{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T09:53:03Z","timestamp":1786960383994,"version":"build-2736575974"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":34,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Respir Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Thoracentesis is required for malignant pleural effusion (MPE) diagnosis. However, it is an invasive procedure and carries risks. It remains unknown whether deep learning using ultrasound images could become a non-invasive diagnostic approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Patients with pleural effusion detected by thoracic ultrasound and received diagnostic thoracentesis were retrospectively collected from two sites. The internal cohort collected patients from the National Taiwan University Hospital (NTUH) Hsin-Chu branch (2014\u20132021), whereas the external cohort collected patients from NTUH (2020\u20132021). The MPE was confirmed by cytopathology reports, while benign pleural effusion was ascertained by negative cytology and compatible clinical courses. A convolutional deep learning model was used to identify MPE. Performance metrics included accuracy, F1 score, sensitivity, specificity and the area under the receiver operating characteristic curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 601 and 144 patients from the internal cohort and the external cohort were used for model development. The model achieved promising results in internal testing (accuracy\u2009=\u20090.750 [95% CI: 0.689\u20130.811], sensitivity\u2009=\u20090.710 [95% CI: 0.619\u20130.798], specificity\u2009=\u20090.803 [95% CI: 0.704\u20130.893], F1\u2009=\u20090.763 [95% CI: 0.691\u20130.826], AUC\u2009=\u20090.814 [95% CI: 0.746\u25000.873]). After fine-tuning with small number of external images, the model achieved the following performance on the external testing set: accuracy\u2009=\u20090.774 [95% CI: 0.679\u20130.857], sensitivity\u2009=\u20090.818 [95% CI: 0.723\u20130.905)], specificity\u2009=\u20090.611 [95% CI: 0.389\u20130.846], F1\u2009=\u20090.850 [95% CI: 0.776\u20130.913], AUC\u2009=\u20090.753 [95% CI: 0.596\u20130.885].<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our deep learning model holds promise as a non-invasive point-of-care modality for assistance in pleural effusion diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12931-026-03574-w","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:16:53Z","timestamp":1770815813000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A deep learning model based on ultrasound imaging to differentiate malignant from benign pleural effusion: a multicenter cohort study"],"prefix":"10.1186","volume":"27","author":[{"given":"Chang-Wei","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Suan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yen-Lin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po-Chih","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng-Rui","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jann-Yuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao-Chi","family":"Ho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin-Yuan","family":"Shih","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao-Chien","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"issue":"Suppl 2","key":"3574_CR1","doi-asserted-by":"publisher","first-page":"ii4","DOI":"10.1136\/thx.2010.136978","volume":"65","author":"C Hooper","year":"2010","unstructured":"Hooper C, Lee YC, Maskell N, BTS Pleural Guideline Group. Investigation of a unilateral pleural effusion in adults: British thoracic society pleural disease guideline 2010. Thorax. 2010;65(Suppl 2):ii4\u201317.","journal-title":"Thorax"},{"issue":"Suppl 3","key":"3574_CR2","doi-asserted-by":"publisher","first-page":"s1","DOI":"10.1136\/thorax-2022-219784","volume":"78","author":"ME Roberts","year":"2023","unstructured":"Roberts ME, Rahman NM, Maskell NA, Bibby AC, Blyth KG, Corcoran JP, et al. British thoracic society guideline for pleural disease. Thorax. 2023;78(Suppl 3):s1\u201342.","journal-title":"Thorax"},{"key":"3574_CR3","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1016\/j.mcna.2011.08.005","volume":"95","author":"RW Light","year":"2011","unstructured":"Light RW. Pleural effusions. Med Clin North Am. 2011;95:1055\u201370.","journal-title":"Med Clin North Am"},{"key":"3574_CR4","doi-asserted-by":"publisher","first-page":"e2120306","DOI":"10.1001\/jamanetworkopen.2021.20306","volume":"4","author":"P Tian","year":"2021","unstructured":"Tian P, Qiu R, Wang M, Xu S, Cao L, Yang P, et al. Prevalence, Causes, and health care burden of pleural effusions among hospitalized adults in China. JAMA Netw Open. 2021;4:e2120306.","journal-title":"JAMA Netw Open"},{"key":"3574_CR5","doi-asserted-by":"publisher","first-page":"230145","DOI":"10.1183\/20734735.0145-2023","volume":"9","author":"LM Piggott","year":"2023","unstructured":"Piggott LM, Hayes C, Greene J, Fitzgerald DB. Malignant pleural disease. Breathe. 