{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:47:13Z","timestamp":1792086433903,"version":"4.4.0"},"reference-count":35,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Pulmonary sarcoidosis is a heterogeneous granulomatous disease with a broad spectrum of clinical and radiological manifestations. While the traditional Scadding classification based on chest radiography remains a cornerstone of disease staging, it provides limited information regarding parenchymal involvement and poorly correlates with functional impairment. High-resolution computed tomography (HRCT) offers superior sensitivity in detecting subtle and early interstitial changes, yet standardized HRCT-based classification systems for sarcoidosis remain underdeveloped.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>This study aimed to propose and validate a novel HRCT-based classification of pulmonary sarcoidosis grounded in expert consensus, to assess its relationship with clinical symptoms, pulmonary function, and quality of life, and to compare it with data-driven radiological groupings obtained through cluster analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      The study population included patients with confirmed pulmonary sarcoidosis managed at a tertiary referral center, either as inpatients or outpatients. HRCT scans were evaluated using a modified version of the previously published questionnaire, capturing 22 radiological features per lung lobe. Based on characteristic imaging patterns, four expert-defined subtypes were proposed: (1) Lymphonodal, (2) Disseminated-Nodular, (3) Central, and (4) Fibrotic. Symptom burden was assessed using the Fatigue Assessment Scale (FAS) and the Sarcoidosis Health Questionnaire (SHQ). Spirometric and gas transfer parameters (FEV\n                      <jats:sub>1<\/jats:sub>\n                      , FVC, T\n                      <jats:sub>L,CO<\/jats:sub>\n                      ) were recorded. Statistical analyses included ANOVA, Spearman\u2019s correlation, and hierarchical clustering (Ward\u2019s method with Euclidean distances), with Cohen\u2019s kappa used to evaluate concordance between classification systems.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Four distinct HRCT subtypes were identified through expert assessment, each reflecting varying degrees and distributions of parenchymal involvement. These subtypes differed significantly in clinical and functional presentation. The fibrotic subtype demonstrated the most severe functional impairment, with the highest prevalence of abnormal spirometry and diffusion deficits. In contrast, the lymphonodal subtype exhibited preserved lung function and minimal symptomatology. The Van den Heuvel radiological severity score showed strong correlation with radiological subtype and was significantly associated with FEV\n                      <jats:sub>1<\/jats:sub>\n                      , FVC, T\n                      <jats:sub>L,CO<\/jats:sub>\n                      , and SHQ scores. Unsupervised cluster analysis independently identified four data-driven radiological groups that partially overlapped with expert-defined subtypes, particularly in nodular and central patterns. However, the fibrotic subtype showed less distinct clustering, underscoring its radiological complexity. The agreement between expert-defined and cluster-derived classifications was limited (\u03ba\u2009=\u20090.271), suggesting that the two approaches capture complementary but distinct dimensions of disease morphology.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec005\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>HRCT-based radiological subtypes of pulmonary sarcoidosis reflect clinically meaningful differences in symptom burden, ventilatory function, and radiological severity. While expert-driven and data-driven classifications show limited concordance, both provide valuable insights into disease heterogeneity. Radiological phenotyping using HRCT may serve as a practical adjunct to traditional staging systems, offering improved risk stratification and guiding personalized treatment decisions. Further prospective validation is needed to determine its utility in routine clinical practice and to explore its integration with emerging clinical and molecular phenotyping strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0358960","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:24:16Z","timestamp":1792085056000},"page":"e0358960","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Expert intuition vs. Algorithmic clustering: Mapping radiological subtypes in pulmonary sarcoidosis"],"prefix":"10.1371","volume":"21","author":[{"given":"Justyna","family":"Sobczak","sequence":"first","affiliation":[{"name":"Medical University of Lodz","place":["Lodz, Poland"],"department":["Department of Pneumology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam J.","family":"Bia\u0142as","sequence":"additional","affiliation":[{"name":"Medical University of Lodz","place":["Lodz, Poland"],"department":["Department of Pneumology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1287-9289","authenticated-orcid":true,"given":"Joanna","family":"Mi\u0142kowska-Dymanowska","sequence":"additional","affiliation":[{"name":"Medical University of Lodz","place":["Lodz, Poland"],"department":["Department of Pneumology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u0141ukasz","family":"Gwadera","sequence":"additional","affiliation":[{"name":"Medical University of Lodz","place":["Lodz, Poland"],"department":["Department of