{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T17:25:19Z","timestamp":1787505919064,"version":"build-2736575974"},"reference-count":28,"publisher":"BMJ","issue":"4","license":[{"start":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T00:00:00Z","timestamp":1664496000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81770096"],"award-info":[{"award-number":["81770096"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82102496"],"award-info":[{"award-number":["82102496"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82172034"],"award-info":[{"award-number":["82172034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Thorax"],"accepted":{"date-parts":[[2022,8,30]]},"published-print":{"date-parts":[[2023,4]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>This study aimed to construct artificial intelligence models based on thoracic CT images to perform segmentation and classification of benign pleural effusion (BPE) and malignant pleural effusion (MPE).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 918 patients with pleural effusion were initially included, with 607 randomly selected cases used as the training cohort and the other 311 as the internal testing cohort; another independent external testing cohort with 362 cases was used. We developed a pleural effusion segmentation model (M1) by combining 3D spatially weighted U-Net with 2D classical U-Net. Then, a classification model (M2) was built to identify BPE and MPE using a CT volume and its 3D pleural effusion mask as inputs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The average Dice similarity coefficient, Jaccard coefficient, precision, sensitivity, Hausdorff distance 95% (HD95) and average surface distance indicators in M1 were 87.6\u00b15.0%, 82.2\u00b16.2%, 99.0\u00b11.0%, 83.0\u00b16.6%, 6.9\u00b13.8 and 1.6\u00b11.1, respectively, which were better than those of the 3D U-Net and 3D spatially weighted U-Net. Regarding M2, the area under the receiver operating characteristic curve, sensitivity and specificity obtained with volume concat masks as input were 0.842 (95% CI 0.801 to 0.878), 89.4% (95% CI 84.4% to 93.2%) and 65.1% (95% CI 57.3% to 72.3%) in the external testing cohort. These performance metrics were significantly improved compared with those for the other input patterns.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We applied a deep learning model to the segmentation of pleural effusions, and the model showed encouraging performance in the differential diagnosis of BPE and MPE.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/thorax-2021-218581","type":"journal-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T13:32:22Z","timestamp":1664544742000},"page":"376-382","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":22,"title":["Differentiation of malignant from benign pleural effusions based on artificial intelligence"],"prefix":"10.1136","volume":"78","author":[{"given":"Sufei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyun","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianqian","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanran","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juanjuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanling","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoyang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingjia","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4664-2474","authenticated-orcid":false,"given":"Lian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2022,9,30]]},"reference":[{"key":"2024051319533985000_78.4.376.1","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.00349-2018"},{"key":"2024051319533985000_78.4.376.2","doi-asserted-by":"publisher","DOI":"10.1111\/resp.13673"},{"key":"2024051319533985000_78.4.376.3","doi-asserted-by":"publisher","DOI":"10.1503\/cmaj.170420"},{"key":"2024051319533985000_78.4.376.4","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1001\/jamaoncol.2019.5409","article-title":"Ascites, or fluid in the belly, in patients with cancer","volume":"6","author":"Gupta","year":"2020","journal-title":"JAMA Oncol"},{"key":"2024051319533985000_78.4.376.5","doi-asserted-by":"crossref","DOI":"10.1186\/s12931-019-1197-5","article-title":"Identifying tuberculous pleural effusion using artificial intelligence machine learning algorithms","volume":"20","author":"Ren","year":"2019","journal-title":"Respir Res"},{"key":"2024051319533985000_78.4.376.6","doi-asserted-by":"crossref","first-page":"1557","DOI":"10.21037\/tlcr-20-1111","article-title":"Pleural biomarkers in diagnostics of malignant pleural effusion: a narrative review","volume":"10","author":"Zhang","year":"2021","journal-title":"Transl Lung Cancer Res"},{"key":"2024051319533985000_78.4.376.7","doi-asserted-by":"publisher","DOI":"10.1378\/chest.14-0299"},{"key":"2024051319533985000_78.4.376.8","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1159\/000435962","article-title":"Efficacy and safety of diagnostic thoracoscopy in undiagnosed pleural effusions","volume":"90","author":"Wang","year":"2015","journal-title":"Respiration"},{"key":"2024051319533985000_78.4.376.9","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.rmed.2017.02.013","article-title":"State-of-the-art: radiological investigation of pleural disease","volume":"124","author":"Hallifax","year":"2017","journal-title":"Respir Med"},{"key":"2024051319533985000_78.4.376.10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"2024051319533985000_78.4.376.11","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0261-2"},{"key":"2024051319533985000_78.4.376.12","doi-asserted-by":"crossref","unstructured":"\u00d6 \u00c7i\u00e7ek , Abdulkadir A , Lienkamp SS . 