{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:13:43Z","timestamp":1760195623523,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032078445","type":"print"},{"value":"9783032078452","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-07845-2_18","type":"book-chapter","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:28:43Z","timestamp":1760192923000},"page":"181-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Test-Time Adaptation of Medical Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4830-9631","authenticated-orcid":false,"given":"Fereshteh","family":"Shakeri","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7551-0464","authenticated-orcid":false,"given":"Ghassen","family":"Baklouti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9726-9393","authenticated-orcid":false,"given":"Julio","family":"Silva-Rodr\u00edguez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4030-3704","authenticated-orcid":false,"given":"Maxime","family":"Zanella","sequence":"additional","affiliation":[]},{"given":"Houda","family":"Bahig","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2436-7750","authenticated-orcid":false,"given":"Jose","family":"Dolz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9668-8027","authenticated-orcid":false,"given":"Ismail Ben","family":"Ayed","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"18_CR1","unstructured":"Baklouti, G., Zanella, M., Ayed, I.B.: Language-aware information maximization for transductive few-shot clip (2025)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Bateson, M., Lombaert, H., Ben\u00a0Ayed, I.: Test-time adaptation with shape moments for image segmentation. In: MICCAI, pp. 736\u2013745 (2022)","DOI":"10.1007\/978-3-031-16440-8_70"},{"key":"18_CR3","unstructured":"Borkowski, A.A., et\u00a0al.: Lung and colon cancer histopathological image dataset (lc25000). arXiv preprint arXiv:1912.12142 (2019)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Boudiaf, M., Mueller, R., Ben\u00a0Ayed, I., Bertinetto, L.: Parameter-free online test-time adaptation. In: CVPR. pp. 8344\u20138353 (2022)","DOI":"10.1109\/CVPR52688.2022.00816"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., et\u00a0al.: Recent advances and clinical applications of deep learning in medical image analysis. Med. Image Anal. 79 (2022)","DOI":"10.1016\/j.media.2022.102444"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for Chinese natural language processing. In: EMNLP, pp. 657\u2013668 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Decenci\u00e8re, E., et\u00a0al.: Feedback on a publicly distributed image database: the messidor database. Image Anal. Stereol. 33, 231\u2013234 (2014)","DOI":"10.5566\/ias.1155"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Du, J., et\u00a0al.: Ret-CLIP: a retinal image foundation model pre-trained with clinical diagnostic reports. In: MICCAI, pp. 709\u2013719 (2024)","DOI":"10.1007\/978-3-031-72390-2_66"},{"key":"18_CR9","unstructured":"Hu, E.J., et\u00a0al.: LoRA: low-rank adaptation of large language models. In: ICLR (2021)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Hu, M., et al.: Fully test-time adaptation for image segmentation. In: MICCAI, pp. 251\u2013260 (2021)","DOI":"10.1007\/978-3-030-87199-4_24"},{"key":"18_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41591-023-02504-3","volume":"29","author":"Z Huang","year":"2023","unstructured":"Huang, Z., et al.: A visual\u2013language foundation model for pathology image analysis using medical twitter. Nat. Med. 29, 1\u201310 (2023)","journal-title":"Nat. Med."},{"key":"18_CR12","first-page":"37995","volume":"36","author":"W Ikezogwo","year":"2023","unstructured":"Ikezogwo, W., et al.: Quilt-1M: one million image-text pairs for histopathology. NeurIPS 36, 37995\u201338017 (2023)","journal-title":"NeurIPS"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Irvin, J., et\u00a0al.: ChexPert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI, vol.\u00a033, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"18_CR14","unstructured":"Jia, C., et\u00a0al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Jin, K., et al.: FIVES: a fundus image dataset for artificial intelligence based vessel segmentation. Sci. Data 9, 475 (08 2022)","DOI":"10.1038\/s41597-022-01564-3"},{"key":"18_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101907","volume":"68","author":"N Karani","year":"2021","unstructured":"Karani, N., et al.: Test-time adaptable neural networks for robust medical image segmentation. Med. Image Anal. 68, 101907 (2021)","journal-title":"Med. Image Anal."},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Karmanov, A., Guan, D., Lu, S., El\u00a0Saddik, A., Xing, E.: Efficient test-time adaptation of vision-language models. In: CVPR, pp. 14162\u201314171 (2024)","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"18_CR18","unstructured":"Kather, J.N., Halama, N., Marx, A.: 100,000 histological images of human colorectal cancer and healthy tissue. Zenodo10 5281 (2018)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Litjens, G., et\u00a0al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017)","DOI":"10.1016\/j.media.2017.07.005"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Q., et\u00a0al.: Single-domain generalization in medical image segmentation via test-time adaptation from shape dictionary. In: AAAI, vol.