{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T09:38:49Z","timestamp":1790415529287,"version":"4.1.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049704","type":"print"},{"value":"9783032049711","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-04971-1_13","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:09:29Z","timestamp":1758301769000},"page":"133-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Delving Into Out-of-Distribution Detection with\u00a0Medical Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Lie","family":"Ju","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoting","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pearse A.","family":"Keane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyuan","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"13_CR1","unstructured":"Borkowski, A.A., Bui, M.M., Thomas, L.B., Wilson, C.P., DeLand, L.A., Mastorides, S.M.: Lung and colon cancer histopathological image dataset (lc25000). arXiv preprint arXiv:1912.12142 (2019)"},{"key":"13_CR2","unstructured":"Cohen, J.P., Morrison, P., Dao, L.: Covid-19 image data collection. arXiv preprint arXiv:2003.11597 (2020)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Graham, M.S., et\u00a0al.: Unsupervised 3D out-of-distribution detection with latent diffusion models. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 446\u2013456. Springer (2023)","DOI":"10.1007\/978-3-031-43907-0_43"},{"key":"13_CR4","unstructured":"Hong, Z., et\u00a0al.: Out-of-distribution detection in medical image analysis: a survey. arXiv preprint arXiv:2404.18279 (2024)"},{"key":"13_CR5","first-page":"37995","volume":"36","author":"W Ikezogwo","year":"2023","unstructured":"Ikezogwo, W., et al.: Quilt-1m: one million image-text pairs for histopathology. Adv. Neural. Inf. Process. Syst. 36, 37995\u201338017 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"13_CR6","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1038\/s41597-022-01564-3","volume":"9","author":"K Jin","year":"2022","unstructured":"Jin, K., et al.: FIVES: a fundus image dataset for artificial intelligence based vessel segmentation. Sci. Data 9(1), 475 (2022)","journal-title":"Sci. Data"},{"issue":"1","key":"13_CR7","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1109\/TMI.2023.3302473","volume":"43","author":"L Ju","year":"2023","unstructured":"Ju, L., et al.: Hierarchical knowledge guided learning for real-world retinal disease recognition. IEEE Trans. Med. Imaging 43(1), 335\u2013350 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"7","key":"13_CR8","first-page":"1593","volume":"65","author":"L Ju","year":"2024","unstructured":"Ju, L., Zhou, Y., Xia, P., Alexander, D., Keane, P.A., Ge, Z.: Explore vision-language model with hierarchical information for multiple retinal disease recognition. Inv. Ophthal. Vis. Sci. 65(7), 1593\u20131593 (2024)","journal-title":"Inv. Ophthal. Vis. Sci."},{"key":"13_CR9","unstructured":"Khattak, M.U., Kunhimon, S., Naseer, M., Khan, S., Khan, F.S.: UniMed-CLIP: towards a unified image-text pretraining paradigm for diverse medical imaging modalities. arXiv preprint arXiv:2412.10372 (2024)"},{"key":"13_CR10","unstructured":"Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Adv. Neural Info. Process. Syst. 31 (2018)"},{"key":"13_CR11","unstructured":"Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: International Conference on Learning Representations (2018)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Lin, W., et al.: PMC-CLIP: contrastive language-image pre-training using biomedical documents. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 525\u2013536. Springer (2023)","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Liu, R., et\u00a0al.: DeepDRID: diabetic retinopathy\u2014grading and image quality estimation challenge. Patterns 3(6) (2022)","DOI":"10.1016\/j.patter.2022.100512"},{"key":"13_CR14","first-page":"21464","volume":"33","author":"W Liu","year":"2020","unstructured":"Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. Adv. Neural. Inf. Process. Syst. 33, 21464\u201321475 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR15","first-page":"35087","volume":"35","author":"Y Ming","year":"2022","unstructured":"Ming, Y., Cai, Z., Gu, J., Sun, Y., Li, W., Li, Y.: Delving into out-of-distribution detection with vision-language representations. Adv. Neural. Inf. Process. Syst. 35, 35087\u201335102 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"13_CR16","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1007\/s11263-023-01895-7","volume":"132","author":"Y Ming","year":"2024","unstructured":"Ming, Y., Li, Y.: How does fine-tuning impact out-of-distribution detection for vision-language models? Int. J. Comput. Vision 132(2), 596\u2013609 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR17","first-page":"76298","volume":"36","author":"A Miyai","year":"2023","unstructured":"Miyai, A., Yu, Q., Irie, G., Aizawa, K.: LoCoOp: Few-shot out-of-distribution detection via prompt learning. Adv. Neural. Inf. Process. Syst. 36, 76298\u201376310 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR18","unstructured":"Miyai, A., Yu, Q., Irie, G., Aizawa, K.: Zero-shot in-distribution detection in multi-object settings using vision-language foundation models. arXiv preprint arXiv:2304.04521 (2023)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Miyai, A., Yu, Q., Irie, G., Aizawa, K.: GL-MCM: global and local maximum concept matching for zero-shot out-of-distribution detection. Int. J. Comput. Vis. 11, 1\u201311 (2025)","DOI":"10.1007\/s11263-025-02356-z"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Noda, S., Miyai, A., Yu, Q., Irie, G., Aizawa, K.: A benchmark and evaluation for real-world out-of-distribution detection using vision-language models. arXiv preprint arXiv:2501.18463 (2025)","DOI":"10.1109\/ICIP55913.2025.11084642"},{"key":"13_CR21","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"13_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103357","volume":"99","author":"J Silva-Rodriguez","year":"2025","unstructured":"Silva-Rodriguez, J., Chakor, H., Kobbi, R., Dolz, J., Ayed, I.B.: 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."},{"issue":"1","key":"13_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl, P., Rosendahl, C., Kittler, H.: The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5(1), 1\u20139 (2018)","journal-title":"Sci. Data"},{"key":"13_CR24","unstructured":"Wang, M., et\u00a0al.: Common and rare fundus diseases identification using vision-language foundation model with knowledge of over 400 diseases. arXiv preprint arXiv:2406.09317 (2024)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: MedCLIP: contrastive learning from unpaired medical images and text. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing vol.\u00a02022, p.\u00a03876 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Wu, R., Zhang, C., Zhang, J., Zhou, Y., Zhou, T., Fu, H.: Mm-Retinal: knowledge-enhanced foundational pretraining with fundus image-text expertise. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 722\u2013732. Springer (2024)","DOI":"10.1007\/978-3-031-72378-0_67"},{"key":"13_CR27","unstructured":"Xia, P., et al.: HGCLIP: exploring vision-language models with graph representations for hierarchical understanding. arXiv preprint arXiv:2311.14064 (2023)"},{"issue":"10","key":"13_CR28","doi-asserted-by":"publisher","first-page":"2607","DOI":"10.1007\/s11263-023-01811-z","volume":"131","author":"J Yang","year":"2023","unstructured":"Yang, J., Zhou, K., Liu, Z.: Full-spectrum out-of-distribution detection. Int. J. Comput. Vision 131(10), 2607\u20132622 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR29","unstructured":"Zhang, R., et al.: Tip-Adapter: training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930 (2021)"},{"key":"13_CR30","unstructured":"Zhang, S., et\u00a0al.: BioMedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04971-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T06:44:28Z","timestamp":1771742668000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04971-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049704","9783032049711"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04971-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","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":"23 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":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}