{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T19:00:35Z","timestamp":1785265235498,"version":"3.55.0"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T00:00:00Z","timestamp":1639958400000},"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>Objectives<\/jats:title>\n<jats:p>To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>Patients with histologically confirmed TET in the years 2000\u20132018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-\/inter-reader agreement (ICC&lt;0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57\u00b114 years; range, 22\u201382 years) with 34 low-risk TET (LRT; WHO types A\/AB\/B1), 28 high-risk TET (HRT; WHO B2\/B3\/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-\/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3\u201394.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9\u201393.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8\u201379.5).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0261401","type":"journal-article","created":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T18:30:30Z","timestamp":1640025030000},"page":"e0261401","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":30,"title":["Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7321-5676","authenticated-orcid":true,"given":"Christian","family":"Bl\u00fcthgen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7622-9472","authenticated-orcid":true,"given":"Miriam","family":"Patella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5019-4585","authenticated-orcid":true,"given":"Andr\u00e9","family":"Euler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bettina","family":"Baessler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2638-6832","authenticated-orcid":true,"given":"Katharina","family":"Martini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jochen","family":"von Spiczak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Didier","family":"Schneiter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5900-9040","authenticated-orcid":true,"given":"Isabelle","family":"Opitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3295-6619","authenticated-orcid":true,"given":"Thomas","family":"Frauenfelder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,12,20]]},"reference":[{"issue":"3","key":"pone.0261401.ref001","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1148\/rg.2017160096","article-title":"IASLC\/ITMIG Staging System and Lymph Node Map for Thymic Epithelial Neoplasms.","volume":"37","author":"BW Carter","year":"2017","journal-title":"RadioGraphics"},{"issue":"6","key":"pone.0261401.ref002","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1093\/ejcts\/ezv426","article-title":"State of the art: diagnostic tools and innovative therapies for treatment of advanced thymoma and thymic carcinoma.","volume":"49","author":"M Ried","year":"2016","journal-title":"European Journal of Cardio-Thoracic Surgery"},{"issue":"3","key":"pone.0261401.ref003","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1097\/00004728-200105000-00010","article-title":"Invasive and Noninvasive Thymoma: Distinctive CT Features.","volume":"25","author":"N Tomiyama","year":"2001","journal-title":"Journal of Computer Assisted Tomography"},{"issue":"5","key":"pone.0261401.ref004","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1097\/JTO.0000000000000154","article-title":"ITMIG Consensus Statement on the Use of the WHO Histological Classification of Thymoma and Thymic Carcinoma: Refined Definitions, Histological Criteria, and Reporting.","volume":"9","author":"A Marx","year":"2014","journal-title":"Journal of Thoracic Oncology"},{"issue":"2","key":"pone.0261401.ref005","doi-asserted-by":"crossref","first-page":"283","DOI":"10.2214\/ajr.183.2.1830283","article-title":"Does CT of Thymic Epithelial Tumors Enable Us to Differentiate Histologic Subtypes and Predict Prognosis?","volume":"183","author":"YJ Jeong","year":"2004","journal-title":"American Journal of Roentgenology"},{"issue":"1","key":"pone.0261401.ref006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.thorsurg.2010.08.008","article-title":"Prediction of Thymoma Histology and Stage by Radiographic Criteria.","volume":"21","author":"M Yanagawa","year":"2011","journal-title":"Thoracic Surgery Clinics"},{"issue":"9","key":"pone.0261401.ref007","doi-asserted-by":"crossref","first-page":"2537","DOI":"10.1053\/j.jvca.2018.07.036","article-title":"Myasthenia Gravis and Thymoma Surgery: A Clinical Update for the Cardiothoracic Anesthesiologist.","volume":"33","author":"JP Cata","year":"2019","journal-title":"Journal of Cardiothoracic and Vascular Anesthesia"},{"key":"pone.0261401.ref008","doi-asserted-by":"crossref","first-page":"v40","DOI":"10.1093\/annonc\/mdv277","article-title":"Thymic epithelial tumours: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up","volume":"26","author":"N Girard","year":"2015","journal-title":"Annals of Oncology"},{"issue":"11","key":"pone.0261401.ref009","doi-asserted-by":"crossref","first-page":"2843","DOI":"10.1172\/JCI29894","article-title":"Myasthenia gravis: past, present, and future","volume":"116","author":"BM Conti-Fine","year":"2006","journal-title":"J Clin Invest"},{"issue":"6","key":"pone.0261401.ref010","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1097\/RLI.0000000000000448","article-title":"Texture Analysis and Machine Learning for Detecting Myocardial Infarction in Noncontrast Low-Dose Computed Tomography: Unveiling the Invisible.","volume":"53","author":"M Mannil","year":"2018","journal-title":"Investigative Radiology."