{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:11:53Z","timestamp":1770271913173,"version":"3.49.0"},"reference-count":16,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"vor","delay-in-days":261,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1016\/j.procs.2025.09.163","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T22:13:24Z","timestamp":1762467204000},"page":"446-455","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Medformer: A Multitask Multimodal Foundational Model for Medical Imaging"],"prefix":"10.1016","volume":"270","author":[{"given":"Cristian","family":"Simionescu","sequence":"first","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.procs.2025.09.163_bib1","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.media.2019.03.009","article-title":"Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis","volume":"54","author":"Cheplygina","year":"2019","journal-title":"Medical image analysis"},{"key":"10.1016\/j.procs.2025.09.163_bib2","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: Transformers for image recognition at scale, arXiv preprint arXiv:2010.11929 (2020)."},{"key":"10.1016\/j.procs.2025.09.163_bib3","unstructured":"J. Chen, Y. Lu, Q. Yu, X. Luo, E. Adeli, Y. Wang, L. Lu, A. L. Yuille, Y. Zhou, Transunet: Transformers make strong encoders for medical image segmentation, arXiv preprint arXiv:2102.04306 (2021)."},{"key":"10.1016\/j.procs.2025.09.163_bib4","doi-asserted-by":"crossref","unstructured":"J. Yang, R. Shi, D. Wei, Z. Liu, L. Zhao, B. Ke, H. Pfister, B. Ni, Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification, Scientific Data 10 (1) (2023) 41.","DOI":"10.1038\/s41597-022-01721-8"},{"key":"10.1016\/j.procs.2025.09.163_bib5","unstructured":"A. Bardes, J. Ponce, Y. LeCun, Vicreg: Variance-invariance-covariance regularization for self-supervised learning, arXiv preprint arXiv:2105.04906 (2021)."},{"key":"10.1016\/j.procs.2025.09.163_bib6","unstructured":"T. Chen, S. Kornblith, M. Norouzi, G. Hinton, A simple framework for contrastive learning of visual representations, in: International conference on machine learning, PMLR, 2020, pp. 1597\u20131607."},{"key":"10.1016\/j.procs.2025.09.163_bib7","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, in: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2020, pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10.1016\/j.procs.2025.09.163_bib8","unstructured":"J. Zbontar, L. Jing, I. Misra, Y. LeCun, S. Deny, Barlow twins: Self-supervised learning via redundancy reduction, in: International Conference on Machine Learning, PMLR, 2021, pp. 12310\u201312320."},{"key":"10.1016\/j.procs.2025.09.163_bib9","first-page":"18158","article-title":"3d self-supervised methods for medical imaging","volume":"33","author":"Taleb","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.procs.2025.09.163_bib10","doi-asserted-by":"crossref","unstructured":"R. Goel, U. Nath, Y. Wang, A. C. Silva, T. Wu, Y. Yang, Learning low-rank feature for thorax disease classification, arXiv preprint arXiv:2404.18933 (2024).","DOI":"10.52202\/079017-3719"},{"key":"10.1016\/j.procs.2025.09.163_bib11","doi-asserted-by":"crossref","unstructured":"C. Simionescu, A. Iftene, Deep learning research directions in medical imaging, Mathematics 10 (23) (2022) 4472.","DOI":"10.3390\/math10234472"},{"key":"10.1016\/j.procs.2025.09.163_bib12","unstructured":"L. Qiao, Y. Gan, B. Wang, J. Qin, S. Xu, S. Yang, L. Ma, Univitar: Unified vision transformer with native resolution, arXiv preprint arXiv:2504.01792 (2025)."},{"key":"10.1016\/j.procs.2025.09.163_bib13","doi-asserted-by":"crossref","unstructured":"J. Ma, Y. He, F. Li, L. Han, C. You, B. Wang, Segment anything in medical images, Nature Communications 15 (1) (2024) 654.","DOI":"10.1038\/s41467-024-44824-z"},{"key":"10.1016\/j.procs.2025.09.163_bib14","unstructured":"I. Loshchilov, F. Hutter, Decoupled weight decay regularization, arXiv preprint arXiv:1711.05101 (2017)."},{"key":"10.1016\/j.procs.2025.09.163_bib15","doi-asserted-by":"crossref","unstructured":"E. D. Cubuk, B. Zoph, J. Shlens, Q. V. Le, Randaugment: Practical automated data augmentation with a reduced search space, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 702\u2013703.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"10.1016\/j.procs.2025.09.163_bib16","doi-asserted-by":"crossref","unstructured":"X. Zhuang, Y. Li, Y. Hu, K. Ma, Y. Yang, Y. Zheng, Self-supervised feature learning for 3d medical images by playing a rubik\u2019s cube, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, 2019, pp. 420\u2013428.","DOI":"10.1007\/978-3-030-32251-9_46"}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050925028339?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050925028339?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T08:35:40Z","timestamp":1766306140000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050925028339"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":16,"alternative-id":["S1877050925028339"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2025.09.163","relation":{},"ISSN":["1877-0509"],"issn-type":[{"value":"1877-0509","type":"print"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Medformer: A Multitask Multimodal Foundational Model for Medical Imaging","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2025.09.163","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}