{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T02:50:43Z","timestamp":1787021443075,"version":"build-2736575974"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"1134","license":[{"start":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T00:00:00Z","timestamp":1648425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,1]]},"abstract":"<jats:sec>\n                    <jats:title>Objective:<\/jats:title>\n                    <jats:p>To examine whether the machine-learning approach using 18-fludeoxyglucose positron emission tomography (18F-FDG-PET)-based radiomic and deep-learning features is useful for predicting the pathological risk subtypes of thymic epithelial tumors (TETs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>This retrospective study included 79 TET [27 low-risk thymomas (types A, AB and B1), 31 high-risk thymomas (types B2 and B3) and 21 thymic carcinomas] patients who underwent pre-therapeutic 18F-FDG-PET\/CT. High-risk TETs (high-risk thymomas and thymic carcinomas) were 52 patients. The 107 PET-based radiomic features, including SUV-related parameters [maximum SUV (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG)] and 1024 deep-learning features extracted from the convolutional neural network were used to predict the pathological risk subtypes of TETs using six different machine-learning algorithms. The area under the curves (AUCs) were calculated to compare the predictive performances.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>SUV-related parameters yielded the following AUCs for predicting thymic carcinomas: SUVmax 0.713, MTV 0.442, and TLG 0.479 or high-risk TETs: SUVmax 0.673, MTV 0.533, and TLG 0.539. The best-performing algorithm was the logistic regression model for predicting thymic carcinomas (AUC 0.900, accuracy 81.0%), and the random forest (RF) model for high-risk TETs (AUC 0.744, accuracy 72.2%). The AUC was significantly higher in the logistic regression model than three SUV-related parameters for predicting thymic carcinomas, and in the RF model than MTV and TLG for predicting high-risk TETs (each; p &amp;lt; 0.05).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>18F-FDG-PET-based radiomic analysis using a machine-learning approach may be useful for predicting the pathological risk subtypes of TETs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Advances in knowledge:<\/jats:title>\n                    <jats:p>Machine-learning approach using 18F-FDG-PET-based radiomic features has the potential to predict the pathological risk subtypes of TETs.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1259\/bjr.20211050","type":"journal-article","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T13:02:26Z","timestamp":1647867746000},"source":"Crossref","is-referenced-by-count":23,"title":["The efficacy of 18F-FDG-PET-based radiomic and deep-learning features using a machine-learning approach to predict the pathological risk subtypes of thymic epithelial tumors"],"prefix":"10.1093","volume":"95","author":[{"given":"Masatoyo","family":"Nakajo","sequence":"first","affiliation":[{"name":"Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences , Kagoshima , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aya","family":"Takeda","sequence":"additional","affiliation":[{"name":"Department of General Thoracic Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences , Kagoshima , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akie","family":"Katsuki","sequence":"additional","affiliation":[{"name":"Research and Development Department, GE Healthcare Japan , Tokyo , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Megumi","family":"Jinguji","sequence":"additional","affiliation":[{"name":"Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences , Kagoshima , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuyuki","family":"Ohmura","sequence":"additional","affiliation":[{"name":"Research and Development Department, GE Healthcare Japan , Tokyo , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi","family":"Tani","sequence":"additional","affiliation":[{"name":"Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences , Kagoshima , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masami","family":"Sato","sequence":"additional","affiliation":[{"name":"Department of General Thoracic Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences , Kagoshima , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takashi","family":"Yoshiura","sequence":"additional","affiliation":[{"name":"Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences , Kagoshima , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,3,28]]},"reference":[{"key":"2024050216113584000_b1","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.ejcts.2009.05.038","article-title":"Thymoma and thymic carcinoma","volume":"37","author":"Venuta","year":"2010","journal-title":"Eur J Cardiothorac Surg"},{"key":"2024050216113584000_b2","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 Suppl 5","author":"Girard","year":"2015","journal-title":"Ann Oncol"},{"key":"2024050216113584000_b3","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1002\/cncr.10226","article-title":"The World Health Organization histologic classification system reflects the oncologic behavior of thymoma: a clinical study of 273 patients","volume":"94","author":"Okumura","year":"2002","journal-title":"Cancer"},{"key":"2024050216113584000_b4","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1097\/00000478-200101000-00012","article-title":"Clinical and functional significance of WHO classification on human thymic epithelial neoplasms: a study of 146 consecutive