\u00a036, pp. 1756\u20131764 (2022)","DOI":"10.1609\/aaai.v36i2.20068"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Lu, M.Y., et\u00a0al.: Visual language pretrained multiple instance zero-shot transfer for histopathology images. In: CVPR, pp. 19764\u201319775 (2023)","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Maier-Hein, L., et\u00a0al.: Metrics reloaded: recommendations for image analysis validation. Nature Meth. 21 (2024)","DOI":"10.1117\/12.3011856"},{"key":"18_CR23","unstructured":"NIHDS-PKU: Competition on Ocular Disease Intelligent Recognition (ODIR). https:\/\/odir2019.grand-challenge.org (2019)"},{"key":"18_CR24","unstructured":"Niu, S., et al.: Towards stable test-time adaptation in dynamic wild world. In: ICLR (2023)"},{"key":"18_CR25","first-page":"48015","volume":"37","author":"D Osowiechi","year":"2025","unstructured":"Osowiechi, D., et al.: WATT: weight average test time adaptation of CLIP. NeurIPS 37, 48015\u201348044 (2025)","journal-title":"NeurIPS"},{"key":"18_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"18_CR27","unstructured":"Raghu, M., Zhang, C., Kleinberg, J., Bengio, S.: Transfusion: understanding transfer learning for medical imaging. In: NeurIPS, pp. 1\u201311 (2019)"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Shakeri, F., et\u00a0al.: Few-shot adaptation of medical vision-language models. In: MICCAI, pp. 553\u2013563 (2024)","DOI":"10.1007\/978-3-031-72390-2_52"},{"key":"18_CR29","first-page":"14274","volume":"35","author":"M Shu","year":"2022","unstructured":"Shu, M., et al.: Test-time prompt tuning for zero-shot generalization in vision-language models. NeurIPS 35, 14274\u201314289 (2022)","journal-title":"NeurIPS"},{"key":"18_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105637","volume":"195","author":"J Silva-Rodr\u00edguez","year":"2020","unstructured":"Silva-Rodr\u00edguez, J., et al.: Going deeper through the Gleason scoring scale: an automatic end-to-end system for histology prostate grading and cribriform pattern detection. Comput. Meth. Progr. Biomed. 195, 105637 (2020)","journal-title":"Comput. Meth. Progr. Biomed."},{"key":"18_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105714","volume":"147","author":"J Silva-Rodr\u00edguez","year":"2022","unstructured":"Silva-Rodr\u00edguez, J., et al.: Proportion constrained weakly supervised histopathology image classification. Comput. Biol. Med. 147, 105714 (2022)","journal-title":"Comput. Biol. Med."},{"key":"18_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103357","volume":"99","author":"J Silva-Rodriguez","year":"2025","unstructured":"Silva-Rodriguez, J., et al.: A foundation language-image model of the retina (FLAIR): encoding expert knowledge in text supervision. Med. Image Anal. 99, 103357 (2025)","journal-title":"Med. Image Anal."},{"key":"18_CR33","unstructured":"Valanarasu, J.M.J., et\u00a0al.: On-the-fly test-time adaptation for medical image segmentation. In: MIDL, pp. 586\u2013598. PMLR (2024)"},{"key":"18_CR34","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: fully test-time adaptation by entropy minimization. In: ICLR (2021)"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Z., et\u00a0al.: MedCLIP: contrastive learning from unpaired medical images and text. In: EMNLP, pp. 1\u201312 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: MedKLIP: medical knowledge enhanced language-image pre-training for X-ray diagnosis. In: ICCV (2023)","DOI":"10.1101\/2023.01.10.23284412"},{"key":"18_CR37","unstructured":"Yang, A., et\u00a0al.: Chinese CLIP: contrastive vision-language pretraining in Chinese. arXiv preprint arXiv:2211.01335 (2022)"},{"issue":"12","key":"18_CR38","first-page":"3575","volume":"41","author":"H Yang","year":"2022","unstructured":"Yang, H., et al.: DLTTA: dynamic learning rate for test-time adaptation on cross-domain medical images. IEEE TMI 41(12), 3575\u20133586 (2022)","journal-title":"IEEE TMI"},{"key":"18_CR39","unstructured":"Yang, S., et\u00a0al.: VilReF: an expert knowledge enabled vision-language retinal foundation model. IEEE TMI (2024)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Zanella, M., Ben\u00a0Ayed, I.: Low-rank few-shot adaptation of vision-language models. In: CVPRw, pp. 1593\u20131603 (2024)","DOI":"10.1109\/CVPRW63382.2024.00166"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Zanella, M., et\u00a0al.: Boosting vision-language models for histopathology classification: predict all at once. In: MedAGI MICCAIw, pp. 153\u2013162 (2024)","DOI":"10.1007\/978-3-031-73471-7_16"},{"key":"18_CR42","first-page":"62223","volume":"37","author":"M Zanella","year":"2024","unstructured":"Zanella, M., et al.: Boosting vision-language models with transduction. NeurIPS 37, 62223\u201362256 (2024)","journal-title":"NeurIPS"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Zanella, M., et\u00a0al.: On the test-time zero-shot generalization of vision-language models: do we really need prompt learning?. In: CVPR, pp. 23783\u201323793 (2024)","DOI":"10.1109\/CVPR52733.2024.02245"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Zanella, M., et\u00a0al.: Realistic test-time adaptation of vision-language models. In: CVPR, pp. 25103\u201325112 (2025)","DOI":"10.1109\/CVPR52734.2025.02337"},{"key":"18_CR45","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive learning of medical visual representations from paired images and text. In: MHLC (2022)"}],"container-title":["Lecture Notes in Computer Science","Foundation Models for General Medical AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07845-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:28:51Z","timestamp":1760192931000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07845-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"ISBN":["9783032078445","9783032078452"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07845-2_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"12 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MedAGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Foundation Models for General Medical AI","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"medagi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/medagi2025.github.io\/#\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}