Pneumology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patryk","family":"Sobczak","sequence":"additional","affiliation":[{"name":"Medical University of Lodz","place":["Lodz, Poland"],"department":["Department of Pneumology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katarzyna","family":"Torbiarczyk","sequence":"additional","affiliation":[{"name":"Medical University of Lodz","place":["Lodz, Poland"],"department":["Department of Pneumology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"\u0141acwik","sequence":"additional","affiliation":[{"name":"Medical University of Lodz","place":["Lodz, Poland"],"department":["Department of Pneumology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4506-6006","authenticated-orcid":true,"given":"Wojciech J.","family":"Piotrowski","sequence":"additional","affiliation":[{"name":"Medical University of Lodz","place":["Lodz, Poland"],"department":["Department of Pneumology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"issue":"2","key":"pone.0358960.ref001","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1164\/ajrccm.160.2.ats4-99","article-title":"Statement on sarcoidosis","volume":"160","year":"1999","journal-title":"Am J Respir Crit Care Med"},{"issue":"9923","key":"pone.0358960.ref002","first-page":"1155","article-title":"M\u00fcller-Quernheim J. Sarcoidosis","volume":"383","author":"D Valeyre","year":"2014","journal-title":"Lancet"},{"issue":"2","key":"pone.0358960.ref003","first-page":"178","article-title":"Clinical findings in 715 patients with newly detected pulmonary sarcoidosis: results of a cooperative study in former West Germany and Switzerland","volume":"15","author":"R Loddenkemper","year":"1998","journal-title":"Sarcoidosis Vasc Diffuse Lung Dis"},{"issue":"5","key":"pone.0358960.ref004","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1164\/rccm.201006-0865CI","article-title":"A concise review of pulmonary sarcoidosis","volume":"183","author":"RP Baughman","year":"2011","journal-title":"Am J Respir Crit Care Med"},{"issue":"2","key":"pone.0358960.ref005","first-page":"312","article-title":"Sarcoidosis","volume":"70","author":"JJ Wu","year":"2004","journal-title":"Am Fam Physician"},{"issue":"3","key":"pone.0358960.ref006","first-page":"325","article-title":"Sarcoidosis: a review for the internist","volume":"13","author":"E Bargagli","year":"2018","journal-title":"Intern Emerg Med"},{"issue":"4","key":"pone.0358960.ref007","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/j.ccm.2015.08.004","article-title":"Chest imaging","volume":"36","author":"RG Keijsers","year":"2015","journal-title":"Clin Chest Med"},{"issue":"1","key":"pone.0358960.ref008","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1055\/s-2007-970336","article-title":"Imaging in sarcoidosis","volume":"28","author":"H Nunes","year":"2007","journal-title":"Semin Respir Crit Care Med"},{"issue":"1","key":"pone.0358960.ref009","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s12016-015-8478-7","article-title":"Imaging of sarcoidosis","volume":"49","author":"M Silva","year":"2015","journal-title":"Clin Rev Allergy Immunol"},{"issue":"5261","key":"pone.0358960.ref010","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1136\/bmj.2.5261.1165","article-title":"Prognosis of intrathoracic sarcoidosis in England","volume":"2","author":"JG Scadding","year":"1961","journal-title":"Br Med J"},{"issue":"1","key":"pone.0358960.ref011","first-page":"46","article-title":"A simple radiographic scoring method for monitoring pulmonary sarcoidosis: relations between radiographic scores, dyspnoea grade and respiratory function in the British thoracic society study of long-term corticosteroid treatment","volume":"14","author":"MF Muers","year":"1997","journal-title":"Sarcoidosis Vasc Diffuse Lung Dis"},{"issue":"3","key":"pone.0358960.ref012","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1136\/thx.51.3.238","article-title":"British Thoracic Society Sarcoidosis study: effects of long term corticosteroid treatment","volume":"51","author":"GJ Gibson","year":"1996","journal-title":"Thorax"},{"issue":"3","key":"pone.0358960.ref013","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1164\/rccm.200705-742OC","article-title":"Phenotyping sarcoidosis from a pulmonary perspective","volume":"177","author":"A Prasse","year":"2008","journal-title":"Am J Respir Crit Care Med"},{"issue":"1","key":"pone.0358960.ref014","doi-asserted-by":"crossref","first-page":"1800050","DOI":"10.1183\/13993003.00050-2018","article-title":"It\u2019s time to evolve from scadding: phenotyping sarcoidosis","volume":"51","author":"DA Culver","year":"2018","journal-title":"Eur Respir J"},{"key":"pone.0358960.ref015","doi-asserted-by":"crossref","first-page":"600","DOI":"10.12688\/f1000research.11068.1","article-title":"Is it time to scrap scadding and adopt computed tomography for initial evaluation of sarcoidosis?","volume":"7","author":"A Levy","year":"2018","journal-title":"F1000Res"},{"issue":"261","key":"pone.0358960.ref016","first-page":"118","article-title":"Radiological examinations in the diagnosis and monitoring of pulmonary sarcoidosis","volume":"44","author":"WJ Piotrowski","year":"2018","journal-title":"Pol Merkur Lekarski"},{"issue":"4","key":"pone.0358960.ref017","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1007\/s00330-013-3088-3","article-title":"Imaging aspects of the diagnosis of sarcoidosis","volume":"24","author":"P Spagnolo","year":"2014","journal-title":"Eur Radiol"},{"issue":"1","key":"pone.0358960.ref018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2214\/ajr.135.1.1","article-title":"CT of the solitary pulmonary nodule","volume":"135","author":"SS