},{"issue":"1","key":"pone.0261401.ref011","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s13244-020-00887-2","article-title":"Radiomics in medical imaging\u2014\u201chow-to\u201d guide and critical reflection.","volume":"11","author":"JE van Timmeren","year":"2020","journal-title":"Insights into Imaging."},{"key":"pone.0261401.ref012","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.ejrad.2017.04.017","article-title":"Quantitative computed tomography texture analysis for estimating histological subtypes of thymic epithelial tumors","volume":"92","author":"K Yasaka","year":"2017","journal-title":"European Journal of Radiology"},{"key":"pone.0261401.ref013","first-page":"3616852","article-title":"Radiomics Signatures of Computed Tomography Imaging for Predicting Risk Categorization and Clinical Stage of Thymomas","volume":"2019","author":"X Wang","year":"2019","journal-title":"Biomed Res Int"},{"issue":"4","key":"pone.0261401.ref014","first-page":"1256","article-title":"A radiomics model to predict the invasiveness of thymic epithelial tumors based on contrast\u2011enhanced computed tomography","volume":"43","author":"X Chen","year":"2020","journal-title":"Oncol Rep"},{"key":"pone.0261401.ref015","doi-asserted-by":"crossref","first-page":"108929","DOI":"10.1016\/j.ejrad.2020.108929","article-title":"Machine-learning-based computed tomography radiomic analysis for histologic subtype classification of thymic epithelial tumours","volume":"126","author":"J Hu","year":"2020","journal-title":"European Journal of Radiology"},{"issue":"1","key":"pone.0261401.ref016","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1186\/s40644-020-00364-5","article-title":"Development and validation of a CT-texture analysis nomogram for preoperatively differentiating thymic epithelial tumor histologic subtypes","volume":"20","author":"C Ren","year":"2020","journal-title":"Cancer Imaging"},{"issue":"1","key":"pone.0261401.ref017","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1007\/s00330-020-07100-4","article-title":"Risk stratification of thymic epithelial tumors by using a nomogram combined with radiomic features and TNM staging.","volume":"31","author":"Q Shen","year":"2021","journal-title":"Eur Radiol."},{"key":"pone.0261401.ref018","article-title":"CT Radiomic Features for Predicting Resectability and TNM Staging in Thymic Epithelial Tumors","author":"JA Batista Araujo-Filho","year":"2021","journal-title":"The Annals of Thoracic Surgery"},{"issue":"5","key":"pone.0261401.ref019","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s11547-017-0845-4","article-title":"Analysis of CT features and quantitative texture analysis in patients with thymic tumors: correlation with grading and staging.","volume":"123","author":"A Iannarelli","year":"2018","journal-title":"Radiol Med."},{"issue":"5","key":"pone.0261401.ref020","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1111\/j.1440-1827.1994.tb02936.x","article-title":"A review of 79 thymomas: Modification of staging system and reappraisal of conventional division into invasive and non-invasive thymoma","volume":"44","author":"K Koga","year":"1994","journal-title":"Pathology International"},{"issue":"2","key":"pone.0261401.ref021","doi-asserted-by":"crossref","first-page":"328","DOI":"10.2214\/AJR.19.21696","article-title":"MRI Radiomics Analysis for Predicting the Pathologic Classification and TNM Staging of Thymic Epithelial Tumors: A Pilot Study.","volume":"214","author":"G Xiao","year":"2020","journal-title":"AJR Am J Roentgenol."},{"key":"pone.0261401.ref022","doi-asserted-by":"crossref","first-page":"101716","DOI":"10.1016\/j.compmedimag.2020.101716","article-title":"Does image normalization and intensity resolution impact texture classification?","volume":"81","author":"M Kocio\u0142ek","year":"2020","journal-title":"Computerized Medical Imaging and Graphics"},{"issue":"21","key":"pone.0261401.ref023","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":"JJM van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"issue":"2","key":"pone.0261401.ref024","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping.","volume":"295","author":"A Zwanenburg","year":"2020","journal-title":"Radiology"},{"issue":"1","key":"pone.0261401.ref025","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/1758-2946-6-10","article-title":"Cross-validation pitfalls when selecting and assessing regression and classification models","volume":"6","author":"D Krstajic","year":"2014","journal-title":"Journal of Cheminformatics"},{"key":"pone.0261401.ref026","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"11","key":"pone.0261401.ref027","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package.","volume":"36","author":"MB Kursa","year":"2010","journal-title":"J Stat Softw"},{"key":"pone.0261401.ref028","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.ejrad.2018.03.013","article-title":"Texture analysis and machine learning of non-contrast T1-weighted MR images in patients with hypertrophic cardiomyopathy\u2014Preliminary results","volume":"102","author":"B Bae\u00dfler","year":"2018","journal-title":"European Journal of Radiology"},{"issue":"1","key":"pone.0261401.ref029","first-page":"6345","article-title":"On the stability of feature selection algorithms.","volume":"18","author":"S Nogueira","year":"2017","journal-title":"J Mach Learn Res."