2023;9:230145.","journal-title":"Breathe"},{"key":"3574_CR6","doi-asserted-by":"publisher","first-page":"h4520","DOI":"10.1136\/bmj.h4520","volume":"351","author":"R Bhatnagar","year":"2015","unstructured":"Bhatnagar R, Maskell N. The modern diagnosis and management of pleural effusions. BMJ. 2015;351:h4520.","journal-title":"BMJ"},{"key":"3574_CR7","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1513\/AnnalsATS.201902-189CME","volume":"16","author":"V Kaul","year":"2019","unstructured":"Kaul V, McCracken DJ, Rahman NM, Epelbaum O. Contemporary approach to the diagnosis of malignant pleural effusion. Ann Am Thorac Soc. 2019;16:1099\u2013106.","journal-title":"Ann Am Thorac Soc"},{"key":"3574_CR8","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1513\/AnnalsATS.201809-620CME","volume":"16","author":"CB Reddy","year":"2019","unstructured":"Reddy CB, DeCamp MM, Diekemper R, Gould MK, Henry T, Iyer NP, et al. Summary for clinicians: clinical practice guideline for management of malignant pleural effusions. Ann Am Thorac Soc. 2019;16:17\u201321.","journal-title":"Ann Am Thorac Soc"},{"key":"3574_CR9","doi-asserted-by":"publisher","first-page":"1800349","DOI":"10.1183\/13993003.00349-2018","volume":"52","author":"AC Bibby","year":"2018","unstructured":"Bibby AC, Dorn P, Psallidas I, Porcel JM, Janssen J, Froudarakis M, et al. ERS\/EACTS statement on the management of malignant pleural effusions. Eur Respir J. 2018;52:1800349.","journal-title":"Eur Respir J"},{"key":"3574_CR10","doi-asserted-by":"publisher","first-page":"1801254","DOI":"10.1183\/13993003.01254-2018","volume":"52","author":"DT Arnold","year":"2018","unstructured":"Arnold DT, De Fonseka D, Perry S, Morley A, Harvey JE, Medford A, et al. Investigating unilateral pleural effusions: the role of cytology. Eur Respir J. 2018;52:1801254.","journal-title":"Eur Respir J"},{"key":"3574_CR11","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.arbres.2013.11.007","volume":"50","author":"JM Porcel","year":"2014","unstructured":"Porcel JM, Esquerda A, Vives M, Bielsa S. Etiology of pleural effusions: analysis of more than 3,000 consecutive Thoracenteses. Arch Bronconeumol. 2014;50:161\u20135.","journal-title":"Arch Bronconeumol"},{"key":"3574_CR12","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1097\/MCP.0000000000000285","volume":"22","author":"EP Cantey","year":"2016","unstructured":"Cantey EP, Walter JM, Corbridge T, Barsuk JH. Complications of thoracentesis: incidence, risk factors, and strategies for prevention. Curr Opin Pulm Med. 2016;22:378\u201385.","journal-title":"Curr Opin Pulm Med"},{"key":"3574_CR13","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1136\/thorax-2021-218581","volume":"78","author":"S Wang","year":"2023","unstructured":"Wang S, Tan X, Li P, Fan Q, Xia H, Tian S, et al. Differentiation of malignant from benign pleural effusions based on artificial intelligence. Thorax. 2023;78:376\u201382.","journal-title":"Thorax"},{"key":"3574_CR14","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1513\/AnnalsATS.202305-410OC","volume":"21","author":"NY Kim","year":"2024","unstructured":"Kim NY, Jang B, Gu KM, Park YS, Kim YG, Cho J. Differential diagnosis of pleural effusion using machine learning. Ann Am Thorac Soc. 2024;21:211\u20137.","journal-title":"Ann Am Thorac Soc"},{"key":"3574_CR15","doi-asserted-by":"publisher","first-page":"5532","DOI":"10.1038\/s41598-022-09550-w","volume":"12","author":"JH Lee","year":"2022","unstructured":"Lee JH, Choi CM, Park N, Park HJ. Classification of pleural effusions using deep learning visual models: contrastive-loss. Sci Rep. 2022;12:5532.","journal-title":"Sci Rep"},{"key":"3574_CR16","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1056\/NEJMra0909487","volume":"364","author":"CL Moore","year":"2011","unstructured":"Moore CL, Copel JA. Point-of-care ultrasonography. N Engl J Med. 2011;364:749\u201357.","journal-title":"N Engl J Med"},{"key":"3574_CR17","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1186\/s13244-019-0775-x","volume":"10","author":"European Society of Radiology (ESR)","year":"2019","unstructured":"European Society of Radiology (ESR). ESR statement on portable ultrasound devices. Insights Imaging. 2019;10:89.","journal-title":"Insights Imaging"},{"key":"3574_CR18","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1136\/thx.2008.100545","volume":"64","author":"NR Qureshi","year":"2009","unstructured":"Qureshi NR, Rahman NM, Gleeson FV. Thoracic ultrasound in the diagnosis of malignant pleural effusion. Thorax. 2009;64:139\u201343.","journal-title":"Thorax"},{"key":"3574_CR19","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1159\/000357266","volume":"87","author":"A Bugalho","year":"2014","unstructured":"Bugalho A, Ferreira D, Dias SS, Schuhmann M, Branco JC, Marques Gomes MJ, et al. The diagnostic value of transthoracic ultrasonographic features in predicting malignancy in undiagnosed pleural effusions: a prospective observational study. Respiration. 