics for the Behavioral Sciences. 5th Edn. Boston, Houghton Mifflin, 2003."},{"key":"2024102102351918000_59.3.2100844.44","doi-asserted-by":"publisher","DOI":"10.1111\/opo.12131"},{"key":"2024102102351918000_59.3.2100844.45","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"2024102102351918000_59.3.2100844.46","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.05.00035205"},{"key":"2024102102351918000_59.3.2100844.47","unstructured":"European Cystic Fibrosis Society . ECFS Patient Registry Annual Data Report. 2018. www.ecfs.eu\/sites\/default\/files\/general-content-files\/working-groups\/ecfs-patient-registry\/ECFSPR_Report_2018_v1.4.pdf Date last accessed: 1 March 2021."},{"key":"2024102102351918000_59.3.2100844.48","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2017.10.005"},{"key":"2024102102351918000_59.3.2100844.49","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01918-2015"},{"key":"2024102102351918000_59.3.2100844.50","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200503-401PP"},{"key":"2024102102351918000_59.3.2100844.51","doi-asserted-by":"crossref","first-page":"1182","DOI":"10.1002\/ppul.22991","article-title":"Tracking CF disease progression with CT and respiratory symptoms in a cohort of children aged 6\u201319\u2005years","volume":"49","author":"Tepper","year":"2014","journal-title":"Pediatr Pulmonol"},{"key":"2024102102351918000_59.3.2100844.52","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01601-2015"},{"key":"2024102102351918000_59.3.2100844.53","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1016\/j.chest.2020.12.008","article-title":"The clinical use of lung MRI in cystic fibrosis: what, now, how?","volume":"159","author":"Dournes","year":"2021","journal-title":"Chest"},{"key":"2024102102351918000_59.3.2100844.54","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1002\/jmri.26734","article-title":"Deep convolutional neural networks with multiplane consensus labeling for lung function quantification using UTE proton MRI","volume":"50","author":"Zha","year":"2019","journal-title":"J Magn Reson Imaging"},{"key":"2024102102351918000_59.3.2100844.55","doi-asserted-by":"crossref","first-page":"1414","DOI":"10.1002\/ppul.23787","article-title":"Quantitative assessment of airway dimensions in young children with cystic fibrosis lung disease using chest computed tomography","volume":"52","author":"Kuo","year":"2017","journal-title":"Pediatr Pulmonol"},{"key":"2024102102351918000_59.3.2100844.56","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.lpm.2015.12.003","article-title":"Scanner thoracique ultra-basse dose: la mort de la radiographie thoracique? [Ultra-low dose chest CT: the end of chest radiograph?]","volume":"45","author":"Ludes","year":"2016","journal-title":"Presse Med"},{"key":"2024102102351918000_59.3.2100844.57","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.radonc.2020.06.049","article-title":"Magnetic resonance-based synthetic computed tomography images generated using generative adversarial networks for nasopharyngeal carcinoma radiotherapy treatment planning","volume":"150","author":"Peng","year":"2020","journal-title":"Radiother Oncol"}],"container-title":["European Respiratory Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1183\/13993003.00844-2021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:46:14Z","timestamp":1740357974000},"score":1,"resource":{"primary":{"URL":"https:\/\/publications.ersnet.org\/lookup\/doi\/10.1183\/13993003.00844-2021"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,15]]},"references-count":57,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,3,3]]},"published-print":{"date-parts":[[2022,3]]}},"alternative-id":["10.1183\/13993003.00844-2021"],"URL":"https:\/\/doi.org\/10.1183\/13993003.00844-2021","relation":{},"ISSN":["0903-1936","1399-3003"],"issn-type":[{"value":"0903-1936","type":"print"},{"value":"1399-3003","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,15]]}}}