{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T10:38:53Z","timestamp":1770460733051,"version":"3.49.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T00:00:00Z","timestamp":1620172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Myasthenia gravis (MG) is the most common paraneoplastic syndromes of thymoma and closely related to thymus abnormalities. Timely detecting of the risk of MG would benefit clinical management and treatment decision for patients with thymoma. Herein, we developed a 3D DenseNet deep learning (DL) model based on preoperative computed tomography (CT) as a non-invasive method to detect MG in thymoma patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A large cohort of 230 thymoma patients in a hospital affiliated with a medical school were enrolled. 182 thymoma patients (81 with MG, 101 without MG) were used for training and model building. 48 cases from another hospital were used for external validation. A 3D-DenseNet-DL model and five radiomic models were performed to detect MG in thymoma patients. A comprehensive analysis by integrating machine learning and semantic CT image features, named 3D-DenseNet-DL-based multi-model, was also performed to establish a more effective prediction model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Findings<\/jats:title><jats:p>By elaborately comparing the prediction efficacy, the 3D-DenseNet-DL effectively identified MG patients and was superior to other five radiomic models, with a mean area under ROC curve (AUC), accuracy, sensitivity, and specificity of 0.734, 0.724, 0.787, and 0.672, respectively. The effectiveness of the 3D-DenseNet-DL-based multi-model was further improved as evidenced by the following metrics: AUC 0.766, accuracy 0.790, sensitivity 0.739, and specificity 0.801. External verification results confirmed the feasibility of this DL-based multi-model with metrics: AUC 0.730, accuracy 0.732, sensitivity 0.700, and specificity 0.690, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Interpretation<\/jats:title><jats:p>Our 3D-DenseNet-DL model can effectively detect MG in patients with thymoma based on preoperative CT imaging. This model may serve as a supplement to the conventional diagnostic criteria for identifying thymoma associated MG.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2021.631964","type":"journal-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T15:05:54Z","timestamp":1620227154000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["3D DenseNet Deep Learning Based Preoperative Computed Tomography for Detecting Myasthenia Gravis in Patients With Thymoma"],"prefix":"10.3389","volume":"11","author":[{"given":"Zhenguo","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kefeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongguo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingqi","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghe","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiting","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zunfu","family":"Ke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2021,5,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2003.10.001","article-title":"Thymic Tumors","volume":"77","author":"Detterbeck","year":"2004","journal-title":"Ann Thorac Surg"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(19871201)60:11<2727::AID-CNCR2820601125>3.0.CO;2-D","article-title":"Thymoma. A Clinicopathologic Review","volume":"60","author":"Lewis","year":"1987","journal-title":"Cancer"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199406233302507","article-title":"Myasthenia Gravis","volume":"330","author":"Drachman","year":"1994","journal-title":"N Engl J Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1111\/j.1399-6576.2011.02564.x","article-title":"A Standardized Protocol for the Perioperative Management of Myasthenia Gravis Patients. Experience With 110 Patients","volume":"56","author":"Gritti","year":"2012","journal-title":"Acta Anaesthesiol Scand"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1002\/ana.25087","article-title":"A Clinical Predictive Score for Postoperative Myasthenic Crisis","volume":"82","author":"Kanai","year":"2017","journal-title":"Ann Neurol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1385\/NCC:3:3:189","article-title":"Myasthenic Crisis","volume":"3","author":"Lacomis","year":"2005","journal-title":"Neurocrit Care"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtcvs.2003.07.036","article-title":"Prognostic Factors for Myasthenic Crisis After Transsternal Thymectomy in Patients With Myasthenia Gravis","volume":"127","author":"Watanabe","year":"2004","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezu530","article-title":"Predictive Factors of Myasthenic Crisis After Extended Thymectomy for Patients With Myasthenia Gravis","volume":"48","author":"Ando","year":"2015","journal-title":"Eur J Cardio-Thoracic Surg"},{"key":"B9","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1055\/s-2004-829595","article-title":"Myasthenia Gravis: Management of Myasthenic Crisis and Perioperative Care","volume":"24","author":"Juel","year":"2004","journal-title":"Semin Neurol"},{"key":"B10","article-title":"Nccn Clinical Practice Guidelines in Oncology","volume-title":"Thymomas and Thymic Caricinomas","year":"2019"},{"key":"B11","doi-asserted-by":"publisher","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":"Cata","year":"2018","journal-title":"J\u00a0Cardiothorac Vasc Anesth"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1586\/1744666X.2016.1110487","article-title":"Overcoming Challenges in the Diagnosis and Treatment of Myasthenia Gravis","volume":"12","author":"Evoli","year":"2016","journal-title":"Expert Rev Clin Immunol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1002\/mus.20030","article-title":"Clinical Evaluation and Management of Myasthenia Gravis","volume":"29","author":"Keesey","year":"2004","journal-title":"Muscle Nerve"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21552","article-title":"Artificial