2014;87:270\u20138.","journal-title":"Respiration"},{"key":"3574_CR20","doi-asserted-by":"publisher","first-page":"00464","DOI":"10.1183\/23120541.00464-2020","volume":"6","author":"A Shiroshita","year":"2020","unstructured":"Shiroshita A, Nozaki S, Tanaka Y, Luo Y, Kataoka Y. Thoracic ultrasound for malignant pleural effusion: a systematic review and meta-analysis. ERJ Open Res. 2020;6:00464\u20132020.","journal-title":"ERJ Open Res"},{"key":"3574_CR21","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","volume":"11","author":"A Buslaev","year":"2020","unstructured":"Buslaev A, Iglovikov VI, Khvedchenya E, Parinov A, Druzhinin M, Kalinin AA. Albumentations: fast and flexible image augmentations. Information. 2020;11:125.","journal-title":"Information"},{"key":"3574_CR22","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.ejmp.2021.02.023","volume":"83","author":"CH Tsai","year":"2021","unstructured":"Tsai CH, van der Burgt J, Vukovic D, Kaur N, Demi L, Canty D, et al. Automatic deep learning-based pleural effusion classification in lung ultrasound images for respiratory pathology diagnosis. Phys Med. 2021;83:38\u201345.","journal-title":"Phys Med"},{"key":"3574_CR23","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1186\/s12911-023-02362-6","volume":"23","author":"D Vukovic","year":"2023","unstructured":"Vukovic D, Wang A, Antico M, Steffens M, Ruvinov I, van Sloun RJ, et al. Automatic deep learning-based pleural effusion segmentation in lung ultrasound images. BMC Med Inf Decis Mak. 2023;23:274.","journal-title":"BMC Med Inf Decis Mak"},{"key":"3574_CR24","doi-asserted-by":"publisher","first-page":"507","DOI":"10.7326\/0003-4819-77-4-507","volume":"77","author":"RW Light","year":"1972","unstructured":"Light RW, Macgregor MI, Luchsinger PC, Ball WC Jr. Pleural effusions: the diagnostic separation of transudates and exudates. Ann Intern MedAnn Intern Med. 1972;77:507.","journal-title":"Ann Intern MedAnn Intern Med"},{"key":"3574_CR25","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1097\/MCP.0b013e32836022dc","volume":"19","author":"JM Porcel","year":"2013","unstructured":"Porcel JM. Identifying transudates misclassified by light\u2019s criteria. Curr Opin Pulm Med. 2013;19:362\u20137.","journal-title":"Curr Opin Pulm Med"},{"key":"3574_CR26","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1513\/AnnalsATS.201601-082OC","volume":"130","author":"OJ Bintcliffe","year":"2016","unstructured":"Bintcliffe OJ, Hooper CE, Rider IJ, Finn RS, Morley AJ, Zahan-Evans N, et al. Unilateral pleural effusions with more than one apparent Etiology. A prospective observational study. Ann Am Thorac Soc. 2016;130:1050\u20136.","journal-title":"Ann Am Thorac Soc"},{"key":"3574_CR27","doi-asserted-by":"publisher","first-page":"2003061","DOI":"10.1183\/13993003.03061-2020","volume":"57","author":"JG Nam","year":"2021","unstructured":"Nam JG, Kim M, Park J, Hwang EJ, Lee JH, Hong JH, et al. Development and validation of a deep learning algorithm detecting 10 common abnormalities on chest radiographs. Eur Respir J. 2021;57:2003061.","journal-title":"Eur Respir J"},{"key":"3574_CR28","doi-asserted-by":"publisher","first-page":"1328","DOI":"10.1016\/j.chest.2022.11.019","volume":"163","author":"A Sundaralingam","year":"2023","unstructured":"Sundaralingam A, Aujayeb A, Akca B, Tiedeman C, George V, Carling M, et al. Achieving molecular profiling in pleural biopsies: A Multicenter, retrospective cohort study. Chest. 2023;163:1328\u201339.","journal-title":"Chest"},{"key":"3574_CR29","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1001\/jamaoncol.2022.6109","volume":"9","author":"KWC Lee","year":"2023","unstructured":"Lee KWC, Li MSC, Gai W, Lau YM, Chan AKC, Chan OSH, et al. Testing for EGFR variants in pleural and pericardial effusion cell-Free DNA in patients with Non-Small cell lung cancer. JAMA Oncol. 2023;9:261\u20135.","journal-title":"JAMA Oncol"}],"container-title":["Respiratory Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12931-026-03574-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12931-026-03574-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12931-026-03574-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:05:53Z","timestamp":1781633153000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12931-026-03574-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,11]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3574"],"URL":"https:\/\/doi.org\/10.1186\/s12931-026-03574-w","relation":{},"ISSN":["1465-993X"],"issn-type":[{"value":"1465-993X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,11]]},"assertion":[{"value":"27 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was conducted in accordance with the principles of the Declaration of Helsinki. The study protocol was reviewed and approved by the Institutional Review Board (IRB) of NTUH (IRB no. 110-129-E and 202110052RINC). Written informed consent was waived by the IRB.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"134"}}