3D U-Net: learning dense volumetric segmentation from sparse annotation. Cham: Springer International Publishing, 2016: 424\u201332.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"2024051319533985000_78.4.376.13","doi-asserted-by":"crossref","first-page":"4316","DOI":"10.1002\/mp.14386","article-title":"CT-based multi-organ segmentation using a 3D self-attention U-net network for pancreatic radiotherapy","volume":"47","author":"Liu","year":"2020","journal-title":"Med Phys"},{"key":"2024051319533985000_78.4.376.14","doi-asserted-by":"crossref","first-page":"101764","DOI":"10.1016\/j.compmedimag.2020.101764","article-title":"CAB U-Net: an end-to-end category attention boosting algorithm for segmentation","volume":"84","author":"Ding","year":"2020","journal-title":"Comput Med Imaging Graph"},{"key":"2024051319533985000_78.4.376.15","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1007\/s10278-020-00355-9","article-title":"The invasiveness classification of ground-glass nodules using 3D attention network and HRCT","volume":"33","author":"Ni","year":"2020","journal-title":"J Digit Imaging"},{"key":"2024051319533985000_78.4.376.16","doi-asserted-by":"crossref","first-page":"102924","DOI":"10.1016\/j.ebiom.2020.102924","article-title":"Development and validation of a novel scoring system developed from a nomogram to identify malignant pleural effusion","volume":"58","author":"Wang","year":"2020","journal-title":"EBioMedicine"},{"key":"2024051319533985000_78.4.376.17","doi-asserted-by":"crossref","first-page":"1790158","DOI":"10.1080\/20013078.2020.1790158","article-title":"Metabolic characteristics of large and small extracellular vesicles from pleural effusion reveal biomarker candidates for the diagnosis of tuberculosis and malignancy","volume":"9","author":"Luo","year":"2020","journal-title":"J Extracell Vesicles"},{"key":"2024051319533985000_78.4.376.18","doi-asserted-by":"publisher","DOI":"10.1007\/s003300050984"},{"key":"2024051319533985000_78.4.376.19","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1378\/chest.14-0013","article-title":"Derivation and validation of a CT scan scoring system for discriminating malignant from benign pleural effusions","volume":"147","author":"Porcel","year":"2015","journal-title":"Chest"},{"key":"2024051319533985000_78.4.376.20","doi-asserted-by":"publisher","DOI":"10.1177\/0284185113513894"},{"key":"2024051319533985000_78.4.376.21","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0193714","article-title":"Differential diagnosis between benign and malignant pleural effusion with dual-energy spectral CT","volume":"13","author":"Zhang","year":"2018","journal-title":"PLoS One"},{"key":"2024051319533985000_78.4.376.22","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.08.1286"},{"key":"2024051319533985000_78.4.376.23","first-page":"377","article-title":"Pleural effusion in adults\u2014etiology, diagnosis, and treatment","volume":"116","author":"Jany","year":"2019","journal-title":"Dtsch Arztebl Int"},{"key":"2024051319533985000_78.4.376.24","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1002\/jcp.24806","article-title":"Review: Cell dynamics in malignant pleural effusions","volume":"230","author":"Giarnieri","year":"2015","journal-title":"J Cell Physiol"},{"key":"2024051319533985000_78.4.376.25","doi-asserted-by":"publisher","DOI":"10.1111\/crj.12900"},{"key":"2024051319533985000_78.4.376.26","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1007\/s00432-016-2130-7","article-title":"Proteomic study of benign and malignant pleural effusion","volume":"142","author":"Li","year":"2016","journal-title":"J Cancer Res Clin Oncol"},{"key":"2024051319533985000_78.4.376.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"2024051319533985000_78.4.376.28","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1631\/FITEE.1700808","article-title":"Visual interpretability for deep learning: a survey","volume":"19","author":"Q-s","year":"2018","journal-title":"Frontiers of Information Technology & Electronic Engineering"}],"container-title":["Thorax"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/thorax-2021-218581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T23:22:26Z","timestamp":1715642546000},"score":1,"resource":{"primary":{"URL":"https:\/\/thorax.bmj.com\/lookup\/doi\/10.1136\/thorax-2021-218581"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,30]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,3,15]]},"published-print":{"date-parts":[[2023,4]]}},"alternative-id":["10.1136\/thorax-2021-218581"],"URL":"https:\/\/doi.org\/10.1136\/thorax-2021-218581","relation":{},"ISSN":["0040-6376","1468-3296"],"issn-type":[{"value":"0040-6376","type":"print"},{"value":"1468-3296","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,30]]}}}