{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T12:28:24Z","timestamp":1775737704332,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>For AI-based classification tasks in computed tomography (CT), a reference standard for evaluating the clinical diagnostic accuracy of individual classes is essential. To enable the implementation of an AI tool in clinical practice, the raw data should be drawn from clinical routine data using state-of-the-art scanners, evaluated in a blinded manner and verified with a reference test. Three hundred and thirty-five consecutive CTs, performed between 1 January 2016 and 1 January 2021 with reported pleural effusion and pathology reports from thoracocentesis or biopsy within 7 days of the CT were retrospectively included. Two radiologists (4 and 10 PGY) blindly assessed the chest CTs for pleural CT features. If needed, consensus was achieved using an experienced radiologist\u2019s opinion (29 PGY). In addition, diagnoses were extracted from written radiological reports. We analyzed these findings for a possible correlation with the following patient outcomes: mortality and median hospital stay. For AI prediction, we used an approach consisting of nnU-Net segmentation, PyRadiomics features and a random forest model. Specificity and sensitivity for CT-based detection of empyema (n = 81 of n = 335 patients) were 90.94 (95%-CI: 86.55\u201394.05) and 72.84 (95%-CI: 61.63\u201381.85%) in all effusions, with moderate to almost perfect interrater agreement for all pleural findings associated with empyema (Cohen\u2019s kappa = 0.41\u20130.82). Highest accuracies were found for pleural enhancement or thickening with 87.02% and 81.49%, respectively. For empyema prediction, AI achieved a specificity and sensitivity of 74.41% (95% CI: 68.50\u201379.57) and 77.78% (95% CI: 66.91\u201385.96), respectively. Empyema was associated with a longer hospital stay (median = 20 versus 14 days), and findings consistent with pleural carcinomatosis impacted mortality.<\/jats:p>","DOI":"10.3390\/jimaging8030050","type":"journal-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T22:34:30Z","timestamp":1645569270000},"page":"50","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Considerations on Baseline Generation for Imaging AI Studies Illustrated on the CT-Based Prediction of Empyema and Outcome Assessment"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9949-7912","authenticated-orcid":false,"given":"Raphael","family":"Sexauer","sequence":"first","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bram","family":"Stieltjes","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland"},{"name":"Department of Informatics, Division of Research and Analytical Services, University Hospital Basel, 4031 Basel, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jens","family":"Bremerich","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7237-711X","authenticated-orcid":false,"given":"Tugba Akinci","family":"D\u2019Antonoli","sequence":"additional","affiliation":[{"name":"Department of Informatics, Division of Research and Analytical Services, University Hospital Basel, 4031 Basel, Switzerland"},{"name":"Department of Radiology, University Children\u2019s Hospital Basel, 4056 Basel, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noemi","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine, University Hospital Basel, 4031 Basel, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,2,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109233","DOI":"10.1016\/j.ejrad.2020.109233","article-title":"Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning","volume":"131","author":"Anastasopoulos","year":"2020","journal-title":"Eur. J. Radiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"4080","DOI":"10.1038\/s41467-020-17971-2","article-title":"Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets","volume":"11","author":"Harmon","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: A revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"Whiting","year":"2011","journal-title":"Ann. Intern. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1177\/1457496917738868","article-title":"Long-term prognosis and causes of death after pleural infections","volume":"107","author":"Khan","year":"2018","journal-title":"Scand. J. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1136\/thx.2010.156406","article-title":"Emergence of parapneumonic empyema in the USA","volume":"66","author":"Grijalva","year":"2011","journal-title":"Thorax"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1093\/ejcts\/ezu104","article-title":"Thoracotomy and decortication: Impact of culture-positive empyema on the outcome of surgery","volume":"46","author":"Okiror","year":"2014","journal-title":"Eur. J. Cardio-Thorac. Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1086\/522996","article-title":"Diagnosis and management of parapneumonic effusions and empyema","volume":"45","author":"Sahn","year":"2007","journal-title":"Clin. Infect. Dis. Off. Publ. Infect. Dis. Soc. Am."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zettinig, D., D\u2019Antonoli, T.A., Wilder-Smith, A., Bremerich, J., Roth, J.A., and Sexauer, R. (2021). Diagnostic accuracy of imaging findings in pleural empyema: Systematic review and meta-analysis. J. Imaging, 8.","DOI":"10.3390\/jimaging8010003"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tsujimoto, N., Saraya, T., Light, R.W., Tsukahara, Y., Koide, T., Kurai, D., Ishii, H., Kimura, H., Goto, H., and Takizawa, H. (2015). A simple method for differentiating complicated parapneumonic effusion\/empyema from parapneumonic effusion using the split pleura sign and the amount of pleural effusion on thoracic CT. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0130141"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1158","DOI":"10.1378\/chest.118.4.1158","article-title":"Medical and surgical treatment of parapneumonic effusions","volume":"118","author":"Colice","year":"2000","journal-title":"Chest"},{"key":"ref_11","first-page":"CR443","article-title":"Treatment of complicated parapneumonic pleural effusion and pleural parapneumonic empyema","volume":"18","author":"Gilart","year":"2012","journal-title":"Med Sci. Monit. Int. Med. J. Exp. Clin. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1513\/pats.200510-113JH","article-title":"Parapneumonic effusions and empyema","volume":"3","author":"Light","year":"2006","journal-title":"Proc. Am. Thorac. Soc."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Fedorov","year":"2017","journal-title":"Cancer Res."},{"key":"ref_15","unstructured":"Sexauer, R. (2021, December 21). Considerations on Baseline Generation for Imaging AI Studies Illustrated on the CT-Based Prediction of Empyema and Outcome Assessment. Available online: https:\/\/zenodo.org\/record\/5793366#.YhNPfejMLIU."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"h5527","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: An updated list of essential items for reporting diagnostic accuracy studies","volume":"351","author":"Bossuyt","year":"2015","journal-title":"BMJ"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1148\/radiology.192.3.8058951","article-title":"Pleural exudates and transudates: Diagnosis with contrast-enhanced CT","volume":"192","author":"Aquino","year":"1994","journal-title":"Radiology"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1111\/resp.13040","article-title":"Computed tomography scoring system for discriminating between parapneumonic effusions eventually drained and those cured only with antibiotics","volume":"22","author":"Porcel","year":"2017","journal-title":"Respirology"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"487","DOI":"10.2214\/ajr.154.3.2106209","article-title":"CT in differential diagnosis of diffuse pleural disease","volume":"154","author":"Leung","year":"1990","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"163","DOI":"10.2214\/ajr.141.1.163","article-title":"Differentiating lung abscess and empyema: Radiography and computed tomography","volume":"141","author":"Stark","year":"1983","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0720-048X(01)00426-0","article-title":"Computed tomography features in malignant pleural mesothelioma and other commonly seen pleural diseases","volume":"41","author":"Metintas","year":"2002","journal-title":"Eur. J. Radiol."},{"key":"ref_22","first-page":"116","article-title":"Efficacy of CT in diagnosis of transudates and exudates in patients with pleural effusion","volume":"20","author":"Cullu","year":"2014","journal-title":"Diagn. Interv. Radiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1007\/s003300050984","article-title":"Evaluation of CT findings for diagnosis of pleural effusions","volume":"10","year":"2000","journal-title":"Eur. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1148\/radiology.175.1.2315473","article-title":"Parietal pleural changes in empyema: Appearances at CT","volume":"175","author":"Waite","year":"1990","journal-title":"Radiology"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"22402","DOI":"10.1038\/s41598-020-80061-2","article-title":"A meta-analysis of accuracy and sensitivity of chest CT and RT-PCR in COVID-19 diagnosis","volume":"10","author":"Khatami","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhan, N., Guo, Y., Tian, S., Huang, B., Tian, X., Zou, J., Xiong, Q., Tang, D., Zhang, L., and Dong, W. (2021). Clinical characteristics of COVID-19 complicated with pleural effusion. BMC Infect. Dis., 21.","DOI":"10.1186\/s12879-021-05856-8"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1099","DOI":"10.1016\/j.chest.2016.12.014","article-title":"Nonmalignant pleural effusions","volume":"151","author":"Walker","year":"2017","journal-title":"Chest"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1183\/09031936.00217114","article-title":"Mortality among patients with pleural effusion undergoing thoracentesis","volume":"46","author":"DeBiasi","year":"2015","journal-title":"Eur. Respir. J."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zamboni, M.M., da Silva, C.T., Baretta, R., Cunha, E.T., and Cardoso, G.P. (2015). Important prognostic factors for survival in patients with malignant pleural effusion. BMC Pulm. Med., 15.","DOI":"10.1186\/s12890-015-0025-z"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.lungcan.2021.01.027","article-title":"Lung cancer prediction by Deep Learning to identify benign lung nodules","volume":"154","author":"Heuvelmans","year":"2021","journal-title":"Lung Cancer"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e129","DOI":"10.1016\/j.jtcvs.2017.01.030","article-title":"The American Association for Thoracic Surgery consensus guidelines for the management of empyema","volume":"153","author":"Shen","year":"2017","journal-title":"J. Thorac. Cardiovasc. Surg."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.lungcan.2021.10.018","article-title":"Positron emission tomography-computed tomography (PET-CT) in suspected malignant pleural effusion. An updated systematic review and meta-analysis","volume":"162","author":"Fjaellegaard","year":"2021","journal-title":"Lung Cancer"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/8\/3\/50\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:24:48Z","timestamp":1760135088000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/8\/3\/50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,22]]},"references-count":32,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,3]]}},"alternative-id":["jimaging8030050"],"URL":"https:\/\/doi.org\/10.3390\/jimaging8030050","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,22]]}}}