},{"issue":"1","key":"pone.0261401.ref030","doi-asserted-by":"crossref","first-page":"103","DOI":"10.15446\/rce.v43n1.80000","article-title":"Nested and Repeated Cross Validation for Classification Model With High-Dimensional Data.","volume":"43","author":"Y Zhong","year":"2020","journal-title":"Rev colomb estad."},{"issue":"1","key":"pone.0261401.ref031","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"SM Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"pone.0261401.ref032","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python.","volume":"17","author":"P Virtanen","year":"2020","journal-title":"Nature Methods"},{"key":"pone.0261401.ref033","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"17","key":"pone.0261401.ref034","first-page":"1","article-title":"Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning.","volume":"18","author":"G Lema\u00eetre","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0261401.ref035","first-page":"4765","volume-title":"A Unified Approach to Interpreting Model Predictions.","author":"SM Lundberg","year":"2017"},{"issue":"12","key":"pone.0261401.ref036","doi-asserted-by":"crossref","first-page":"7607","DOI":"10.21037\/jtd-2019-thym-01","article-title":"Classification and staging of thymoma.","volume":"12","author":"T Markowiak","year":"2020","journal-title":"J Thorac Dis."},{"key":"pone.0261401.ref037","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.lungcan.2018.01.025","article-title":"Optimal surgical approach to thymic malignancies: New trends challenging old dogmas","volume":"118","author":"E Ruffini","year":"2018","journal-title":"Lung Cancer"},{"issue":"1083","key":"pone.0261401.ref038","doi-asserted-by":"crossref","first-page":"20170546","DOI":"10.1259\/bjr.20170546","article-title":"Texture analysis of 18F-FDG PET\/CT for grading thymic epithelial tumours: usefulness of combining SUV and texture parameters.","volume":"91","author":"M Nakajo","year":"2018","journal-title":"Br J Radiol."},{"key":"pone.0261401.ref039","first-page":"1527","article-title":"3D DenseNet Deep Learning Based Preoperative Computed Tomography for Detecting Myasthenia Gravis in Patients With Thymoma.","volume":"11","author":"Z Liu","year":"2021","journal-title":"Frontiers in Oncology"},{"issue":"2","key":"pone.0261401.ref040","doi-asserted-by":"crossref","first-page":"341","DOI":"10.2214\/AJR.19.21844","article-title":"Quantitative 3D Shape Analysis of CT Images of Thymoma: A Comparison With Histological Types.","volume":"214","author":"M Yamazaki","year":"2020","journal-title":"AJR Am J Roentgenol."},{"issue":"5","key":"pone.0261401.ref041","doi-asserted-by":"crossref","first-page":"e0126175","DOI":"10.1371\/journal.pone.0126175","article-title":"Value of Computerized 3D Shape Analysis in Differentiating Encapsulated from Invasive Thymomas.","volume":"10","author":"JH Lee","year":"2015","journal-title":"PLoS One."},{"issue":"7","key":"pone.0261401.ref042","doi-asserted-by":"crossref","first-page":"4595","DOI":"10.1007\/s00330-020-07617-8","article-title":"Radiomics analysis of 18F-Choline PET\/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients.","volume":"31","author":"P Alongi","year":"2021","journal-title":"Eur Radiol."},{"issue":"11","key":"pone.0261401.ref043","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1097\/RLI.0000000000000180","article-title":"Measuring CT scanner variability of radiomics features.","volume":"50","author":"D Mackin","year":"2015","journal-title":"Invest Radiol."},{"issue":"9","key":"pone.0261401.ref044","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1097\/RLI.0000000000000666","article-title":"Variability and Standardization of Quantitative Imaging.","volume":"55","author":"A Hagiwara","year":"2020","journal-title":"Invest Radiol."},{"issue":"1","key":"pone.0261401.ref045","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1148\/radiol.2019182023","article-title":"Validation of A Method to Compensate Multicenter Effects Affecting CT Radiomics.","volume":"291","author":"F Orlhac","year":"2019","journal-title":"Radiology"},{"issue":"1","key":"pone.0261401.ref046","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1148\/radiol.2016152771","article-title":"Dealing with Uncertainty in CT Images.","volume":"279","author":"JG Fletcher","year":"2016","journal-title":"Radiology"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0261401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,20]],"date-time":"2021-12-20T18:31:38Z","timestamp":1640025098000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0261401"}},"subtitle":[],"editor":[{"given":"Omar Sultan","family":"Al-Kadi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,12,20]]},"references-count":46,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,12,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0261401","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,20]]}}}