Intelligence in Cancer Imaging: Clinical Challenges and Applications","volume":"69","author":"Bi","year":"2019","journal-title":"CA Cancer J Clin"},{"key":"B15","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s13139-018-0514-0","article-title":"Radiomics and Deep Learning in Clinical Imaging: What Should We do","volume":"52","author":"Choi","year":"2018","journal-title":"Nucl Med Mol Imaging"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s00595-012-0318-2","article-title":"Thymus, Thymoma and Myasthenia Gravis","volume":"43","author":"Fujii","year":"2013","journal-title":"Surg Today"},{"key":"B17","doi-asserted-by":"publisher","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":"B18","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.ccell.2018.01.003","article-title":"The Integrated Genomic Landscape of Thymic Epithelial Tumors","volume":"33","author":"Radovich","year":"2018","journal-title":"Cancer Cell"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2019.01041","article-title":"Relationship Between Computed Tomography Imaging Features and Clinical Characteristics, Masaoka-Koga Stages, and World Health Organization Histological Classifications of Thymoma","volume":"9","author":"Han","year":"2019","journal-title":"Front Oncol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2006.01.015","article-title":"User-Guided 3d Active Contour Segmentation of Anatomical Structures: Significantly Improved Efficiency and Reliability","volume":"31","author":"Yushkevich","year":"2006","journal-title":"Neuroimage"},{"key":"B21","doi-asserted-by":"publisher","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":"B22","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely Connected Convolutional Networks","volume-title":"30th Ieee Conference on Computer Vision and Pattern Recognition (Cvpr 2017)","author":"Huang","year":"2017"},{"key":"B23","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s41572-019-0079-y","article-title":"Myasthenia Gravis","volume":"5","author":"Gilhus","year":"2019","journal-title":"Nat Rev Dis Primers"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.26.11.1054","article-title":"Antibody to Acetylcholine Receptor in Myasthenia Gravis","volume":"26","author":"Lindstrom","year":"1976","journal-title":"Prevalence Clin correlates Diagn value Neurol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1017\/S0317167100026652","article-title":"Acetylcholine Receptor Antibodies in Myasthenia Gravis: Use of a Qualitative Assay for Diagnostic Purposes","volume":"14","author":"Oger","year":"1987","journal-title":"Can J Neurol Sci"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.autrev.2013.03.002","article-title":"Serological Diagnostics in Myasthenia Gravis Based on Novel Assays and Recently Identified Antigens","volume":"12","author":"Zisimopoulou","year":"2013","journal-title":"Autoimmun Rev"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1002\/mus.880120802","article-title":"Aaee Minimonograph #33: Electrodiagnostic Approach to Defects of Neuromuscular Transmission","volume":"12","author":"Keesey","year":"1989","journal-title":"Muscle Nerve"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1002\/mus.10141","article-title":"Clinical Impact of Single-Fiber Electromyography","volume":"11","author":"Sanders","year":"2002","journal-title":"Muscle Nerve"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranon.2014.07.007","article-title":"Nci Workshop Report: Clinical and Computational Requirements for Correlating Imaging Phenotypes With Genomics Signatures","volume":"7","author":"Colen","year":"2014","journal-title":"Transl Oncol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.14131691","article-title":"Outcome Prediction in Patients With Glioblastoma by Using Imaging, Clinical, and Genomic Biomarkers: Focus on the Nonenhancing Component of the Tumor","volume":"272","author":"Jain","year":"2014","journal-title":"Radiology"},{"key":"B31","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s00330-015-3814-0","article-title":"Ct Radiogenomic Characterization of EGFR, K-RAS, and ALK Mutations in Non-Small Cell Lung Cancer","volume":"26","author":"Rizzo","year":"2016","journal-title":"Eur Radiol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000116","article-title":"Texture Analysis as Imaging Biomarker of Tumoral Response to Neoadjuvant Chemoradiotherapy in Rectal Cancer Patients Studied With 3-T Magnetic Resonance","volume":"50","author":"De Cecco","year":"2015","journal-title":"Invest Radiol"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.179.4.1790881","article-title":"Using the World Health Organization Classification of Thymic Epithelial Neoplasms to Describe Ct Findings","volume":"179","author":"Tomiyama","year":"2002","journal-title":"AJR Am J Roentgenol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1097\/00004728-200105000-00010","article-title":"Invasive and Noninvasive Thymoma: Distinctive Ct Features","volume":"25","author":"Tomiyama","year":"2001","journal-title":"J Comput Assist Tomogr"},{"key":"B35","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3348\/kjr.2003.4.1.46","article-title":"Thymic Epithelial Tumors Classified According to a Newly Established WHO Scheme: CT and MR Findings","volume":"4","author":"Han","year":"2003","journal-title":"Korean J Radiol"},{"key":"B36","doi-asserted-by":"publisher","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":"Iannarelli","year":"2018","journal-title":"Radiol Med"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2021.631964\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T15:06:01Z","timestamp":1620227161000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2021.631964\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,5]]},"references-count":36,"alternative-id":["10.3389\/fonc.2021.631964"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2021.631964","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,5]]},"article-number":"631964"}}