{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:10:52Z","timestamp":1789031452591,"version":"build-2803163510"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003243","name":"Ministry of Health of the Czech Republic","doi-asserted-by":"crossref","award":["MH CZ-DRO, Motol University Hospital, 00064203"],"award-info":[{"award-number":["MH CZ-DRO, Motol University Hospital, 00064203"]}],"id":[{"id":"10.13039\/501100003243","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007397","name":"Charles University","doi-asserted-by":"crossref","award":["Cooperatio, Medical Diagnostics and Basic Medical Sciences"],"award-info":[{"award-number":["Cooperatio, Medical Diagnostics and Basic Medical Sciences"]}],"id":[{"id":"10.13039\/100007397","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Chest radiography provides limited precision of pleural effusion volume estimates. This study compares volume estimates from experienced radiologists and a multimodal artificial intelligence (AI) model, using computed tomography (CT)-derived volumetry as the reference standard.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>In this retrospective observational study, same-day chest CT and radiographs from adult patients with CT-confirmed pleural effusion (\u2265\u200920\u2009mL) were evaluated. Manually segmented pleural effusion volumes from CT served as the reference standard. Two board-certified radiologists independently estimated left and right pleural fluid volume on radiographs. A general-purpose multimodal AI model analyzed each radiograph using a standardized prompt and generated volume estimates for each hemithorax.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Eighty-eight patients (72.0\u2009\u00b1\u200914.4 years (mean\u2009\u00b1\u2009standard deviation); 56% male) were included, and 176 hemithoraces were analyzed. Median CT-derived pleural effusion volume was 389\u2009mL (interquartile range 188\u2013703\u2009mL). Correlation with CT volumes was moderate for both radiologists (intraclass correlation coefficient 0.64 and 0.74) and the AI model (0.66). Mean absolute error was 300\u2009mL (95% confidence interval 252 to 356\u2009mL) for radiologist #1, 250\u2009mL (216 to 285\u2009mL) for radiologist #2, and 264\u2009mL (227 to 299\u2009mL) for AI. For detection of effusions \u2265\u2009300\u2009mL, AUC values were 0.84 (radiologist #1), 0.90 (radiologist #2), and 0.85 (AI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Quantitative estimation of pleural effusion volume on chest radiography demonstrates only moderate agreement with CT, regardless of whether the interpretation is performed by experienced radiologists or a general multimodal AI model. This limitation appears intrinsic to the imaging modality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Question<\/jats:italic>\n                      <\/jats:bold>\n                      Can a general-purpose multimodal AI model estimate pleural effusion volume on chest radiographs with accuracy comparable to experienced radiologists, using CT volumetry as reference?\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      Across 88 patients (176 hemithoraces), radiologists and AI showed comparable moderate agreement with CT (mean absolute errors 250\u2013300\u2009mL; intraclass correlation coefficient 0.64\u20130.74); chest radiography is intrinsically imprecise.\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Relevance statement<\/jats:italic>\n                      <\/jats:bold>\n                      Chest radiography supports only coarse pleural effusion volume estimation regardless of interpreter; however, a general-purpose multimodal AI model achieved accuracy comparable to that of experienced radiologists.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-026-00790-3","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:47:50Z","timestamp":1789030070000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Quantitative estimation of pleural effusion volume on chest radiography: comparison of radiologists and a general-purpose multimodal AI model using CT as the reference standard"],"prefix":"10.1186","volume":"10","author":[{"given":"Dominik","family":"Schiller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakub","family":"Pristoupil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavlina","family":"Polaskova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martina","family":"Sterclova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2299-4707","authenticated-orcid":false,"given":"Lukas","family":"Lambert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"790_CR1","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.rmed.2017.02.013","volume":"124","author":"RJ Hallifax","year":"2017","unstructured":"Hallifax RJ, Talwar A, Wrightson JM, Edey A, Gleeson FV (2017) State-of-the-art: radiological investigation of pleural disease. Respir Med 124:88\u201399. https:\/\/doi.org\/10.1016\/j.rmed.2017.02.013","journal-title":"Respir Med"},{"key":"790_CR2","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/s1076-6332(05)80373-3","volume":"3","author":"CC Blackmore","year":"1996","unstructured":"Blackmore CC, Black WC, Dallas RV, Crow HC (1996) Pleural fluid volume estimation: a chest radiograph prediction rule. Acad Radiol 3:103\u2013109. https:\/\/doi.org\/10.1016\/s1076-6332(05)80373-3","journal-title":"Acad Radiol"},{"key":"790_CR3","doi-asserted-by":"publisher","first-page":"230172","DOI":"10.1183\/20734735.0172-2023","volume":"20","author":"M Hassan","year":"2024","unstructured":"Hassan M, Touman AA, Grabczak EM et al (2024) Imaging of pleural disease. Breathe 20:230172. https:\/\/doi.org\/10.1183\/20734735.0172-2023","journal-title":"Breathe"},{"key":"790_CR4","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230860","volume":"309","author":"S Bennani","year":"2023","unstructured":"Bennani S, Regnard N-E, Ventre J et al (2023) Using AI to improve radiologist performance in detection of abnormalities on chest radiographs. Radiology 309: e230860. https:\/\/doi.org\/10.1148\/radiol.230860","journal-title":"Radiology"},{"key":"790_CR5","doi-asserted-by":"publisher","unstructured":"Bosbach WA, Schoeni L, Senge JF et al (2026) Novel artificial intelligence chest X-ray diagnostics: a quality assessment of their agreement with human doctors in clinical routine. Rofo. https:\/\/doi.org\/10.1055\/a-2772-7798","DOI":"10.1055\/a-2772-7798"},{"key":"790_CR6","doi-asserted-by":"publisher","first-page":"194","DOI":"10.3390\/jpm15050194","volume":"15","author":"PG Lacaita","year":"2025","unstructured":"Lacaita PG, Galijasevic M, Swoboda M et al (2025) The accuracy of ChatGPT-4o in interpreting chest and abdominal X-ray images. J Pers Med 15:194. https:\/\/doi.org\/10.3390\/jpm15050194","journal-title":"J Pers Med"},{"key":"790_CR7","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.ajem.2025.03.060","volume":"93","author":"AM Ostrovsky","year":"2025","unstructured":"Ostrovsky AM (2025) Evaluating a large language model\u2019s accuracy in chest X-ray interpretation for acute thoracic conditions. Am J Emerg Med 93:99\u2013102. https:\/\/doi.org\/10.1016\/j.ajem.2025.03.060","journal-title":"Am J Emerg Med"},{"key":"790_CR8","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1378\/chest.12-1292","volume":"143","author":"MP Moy","year":"2013","unstructured":"Moy MP, Levsky JM, Berko NS et al (2013) A new, simple method for estimating pleural effusion size on CT scans. Chest 143:1054\u20131059. https:\/\/doi.org\/10.1378\/chest.12-1292","journal-title":"Chest"},{"key":"790_CR9","doi-asserted-by":"publisher","first-page":"136","DOI":"10.3390\/info16020136","volume":"16","author":"Z Yi","year":"2025","unstructured":"Yi Z, Xiao T, Albert MV (2025) A survey on multimodal large language models in radiology for report generation and visual question answering. Information 16:136. https:\/\/doi.org\/10.3390\/info16020136","journal-title":"Information"},{"key":"790_CR10","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1097\/RTI.0000000000000147","volume":"30","author":"JG Mammarappallil","year":"2015","unstructured":"Mammarappallil JG, Anderson SA, Danelson KA, Stitzel JA, Chiles C (2015) Estimation of pleural fluid volumes on chest radiography using computed tomography volumetric analysis: an update of the visual prediction rule. J Thorac Imaging 30:336\u2013339. https:\/\/doi.org\/10.1097\/RTI.0000000000000147","journal-title":"J Thorac Imaging"},{"key":"790_CR11","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1002\/jhm.2434","volume":"10","author":"NJ Soni","year":"2015","unstructured":"Soni NJ, Franco R, Velez MI et al (2015) Ultrasound in the diagnosis & management of pleural effusions. J Hosp Med 10:811\u2013816. https:\/\/doi.org\/10.1002\/jhm.2434","journal-title":"J Hosp Med"},{"key":"790_CR12","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.3390\/diagnostics15182322","volume":"15","author":"Y-Y Huang","year":"2025","unstructured":"Huang Y-Y, Lin Y-C, Tsai S-H et al (2025) Automated computer-assisted diagnosis of pleural effusion in chest X-rays via deep learning. Diagnostics (Basel) 15:2322. https:\/\/doi.org\/10.3390\/diagnostics15182322","journal-title":"Diagnostics"},{"key":"790_CR13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-30521-2","volume":"13","author":"JH Niehoff","year":"2023","unstructured":"Niehoff JH, Kalaitzidis J, Kroeger JR et al (2023) Evaluation of the clinical performance of an AI-based application for the automated analysis of chest X-rays. Sci Rep 13: 3680. https:\/\/doi.org\/10.1038\/s41598-023-30521-2","journal-title":"Sci Rep"},{"key":"790_CR14","doi-asserted-by":"publisher","first-page":"2592","DOI":"10.3390\/diagnostics14222592","volume":"14","author":"J L\u00f3pez Alcolea","year":"2024","unstructured":"L\u00f3pez Alcolea J, Fern\u00e1ndez Alfonso A, Cano Alonso R et al (2024) Diagnostic performance of artificial intelligence in chest radiographs referred from the emergency department. Diagnostics (Basel) 14:2592. https:\/\/doi.org\/10.3390\/diagnostics14222592","journal-title":"Diagnostics"},{"key":"790_CR15","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-024-01260-1","volume":"24","author":"J Chang","year":"2024","unstructured":"Chang J, Lin B-R, Wang T-H, Chen C-M (2024) Deep learning model for pleural effusion detection via active learning and pseudo-labeling: a multisite study. BMC Med Imaging 24: 92. https:\/\/doi.org\/10.1186\/s12880-024-01260-1","journal-title":"BMC Med Imaging"},{"key":"790_CR16","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-022-00827-0","volume":"22","author":"T Huang","year":"2022","unstructured":"Huang T, Yang R, Shen L et al (2022) Deep transfer learning to quantify pleural effusion severity in chest X-rays. BMC Med Imaging 22: 100. https:\/\/doi.org\/10.1186\/s12880-022-00827-0","journal-title":"BMC Med Imaging"},{"key":"790_CR17","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1111\/j.1440-1843.2004.00599.x","volume":"9","author":"AL Evans","year":"2004","unstructured":"Evans AL, Gleeson FV (2004) Radiology in pleural disease: State of the art. Respirology 9:300\u2013312. https:\/\/doi.org\/10.1111\/j.1440-1843.2004.00599.x","journal-title":"Respirology"},{"key":"790_CR18","doi-asserted-by":"publisher","first-page":"407","DOI":"10.2214\/AJR.09.2950","volume":"194","author":"MT Kitazono","year":"2010","unstructured":"Kitazono MT, Lau CT, Parada AN, Renjen P, Miller WT (2010) Differentiation of pleural effusions from parenchymal opacities: accuracy of bedside chest radiography. AJR Am J Roentgenol 194:407\u2013412. https:\/\/doi.org\/10.2214\/AJR.09.2950","journal-title":"Am J Roentgenol"},{"key":"790_CR19","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1186\/s41747-025-00591-0","volume":"9","author":"J Pristoupil","year":"2025","unstructured":"Pristoupil J, Oleaga L, Junquero V et al (2025) Five advanced chatbots solving European Diploma in Radiology (EDiR) text-based questions: differences in performance and consistency. Eur Radiol Exp 9:79. https:\/\/doi.org\/10.1186\/s41747-025-00591-0","journal-title":"Eur Radiol Exp"},{"key":"790_CR20","doi-asserted-by":"publisher","first-page":"1541","DOI":"10.3390\/diagnostics14141541","volume":"14","author":"A Wada","year":"2024","unstructured":"Wada A, Akashi T, Shih G et al (2024) Optimizing GPT-4 turbo diagnostic accuracy in neuroradiology through prompt engineering and confidence thresholds. Diagnostics (Basel) 14:1541. https:\/\/doi.org\/10.3390\/diagnostics14141541","journal-title":"Diagnostics"},{"key":"790_CR21","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1186\/s13244-025-01941-7","volume":"16","author":"J Pristoupil","year":"2025","unstructured":"Pristoupil J, Oleaga L, Junquero V et al (2025) Generative pre-trained transformer 4o (GPT-4o) in solving text-based multiple response questions for European Diploma in Radiology (EDiR): a comparative study with radiologists. Insights Imaging 16:66. https:\/\/doi.org\/10.1186\/s13244-025-01941-7","journal-title":"Insights Imaging"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00790-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-026-00790-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-026-00790-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:47:51Z","timestamp":1789030071000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s41747-026-00790-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,10]]},"references-count":21,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["790"],"URL":"https:\/\/doi.org\/10.1186\/s41747-026-00790-3","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,10]]},"assertion":[{"value":"1 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was conducted in accordance with the principles of the Declaration of Helsinki. Ethical approval was obtained from the Ethics Committee of Motol and Homolka University Hospital (EK-17\/23, 11\/2\/2026). The requirement for informed consent was waived due to the retrospective nature of the study and the use of anonymized imaging and clinical data.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"126"}}