Siegelman","year":"1980","journal-title":"AJR Am J Roentgenol"},{"issue":"3","key":"pone.0358960.ref019","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1097\/00004424-198803000-00003","article-title":"Optimization of computed tomography technique to demonstrate the fine structure of the lung","volume":"23","author":"K Murata","year":"1988","journal-title":"Invest Radiol"},{"issue":"6","key":"pone.0358960.ref020","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1097\/00004728-198212000-00005","article-title":"Factors influencing quantitative CT measurements of solitary pulmonary nodules","volume":"6","author":"EA Zerhouni","year":"1982","journal-title":"J Comput Assist Tomogr"},{"issue":"2","key":"pone.0358960.ref021","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1148\/radiology.163.2.3562834","article-title":"High-resolution CT of the lungs: an optimal approach","volume":"163","author":"JR Mayo","year":"1987","journal-title":"Radiology"},{"issue":"1","key":"pone.0358960.ref022","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1148\/radiology.171.1.2928513","article-title":"Chronic diffuse infiltrative lung disease: comparison of diagnostic accuracy of CT and chest radiography","volume":"171","author":"JR Mathieson","year":"1989","journal-title":"Radiology"},{"issue":"4","key":"pone.0358960.ref023","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1097\/00005382-199910000-00007","article-title":"A CT sign of chronic pulmonary arterial hypertension: the ratio of main pulmonary artery to aortic diameter","volume":"14","author":"CS Ng","year":"1999","journal-title":"J Thorac Imaging"},{"issue":"2","key":"pone.0358960.ref024","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/S2213-2600(13)70276-5","article-title":"An integrated clinicoradiological staging system for pulmonary sarcoidosis: a case-cohort study","volume":"2","author":"SL Walsh","year":"2014","journal-title":"Lancet Respir Med"},{"issue":"9","key":"pone.0358960.ref025","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1007\/s00330-015-3685-4","article-title":"Chest computed tomography-based scoring of thoracic sarcoidosis: inter-rater reliability of CT abnormalities","volume":"25","author":"DA Van den Heuvel","year":"2015","journal-title":"Eur Radiol"},{"issue":"3","key":"pone.0358960.ref026","doi-asserted-by":"crossref","first-page":"822","DOI":"10.3390\/jcm13030822","article-title":"Imaging of pulmonary sarcoidosis-a review","volume":"13","author":"GL Bailey","year":"2024","journal-title":"J Clin Med"},{"issue":"5","key":"pone.0358960.ref027","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1016\/S2213-2600(23)00267-9","article-title":"High-resolution CT phenotypes in pulmonary sarcoidosis: a multinational Delphi consensus study","volume":"12","author":"SR Desai","year":"2024","journal-title":"Lancet Respir Med"},{"key":"pone.0358960.ref028","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1348\/1359107041557048","article-title":"Measuring fatigue in sarcoidosis: the Fatigue Assessment Scale (FAS)","volume":"9","author":"J De Vries","year":"2004","journal-title":"Br J Health Psychol"},{"issue":"3","key":"pone.0358960.ref029","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1164\/rccm.200211-1343OC","article-title":"The Sarcoidosis Health Questionnaire: a new measure of health-related quality of life","volume":"168","author":"CE Cox","year":"2003","journal-title":"Am J Respir Crit Care Med"},{"issue":"1","key":"pone.0358960.ref030","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1186\/s12931-022-01993-z","article-title":"Clinical phenotyping in sarcoidosis using cluster analysis","volume":"23","author":"NW Lin","year":"2022","journal-title":"Respir Res"},{"issue":"5","key":"pone.0358960.ref031","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1378\/chest.129.5.1234","article-title":"A new tool to assess sarcoidosis severity","volume":"129","author":"YS Wasfi","year":"2006","journal-title":"Chest"},{"key":"pone.0358960.ref032","unstructured":"Machine learning. Wikipedia. 2020. Accessed 2020 March 20. https:\/\/en.wikipedia.org\/w\/index.php?title=Machine_learning&oldid=946015196"},{"issue":"3","key":"pone.0358960.ref033","doi-asserted-by":"crossref","first-page":"304","DOI":"10.21037\/tlcr.2018.05.15","article-title":"Lung cancer prediction using machine learning and advanced imaging techniques","volume":"7","author":"T Kadir","year":"2018","journal-title":"Transl Lung Cancer Res"},{"key":"pone.0358960.ref034","doi-asserted-by":"crossref","first-page":"672520","DOI":"10.1155\/2015\/672520","article-title":"Enhanced Classification of Interstitial Lung Disease Patterns in HRCT Images Using Differential Lacunarity","volume":"2015","author":"V Vasconcelos","year":"2015","journal-title":"Biomed Res Int"},{"issue":"4","key":"pone.0358960.ref035","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s10278-017-0028-9","article-title":"Comparison of shallow and deep learning methods on classifying the regional pattern of diffuse lung disease","volume":"31","author":"GB Kim","year":"2018","journal-title":"J Digit Imaging"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T17:24:23Z","timestamp":1792085063000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0358960"}},"subtitle":[],"editor":[{"given":"Selvakumar","family":"Subbian","sequence":"first","affiliation":[{"name":"Rutgers Biomedical and Health Sciences","place":["UNITED STATES OF AMERICA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,15]]},"references-count":35,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0358960","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,15]]}}}