{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T15:33:41Z","timestamp":1781969621549,"version":"3.54.5"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T00:00:00Z","timestamp":1771286400000},"content-version":"vor","delay-in-days":18,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the National Cancer Center Research and Development Fund","award":["2023-A-19"],"award-info":[{"award-number":["2023-A-19"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Rare diseases are often difficult to diagnose, and their scarcity also makes it challenging to develop deep learning models for them due to limited large-scale datasets. Anterior mediastinal tumors\u2014including thymoma and thymic carcinoma\u2014represent such rare entities. A few diagnostic support systems for these tumors have been proposed; however, no prior studies have tested them across multiple institutions, and clinically applicable and generalizable models remain lacking. A total of 711 computed tomography (CT) images were collected from 136 hospitals, each from a different patient with pathologically proven anterior mediastinal tumors (339 males, 372 females). Of these, 485 images were used for training, 62 for tuning, and 164 for external testing. The external testing dataset comprised CT images from 121 unique institutions not involved in the other datasets. A 3D U-Net-based model was trained on the training dataset, and the model with the best performance on the tuning dataset was selected. This model was then evaluated on the external testing dataset for its segmentation and detection performance across different institutions. Based on the reference standards provided by board-certified diagnostic radiologists, the trained model achieved average Dice scores of 0.82, Intersection over Union (IoU) of 0.72, Precision of 0.85, and Recall of 0.82 for tumor segmentation at the CT-image level. The free-response receiver operating characteristic curve\u2014derived from lesion-wise IoU thresholds\u2014demonstrated high sensitivity and a low false-positive rate for tumor detection. Even under a stricter IoU threshold of 0.50, the model maintained a sensitivity of 0.87 with only 0.61 false positives per scan. Our model achieved clinically applicable segmentation and detection performance for anterior mediastinal tumors, demonstrating broad generalizability across 121 institutions and overcoming the data-scarcity challenges inherent to such rare diseases.<\/jats:p>","DOI":"10.1038\/s41598-026-37504-z","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T13:04:05Z","timestamp":1769778245000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A clinically applicable and generalizable deep learning model for anterior mediastinal tumors in CT images across multiple institutions"],"prefix":"10.1038","volume":"16","author":[{"given":"Chihiro","family":"Takemura","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mototaka","family":"Miyake","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuma","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiromi","family":"Matsumoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryota","family":"Shibaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsushi","family":"Urikura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasushi","family":"Goto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasushi","family":"Yatabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun-ichi","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miyuki","family":"Sone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masahiko","family":"Kusumoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryuji","family":"Hamamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hirokazu","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"37504_CR1","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.ejrad.2007.10.002","volume":"69","author":"N Tomiyama","year":"2009","unstructured":"Tomiyama, N. et al. Anterior mediastinal tumors: Diagnostic accuracy of CT and MRI. Eur. J. Radiol. 69, 280\u2013288. https:\/\/doi.org\/10.1016\/j.ejrad.2007.10.002 (2009).","journal-title":"Eur. J. Radiol."},{"key":"37504_CR2","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1002\/jmri.22377","volume":"32","author":"K Takahashi","year":"2010","unstructured":"Takahashi, K. & Al-Janabi, N. J. Computed tomography and magnetic resonance imaging of mediastinal tumors. J. Magn. Reson. Imaging 32, 1325\u20131339. https:\/\/doi.org\/10.1002\/jmri.22377 (2010).","journal-title":"J. Magn. Reson. Imaging"},{"key":"37504_CR3","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1097\/RTI.0b013e31828609a0","volume":"28","author":"EM Marom","year":"2013","unstructured":"Marom, E. M. Advances in thymoma imaging. J. Thorac. Imaging 28, 69\u201380. https:\/\/doi.org\/10.1097\/RTI.0b013e31828609a0 (2013).","journal-title":"J. Thorac. Imaging"},{"key":"37504_CR4","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.jtho.2021.10.010","volume":"17","author":"A Marx","year":"2022","unstructured":"Marx, A. et al. The 2021 WHO Classification of Tumors of the Thymus and Mediastinum: What is new in thymic epithelial, germ cell, and mesenchymal tumors?. J. Thorac. Oncol. 