tumors","volume":"25","author":"Okumura","year":"2001","journal-title":"Am J Surg Pathol"},{"key":"2024050216113584000_b5","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":"Jeong","year":"2004","journal-title":"AJR Am J Roentgenol"},{"key":"2024050216113584000_b6","first-page":"145","volume-title":"Pathology & Gen-etics, Tumours of the Lung, Pleura, Thymus and Heart","author":"M\u00fcller-Hermelink","year":"2004"},{"key":"2024050216113584000_b7","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1002\/cncr.10665","article-title":"New WHO histologic classification predicts prognosis of thymic epithelial tumors: a clinicopathologic study of 200 thymoma cases from China","volume":"95","author":"Chen","year":"2002","journal-title":"Cancer"},{"key":"2024050216113584000_b8","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1016\/j.athoracsur.2003.07.042","article-title":"WHO histologic classification is a prognostic indicator in thymoma","volume":"77","author":"Kondo","year":"2004","journal-title":"Ann Thorac Surg"},{"key":"2024050216113584000_b9","first-page":"1628","article-title":"18F##ltsup##gt-F##lt\/sup##gtDG PET\/CT of thymic epithelial tumors: usefulness for distinguishing and staging tumor subgroups","volume":"47","author":"Sung","year":"2006","journal-title":"J Nucl Med"},{"key":"2024050216113584000_b10","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.lungcan.2011.02.018","article-title":"Usefulness of 18-F FDG PET\/CT in the pre-treatment evaluation of thymic epithelial neoplasms","volume":"74","author":"Terzi","year":"2011","journal-title":"Lung Cancer"},{"key":"2024050216113584000_b11","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.ejrad.2010.08.010","article-title":"1##ltsup##gt8F##lt\/sup##gtDG PET for grading malignancy in thymic epithelial tumors: significant differences in 1##ltsup##gt8F##lt\/sup##gtDG uptake and expression of glucose transporter-1 and hexokinase II between low and high-risk tumors: preliminary study","volume":"81","author":"Nakajo","year":"2012","journal-title":"Eur J Radiol"},{"key":"2024050216113584000_b12","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/j.lungcan.2008.01.003","article-title":"Utility of 1##ltsup##gt8F##lt\/sup##gt-FDG PET for differentiating the grade of malignancy in thymic epithelial tumors","volume":"61","author":"Endo","year":"2008","journal-title":"Lung Cancer"},{"key":"2024050216113584000_b13","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1093\/ejcts\/ezu030","article-title":"18-Fluorine fluorodeoxyglucose positron emission tomography in the pretreatment evaluation of thymic epithelial neoplasms: a \u2018metabolic biopsy\u2019 confirmed by Ki-67 expression","volume":"46","author":"Viti","year":"2014","journal-title":"Eur J Cardiothorac Surg"},{"key":"2024050216113584000_b14","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.athoracsur.2012.09.052","article-title":"Usefulness of fluorine-18 fluorodeoxyglucose\u2013positron emission tomography in management strategy for thymic epithelial tumors","volume":"95","author":"Matsumoto","year":"2013","journal-title":"Ann Thorac Surg"},{"key":"2024050216113584000_b15","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/j.lungcan.2014.08.008","article-title":"Is 1##ltsup##gt8F##lt\/sup##gt-FDG PET useful in predicting the WHO grade of malignancy in thymic epithelial tumors? A meta-analysis","volume":"86","author":"Treglia","year":"2014","journal-title":"Lung Cancer"},{"key":"2024050216113584000_b16","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1097\/JTO.0b013e3182835549","article-title":"FDG PET-CT aids in the preoperative assessment of patients with newly diagnosed thymic epithelial malignancies","volume":"8","author":"Benveniste","year":"2013","journal-title":"J Thorac Oncol"},{"key":"2024050216113584000_b17","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1097\/RLU.0000000000001032","article-title":"Value of 18F-FDG PET\/CT for predicting the world health organization malignant grade of thymic epithelial tumors","volume":"41","author":"Park","year":"2016","journal-title":"Clin Nucl Med"},{"key":"2024050216113584000_b18","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"2024050216113584000_b19","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s12149-016-1062-2","article-title":"Differentiating the grades of thymic epithelial tumor malignancy using textural features of intratumoral heterogeneity via (18)F-FDG PET\/CT","volume":"30","author":"Lee","year":"2016","journal-title":"Ann Nucl Med"},{"key":"2024050216113584000_b20","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1259\/bjr.20170546","article-title":"Texture analysis of 1##ltsup##gt8F##lt\/sup##gt-FDG PET\/CT for grading thymic epithelial tumours: usefulness of combining SUV and texture parameters","volume":"91","author":"Nakajo","year":"2018","journal-title":"Br J Radiol"},{"key":"2024050216113584000_b21","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1148\/rg.2017160130","article-title":"Machine learning for medical imaging","volume":"37","author":"Erickson","year":"2017","journal-title":"Radiographics"},{"key":"2024050216113584000_b22","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1038\/ajg.2010.173","article-title":"Machine learning in medicine: A primer for physicians","volume":"105","author":"Waljee","year":"2010","journal-title":"Am J Gastroenterol"},{"key":"2024050216113584000_b23","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.ejrad.2014.11.006","article-title":"The method and efficacy of support vector machine classifiers based on texture features and multi-resolution histogram from (18)F-FDG PET-CT images