{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T23:03:21Z","timestamp":1784243001619,"version":"3.55.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004829","name":"Sichuan Province Department of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004829","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.media.2026.104177","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:44:13Z","timestamp":1782492253000},"page":"104177","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis"],"prefix":"10.1016","volume":"113","author":[{"given":"Lanfeng","family":"Zhong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0496-1784","authenticated-orcid":false,"given":"Kun","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiren","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8632-158X","authenticated-orcid":false,"given":"Guotai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.104177_b1","unstructured":"Arthur, D., Vassilvitskii, S., 2007. K-means++ the advantages of careful seeding. In: ACM-SIAM Symposium on Discrete Algorithms. pp. 1027\u20131035."},{"key":"10.1016\/j.media.2026.104177_b2","series-title":"Lung and colon cancer histopathological image dataset (LC25000)","author":"Borkowski","year":"2019"},{"key":"10.1016\/j.media.2026.104177_b3","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A., 2021. Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9650\u20139660.","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"3","key":"10.1016\/j.media.2026.104177_b4","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nature Med."},{"key":"10.1016\/j.media.2026.104177_b5","series-title":"ICLR","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.media.2026.104177_b6","series-title":"Longnet: Scaling transformers to 1,000,000,000 tokens","author":"Ding","year":"2023"},{"key":"10.1016\/j.media.2026.104177_b7","series-title":"Multimodal whole slide foundation model for pathology","author":"Ding","year":"2024"},{"key":"10.1016\/j.media.2026.104177_b8","series-title":"ICLR","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"issue":"1","key":"10.1016\/j.media.2026.104177_b9","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1038\/s41596-024-01047-2","article-title":"From whole-slide image to biomarker prediction: end-to-end weakly supervised deep learning in computational pathology","volume":"20","author":"El Nahhas","year":"2025","journal-title":"Nat. Protoc."},{"key":"10.1016\/j.media.2026.104177_b10","series-title":"Distilling foundation models for robust and efficient models in digital pathology","author":"Filiot","year":"2025"},{"key":"10.1016\/j.media.2026.104177_b11","series-title":"Phikon-v2, a large and public feature extractor for biomarker prediction","author":"Filiot","year":"2024"},{"issue":"6","key":"10.1016\/j.media.2026.104177_b12","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.media.2026.104177_b13","series-title":"Towards computation-and communication-efficient computational pathology","author":"Han","year":"2025"},{"key":"10.1016\/j.media.2026.104177_b14","series-title":"CVPR","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.media.2026.104177_b15","series-title":"CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.media.2026.104177_b16","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"10.1016\/j.media.2026.104177_b17","first-page":"1","article-title":"A visual\u2013language foundation model for pathology image analysis using medical Twitter","author":"Huang","year":"2023","journal-title":"Nature Med."},{"key":"10.1016\/j.media.2026.104177_b18","series-title":"International Conference on Machine Learning","first-page":"2127","article-title":"Attention-based deep multiple instance learning","author":"Ilse","year":"2018"},{"key":"10.1016\/j.media.2026.104177_b19","series-title":"CVPR","first-page":"24120","article-title":"C-sfda: A curriculum learning aided self-training framework for efficient source free domain adaptation","author":"Karim","year":"2023"},{"issue":"1","key":"10.1016\/j.media.2026.104177_b20","doi-asserted-by":"crossref","first-page":"27988","DOI":"10.1038\/srep27988","article-title":"Multi-class texture analysis in colorectal cancer histology","volume":"6","author":"Kather","year":"2016","journal-title":"Sci. Rep."},{"issue":"6","key":"10.1016\/j.media.2026.104177_b21","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1109\/TAI.2021.3110179","article-title":"Domain adaptation without source data","volume":"2","author":"Kim","year":"2021","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.media.2026.104177_b22","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume":"31","author":"Kim","year":"2018","journal-title":"NeurIPS"},{"issue":"8","key":"10.1016\/j.media.2026.104177_b23","doi-asserted-by":"crossref","first-page":"5743","DOI":"10.1109\/TPAMI.2024.3370978","article-title":"A comprehensive survey on source-free domain adaptation","volume":"46","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104177_b24","series-title":"CVPR","first-page":"7096","article-title":"Knowledge distillation via instance relationship graph","author":"Liu","year":"2019"},{"issue":"8","key":"10.1016\/j.media.2026.104177_b25","doi-asserted-by":"crossref","first-page":"5430","DOI":"10.1109\/TPAMI.2024.3370721","article-title":"Source-free domain adaptation with domain generalized pretraining for face anti-spoofing","volume":"46","author":"Liu","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.media.2026.104177_b26","series-title":"ICCV","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"3","key":"10.1016\/j.media.2026.104177_b27","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visual-language foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nature Med."},{"issue":"8033","key":"10.1016\/j.media.2026.104177_b28","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1038\/s41586-024-07618-3","article-title":"A multimodal generative AI copilot for human pathology","volume":"634","author":"Lu","year":"2024","journal-title":"Nature"},{"issue":"6","key":"10.1016\/j.media.2026.104177_b29","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"Lu","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.media.2026.104177_b30","series-title":"Towards a generalizable pathology foundation model via unified knowledge distillation","author":"Ma","year":"2024"},{"key":"10.1016\/j.media.2026.104177_b31","series-title":"CVPR","first-page":"15720","article-title":"Vkd: Improving knowledge distillation using orthogonal projections","author":"Miles","year":"2024"},{"key":"10.1016\/j.media.2026.104177_b32","series-title":"AAAI","first-page":"4233","article-title":"Understanding the role of the projector in knowledge distillation","volume":"vol. 38","author":"Miles","year":"2024"},{"key":"10.1016\/j.media.2026.104177_b33","article-title":"When does label smoothing help?","volume":"32","author":"M\u00fcller","year":"2019","journal-title":"NeurIPS"},{"key":"10.1016\/j.media.2026.104177_b34","series-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.media.2026.104177_b35","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M., 2019. Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3967\u20133976.","DOI":"10.1109\/CVPR.2019.00409"},{"key":"10.1016\/j.media.2026.104177_b36","series-title":"CVPR","first-page":"23334","article-title":"Lead: Learning decomposition for source-free universal domain adaptation","author":"Qu","year":"2024"},{"key":"10.1016\/j.media.2026.104177_b37","doi-asserted-by":"crossref","unstructured":"Qu, S., Zou, T., R\u00f6hrbein, F., Lu, C., Chen, G., Tao, D., Jiang, C., 2023. Upcycling models under domain and category shift. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 20019\u201320028.","DOI":"10.1109\/CVPR52729.2023.01917"},{"key":"10.1016\/j.media.2026.104177_b38","series-title":"ICML","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.media.2026.104177_b39","series-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"10.1016\/j.media.2026.104177_b40","series-title":"Prism: A multi-modal generative foundation model for slide-level histopathology","author":"Shaikovski","year":"2024"},{"key":"10.1016\/j.media.2026.104177_b41","first-page":"2136","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.media.2026.104177_b42","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"issue":"10221","key":"10.1016\/j.media.2026.104177_b43","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/S0140-6736(19)32998-8","article-title":"Deep learning for prediction of colorectal cancer outcome: a discovery and validation study","volume":"395","author":"Skrede","year":"2020","journal-title":"Lancet"},{"key":"10.1016\/j.media.2026.104177_b44","series-title":"ICLR","article-title":"PathGen-1.6 m: 1.6 million pathology image-text pairs generation through multi-agent collaboration","author":"Sun","year":"2025"},{"key":"10.1016\/j.media.2026.104177_b45","doi-asserted-by":"crossref","unstructured":"Tang, S., Su, W., Ye, M., Zhu, X., 2024. Source-free domain adaptation with frozen multimodal foundation model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 23711\u201323720.","DOI":"10.1109\/CVPR52733.2024.02238"},{"key":"10.1016\/j.media.2026.104177_b46","series-title":"ICML","first-page":"10347","article-title":"Training data-efficient image transformers and distillation through attention","volume":"139","author":"Touvron","year":"2021"},{"issue":"10","key":"10.1016\/j.media.2026.104177_b47","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","article-title":"A foundation model for clinical-grade computational pathology and rare cancers detection","volume":"30","author":"Vorontsov","year":"2024","journal-title":"Nature Med."},{"key":"10.1016\/j.media.2026.104177_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102559","article-title":"Transformer-based unsupervised contrastive learning for histopathological image classification","volume":"81","author":"Wang","year":"2022","journal-title":"Med. Image Anal."},{"issue":"8035","key":"10.1016\/j.media.2026.104177_b49","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1038\/s41586-024-07894-z","article-title":"A pathology foundation model for cancer diagnosis and prognosis prediction","volume":"634","author":"Wang","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.media.2026.104177_b50","first-page":"1","article-title":"A vision\u2013language foundation model for precision oncology","author":"Xiang","year":"2025","journal-title":"Nature"},{"issue":"8015","key":"10.1016\/j.media.2026.104177_b51","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","article-title":"A whole-slide foundation model for digital pathology from real-world data","volume":"630","author":"Xu","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.media.2026.104177_b52","series-title":"ICCV","first-page":"8978","article-title":"Generalized source-free domain adaptation","author":"Yang","year":"2021"},{"key":"10.1016\/j.media.2026.104177_b53","series-title":"ACM Multimedia","first-page":"1935","article-title":"Alleviating style sensitivity then adapting: Source-free domain adaptation for medical image segmentation","author":"Ye","year":"2022"},{"key":"10.1016\/j.media.2026.104177_b54","series-title":"ACM SIGKDD","first-page":"1285","article-title":"Learning from multiple teacher networks","author":"You","year":"2017"},{"key":"10.1016\/j.media.2026.104177_b55","doi-asserted-by":"crossref","unstructured":"Yuan, L., Tay, F.E., Li, G., Wang, T., Feng, J., 2020. Revisiting knowledge distillation via label smoothing regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3903\u20133911.","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"10.1016\/j.media.2026.104177_b56","series-title":"ICLR","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2017"},{"issue":"9","key":"10.1016\/j.media.2026.104177_b57","doi-asserted-by":"crossref","first-page":"2513","DOI":"10.1109\/TMI.2023.3262680","article-title":"Efficient multi-organ segmentation from 3D abdominal CT images with lightweight network and knowledge distillation","volume":"42","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104177_b58","series-title":"Ibot: Image bert pre-training with online tokenizer","author":"Zhou","year":"2021"},{"key":"10.1016\/j.media.2026.104177_b59","series-title":"Virchow2: Scaling self-supervised mixed magnification models in pathology","author":"Zimmermann","year":"2024"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136184152600246X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136184152600246X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:06:29Z","timestamp":1784239589000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S136184152600246X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":59,"alternative-id":["S136184152600246X"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104177","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104177","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104177"}}