17, 200\u2013213. https:\/\/doi.org\/10.1016\/j.jtho.2021.10.010 (2022).","journal-title":"J. Thorac. Oncol."},{"key":"37504_CR5","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1016\/S2589-7500(23)00106-1","volume":"5","author":"R Tang","year":"2023","unstructured":"Tang, R. et al. Pan-mediastinal neoplasm diagnosis via nationwide federated learning: A multicentre cohort study. Lancet Digit. Health 5, 560\u2013570. https:\/\/doi.org\/10.1016\/S2589-7500(23)00106-1 (2023).","journal-title":"Lancet Digit. Health"},{"key":"37504_CR6","doi-asserted-by":"publisher","DOI":"10.3389\/FONC.2020.618357\/BIBTEX","volume":"10","author":"S Huang","year":"2021","unstructured":"Huang, S. et al. Anterior mediastinal lesion segmentation based on two-stage 3D ResUNet with attention gates and lung segmentation. Front. Oncol. 10, 618357. https:\/\/doi.org\/10.3389\/FONC.2020.618357\/BIBTEX (2021).","journal-title":"Front. Oncol."},{"key":"37504_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-024-01290-7","volume":"7","author":"Z Zhou","year":"2024","unstructured":"Zhou, Z. et al. Privacy enhancing and generalizable deep learning with synthetic data for mediastinal neoplasm diagnosis. NPJ Digit. Med. 7, 1\u201315 (2024).","journal-title":"NPJ Digit. Med."},{"key":"37504_CR8","doi-asserted-by":"publisher","unstructured":"Huang, S., Yu, H., Ai, D., Ma, G. & Yang, J. CLIP and image integrative prompt for anterior mediastinal lesion segmentation in CT image. 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 99, 3315\u20133318. https:\/\/doi.org\/10.1109\/BIBM62325.2024.10822165 (2024).","DOI":"10.1109\/BIBM62325.2024.10822165"},{"key":"37504_CR9","doi-asserted-by":"publisher","first-page":"1362637","DOI":"10.3389\/fnagi.2024.1362637","volume":"16","author":"S Yamada","year":"2024","unstructured":"Yamada, S. et al. Automatic assessment of disproportionately enlarged subarachnoid-space hydrocephalus from 3D MRI using two deep learning models. Front. Aging Neurosci. 16, 1362637. https:\/\/doi.org\/10.3389\/fnagi.2024.1362637 (2024).","journal-title":"Front. Aging Neurosci."},{"key":"37504_CR10","doi-asserted-by":"publisher","DOI":"10.1148\/RYAI.240300","author":"AS Tejani","year":"2024","unstructured":"Tejani, A. S. Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update. Radiol. Artif. Intell. https:\/\/doi.org\/10.1148\/RYAI.240300 (2024).","journal-title":"Radiol. Artif. Intell."},{"key":"37504_CR11","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1148\/RG.2017160095\/ASSET\/IMAGES\/LARGE\/RG.2017160095.FIG20B.JPEG","volume":"37","author":"BW Carter","year":"2017","unstructured":"Carter, B. W. et al. ITMIG classification of mediastinal compartments and multidisciplinary approach to mediastinal masses. Radiographics 37, 413\u2013436. https:\/\/doi.org\/10.1148\/RG.2017160095\/ASSET\/IMAGES\/LARGE\/RG.2017160095.FIG20B.JPEG (2017).","journal-title":"Radiographics"},{"key":"37504_CR12","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015 (eds Navab, N. et al.) 234\u2013241 (Springer, Cham, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"37504_CR13","doi-asserted-by":"publisher","unstructured":"Milletari, F., Navab, N., & Ahmadi, S.-A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE, Stanford, CA, USA https:\/\/doi.org\/10.1109\/3DV.2016.79 (2016).","DOI":"10.1109\/3DV.2016.79"},{"key":"37504_CR14","doi-asserted-by":"publisher","first-page":"4006","DOI":"10.1038\/ncomms5006","volume":"5","author":"HJWL Aerts","year":"2014","unstructured":"Aerts, H. J. W. L. et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat. Commun. 5, 4006. https:\/\/doi.org\/10.1038\/ncomms5006 (2014).","journal-title":"Nat. Commun."},{"key":"37504_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2024.110207","volume":"112","author":"G Dasegowda","year":"2024","unstructured":"Dasegowda, G. et al. No code machine learning: Validating the approach on use-case for classifying clavicle fractures. Clin. Imaging 112, 110207. https:\/\/doi.org\/10.1016\/j.clinimag.2024.110207 (2024).","journal-title":"Clin. Imaging"},{"key":"37504_CR16","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1007\/s11604-024-01608-1","volume":"42","author":"SL Walston","year":"2024","unstructured":"Walston, S. L. et al. Data set terminology of deep learning in medicine: A historical review and recommendation. Jpn. J. Radiol. 42, 1100\u20131109. https:\/\/doi.org\/10.1007\/s11604-024-01608-1 (2024).","journal-title":"Jpn. J. Radiol."},{"key":"37504_CR17","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220062","volume":"5","author":"SM Santomartino","year":"2023","unstructured":"Santomartino, S. M. et al. Performance and usability of code-free deep learning for chest radiograph classification, object detection, and segmentation. Radiol. Artif. Intell. 5, 220062. https:\/\/doi.org\/10.1148\/ryai.220062 (2023).","journal-title":"Radiol. Artif. Intell."