for the evaluation of mediastinal lymph nodes in patients with lung cancer","volume":"84","author":"Gao","year":"2015","journal-title":"Eur J Radiol"},{"issue":"9","key":"2024050216113584000_b24","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0137036","article-title":"Predicting response to neoadjuvant chemotherapy with PET imaging using convolutional neural networks","volume":"10","author":"Ypsilantis","year":"2015","journal-title":"PLoS One"},{"key":"2024050216113584000_b25","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1016\/j.crad.2019.02.008","article-title":"Pre-treatment 1##ltsup##gt8F##lt\/sup##gt-FDG PET-based radiomics predict survival in resected non-small cell lung cancer","volume":"74","author":"Ahn","year":"2019","journal-title":"Clin Radiol"},{"key":"2024050216113584000_b26","doi-asserted-by":"crossref","first-page":"6741","DOI":"10.1007\/s00330-019-06265-x","article-title":"Prediction of local relapse and distant metastasis in patients with definitive chemoradiotherapy-treated cervical cancer by deep learning from [18f]-fluorodeoxyglucose positron emission tomography\/computed tomography","volume":"29","author":"Shen","year":"2019","journal-title":"Eur Radiol"},{"key":"2024050216113584000_b27","doi-asserted-by":"crossref","first-page":"R150","DOI":"10.1088\/0031-9155\/61\/13\/R150","article-title":"Applications and limitations of radiomics","volume":"61","author":"Yip","year":"2016","journal-title":"Phys Med Biol"},{"key":"2024050216113584000_b28","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1007\/s11307-021-01599-9","article-title":"Application of a machine learning approach for the analysis of clinical and radiomic features of pretreatment [18f]-fdg pet\/ct to predict prognosis of patients with endometrial cancer","volume":"23","author":"Nakajo","year":"2021","journal-title":"Mol Imaging Biol"},{"key":"2024050216113584000_b29","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":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"2024050216113584000_b30","first-page":"260","article-title":"Cross-validated bagged learning","volume":"25","author":"Petersen","year":"2008","journal-title":"J Multivar Anal"},{"key":"2024050216113584000_b31","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1080\/10485252.2017.1404598","article-title":"Multiple predicting K-fold cross-validation for model selection","volume":"30","author":"Jung","year":"2017","journal-title":"Journal of Nonparametric Statistics"},{"key":"2024050216113584000_b32","doi-asserted-by":"crossref","first-page":"1814","DOI":"10.1002\/bjs.10244","article-title":"Overfitting","volume":"103","author":"Cook","year":"2016","journal-title":"Br J Surg"},{"key":"2024050216113584000_b33","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach Learn"},{"key":"2024050216113584000_b34","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2024050216113584000_b35","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"2024050216113584000_b36","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1186\/s13058-017-0846-1","article-title":"Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI","volume":"19","author":"Braman","year":"2017","journal-title":"Breast Cancer Res"},{"key":"2024050216113584000_b37","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1007\/s00330-017-4964-z","article-title":"MRI features can predict EGFR expression in lower grade gliomas: A voxel-based radiomic analysis","volume":"28","author":"Li","year":"2018","journal-title":"Eur Radiol"},{"key":"2024050216113584000_b38","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1200\/JCO.2011.39.2316","article-title":"Cancer genomics: technology, discovery, and translation","volume":"30","author":"Tran","year":"2012","journal-title":"J Clin Oncol"},{"key":"2024050216113584000_b39","doi-asserted-by":"crossref","first-page":"956","DOI":"10.1097\/RLU.0000000000002810","article-title":"A machine-learning approach using PET-based radiomics to predict the histological subtypes of lung cancer","volume":"44","author":"Hyun","year":"2019","journal-title":"Clin Nucl Med"},{"key":"2024050216113584000_b40","doi-asserted-by":"crossref","first-page":"37","DOI":"10.2967\/jnumed.112.116715","article-title":"The effect of small tumor volumes on studies of intratumoral heterogeneity of tracer uptake","volume":"55","author":"Brooks","year":"2014","journal-title":"J Nucl Med"},{"key":"2024050216113584000_b41","doi-asserted-by":"crossref","first-page":"e262","DOI":"10.1016\/S1470-2045(19)30149-4","article-title":"Big data and machine learning algorithms for health-care delivery","volume":"20","author":"Ngiam","year":"2019","journal-title":"Lancet Oncol"}],"container-title":["The British Journal of Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bjr\/article-pdf\/95\/1134\/20211050\/57371635\/bjr.20211050.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bjr\/article-pdf\/95\/1134\/20211050\/57371635\/bjr.20211050.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,2]],"date-time":"2024-05-02T14:36:36Z","timestamp":1714660596000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bjr\/article\/doi\/10.1259\/bjr.20211050\/7451367"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,28]]},"references-count":41,"journal-issue":{"issue":"1134","published-online":{"date-parts":[[2022,3,28]]},"published-print":{"date-parts":[[2022,6,1]]}},"URL":"https:\/\/doi.org\/10.1259\/bjr.20211050","relation":{},"ISSN":["0007-1285","1748-880X"],"issn-type":[{"value":"0007-1285","type":"print"},{"value":"1748-880X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,6,1]]},"published":{"date-parts":[[2022,3,28]]},"article-number":"20211050"}}