},{"issue":"8","key":"37504_CR18","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3571724","volume":"66","author":"MH Jarrahi","year":"2023","unstructured":"Jarrahi, M. H., Memariani, A. & Guha, S. The principles of data-centric AI. Commun. ACM 66(8), 84\u201392. https:\/\/doi.org\/10.1145\/3571724 (2023).","journal-title":"Commun. ACM"},{"key":"37504_CR19","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1016\/J.ACRA.2023.10.018","volume":"31","author":"Y Yang","year":"2024","unstructured":"Yang, Y. et al. Development and validation of contrast-enhanced CT-based deep transfer learning and combined clinical-radiomics model to discriminate thymomas and thymic cysts: A multicenter study. Acad. Radiol. 31, 1615\u20131628. https:\/\/doi.org\/10.1016\/J.ACRA.2023.10.018 (2024).","journal-title":"Acad. Radiol."},{"key":"37504_CR20","doi-asserted-by":"publisher","DOI":"10.1259\/BJR.20211050\/SUPPL_FILE\/BJR.20211050.SUPPL-01.DOCX","author":"M Nakajo","year":"2022","unstructured":"Nakajo, M. et al. The efficacy of18F-FDG-PET-based radiomic and deep-learning features using a machine-learning approach to predict the pathological risk subtypes of thymic epithelial tumors. Brit. J. Radiol. https:\/\/doi.org\/10.1259\/BJR.20211050\/SUPPL_FILE\/BJR.20211050.SUPPL-01.DOCX (2022).","journal-title":"Brit. J. Radiol."},{"key":"37504_CR21","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1097\/RLU.0000000000004146","volume":"47","author":"S Han","year":"2022","unstructured":"Han, S. et al. Fully automatic quantitative measurement of 18F-FDG PET\/CT in thymic epithelial tumors using a convolutional neural network. Clin. Nucl. Med. 47, 590\u2013598. https:\/\/doi.org\/10.1097\/RLU.0000000000004146 (2022).","journal-title":"Clin. Nucl. Med."},{"key":"37504_CR22","doi-asserted-by":"publisher","DOI":"10.1136\/BMJRESP-2023-002249","volume":"11","author":"D Yamada","year":"2024","unstructured":"Yamada, D. et al. Multimodal modeling with low-dose CT and clinical information for diagnostic artificial intelligence on mediastinal tumors: A preliminary study. BMJ Open Respir. Res. 11, 002249. https:\/\/doi.org\/10.1136\/BMJRESP-2023-002249 (2024).","journal-title":"BMJ Open Respir. Res."},{"key":"37504_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/S12916-025-04104-Z","volume":"23","author":"F Wang","year":"2025","unstructured":"Wang, F. et al. A deep learning model combining circulating tumor cells and radiological features in the multi-classification of mediastinal lesions in comparison with thoracic surgeons: A large-scale retrospective study. BMC Med. 23, 1\u201311. https:\/\/doi.org\/10.1186\/S12916-025-04104-Z (2025).","journal-title":"BMC Med."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37504-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37504-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37504-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T09:36:17Z","timestamp":1771320977000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37504-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["37504"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-37504-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6694793\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]},"assertion":[{"value":"19 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"K.K. has received research funding from FUJIFILM Corporation. A.U. has received honoraria for lectures on CT imaging from Canon Medical Systems, Japan; GE Healthcare Pharma, Japan; and Fuji Pharma, Japan. Furthermore, A.U. serves as the Vice President of the Japanese Society of CT Technology and as a Delegate for the Japanese Society of Radiological Technology. Y.G. has received grants or contracts paid to his institution from AIQIVA Services Japan, MSD, Astellas Pharma, AstraZeneca, AbbVie, Amgen, Syneos Health, Sysmex Corporation, CMIC, Novartis Pharma, Bayer Pharmaceuticals, Bristol-Myers Squibb, MedPace Japan, Janssen Pharma, Clinical Research Support Center Kyushu, SATOMI, Ono Pharmaceutical, Daiichi Sankyo, Takeda Pharmaceutical, Chugai Pharmaceutical, NPO Thoracic Oncology Research Group, Eli Lilly Japan, and Preferred Network. He has also received grants or contracts paid to himself from AstraZeneca, AbbVie, Eli Lilly, Pfizer, Bristol Myers Squibb, Ono, Novartis, Kyorin, and Daiichi Sankyo. In addition, Y.G. has received payment or honoraria for lectures, presentations, speakers bureaus, manuscript writing, or educational events from Eli Lilly, Chugai, Taiho, Boehringer Ingelheim, Ono, Bristol Myers Squibb, Pfizer, MSD, Novartis, Merck, and Thermo Fisher. He has served on the monitoring or advisory boards for AstraZeneca, Chugai, Boehringer Ingelheim, Eli Lilly, GlaxoSmithKline, Taiho, Pfizer, Novartis, Kyorin, Guardant Health Inc., Illumina, Daiichi-Sankyo, Merck, MSD, Ono, and Janssen. He also holds a leadership or fiduciary role in Cancer Net Japan and JAMT. M.K. has received grants or contracts from Canon Medical Systems Corporation. M.K. has also received consulting fees from Daiichi-Sankyo Co., Ltd. R.H. has received research funds under contract from Fujifilm Corporation since the initial planning of this work. All other authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6774"}}