{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:28Z","timestamp":1776888388165,"version":"3.51.2"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031721168","type":"print"},{"value":"9783031721175","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72117-5_6","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T12:02:53Z","timestamp":1727870573000},"page":"57-67","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Aligning Medical Images with\u00a0General Knowledge from\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Xiao","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwang-Ting","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"6_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv (2023)"},{"key":"6_CR2","unstructured":"Byra, M., Rachmadi, M.F., Skibbe, H.: Few-shot medical image classification with simple shape and texture text descriptors using vision-language models. arXiv (2023)"},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"102615","DOI":"10.1016\/j.media.2022.102615","volume":"82","author":"J Chen","year":"2022","unstructured":"Chen, J., Frey, E.C., He, Y., Segars, W.P., Li, Y., Du, Y.: TransMorph: transformer for unsupervised medical image registration. Med. Image Anal. 82, 102615 (2022)","journal-title":"Med. Image Anal."},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Derakhshani, M.M., et al.: Bayesian prompt learning for image-language model generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15237\u201315246 (2023)","DOI":"10.1109\/ICCV51070.2023.01398"},{"key":"6_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"issue":"1","key":"6_CR6","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1183\/09031936.01.00213501","volume":"18","author":"T Franquet","year":"2001","unstructured":"Franquet, T.: Imaging of pneumonia: trends and algorithms. Eur. Respir. J. 18(1), 196\u2013208 (2001)","journal-title":"Eur. Respir. J."},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"6_CR8","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1109\/JBHI.2018.2824327","volume":"23","author":"J Kawahara","year":"2018","unstructured":"Kawahara, J., Daneshvar, S., Argenziano, G., Hamarneh, G.: Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE J. Biomed. Health Inform. 23(2), 538\u2013546 (2018)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Kermany, D.S., et\u00a0al.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5), 1122\u20131131 (2018)","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: MaPLe: multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"6_CR11","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23390\u201323400 (2023)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"6_CR14","unstructured":"Lin, Y., Fang, X., Zhang, D., Cheng, K., Chen, H.: Boosting convolution with efficient MLP-permutation for volumetric medical image segmentation. arXiv (2023)"},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Lin, Y., Zhang, D., Fang, X., Chen, Y., Cheng, K.T., Chen, H.: Rethinking boundary detection in deep learning models for medical image segmentation. In: In: Frangi, A., de Bruijne, M., Wassermann, D., Navab, N. (eds.) Information Processing in Medical Imaging, IPMI 2023. LNCS, vol. 13939, pp. 730\u2013742. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-34048-2_56","DOI":"10.1007\/978-3-031-34048-2_56"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Liu, J., Hu, T., Zhang, Y., Gai, X., Feng, Y., Liu, Z.: A ChatGPT aided explainable framework for zero-shot medical image diagnosis. arXiv (2023)","DOI":"10.18653\/v1\/2024.findings-emnlp.583"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Markovic, S.N., et\u00a0al.: Malignant melanoma in the 21st century, part 1: epidemiology, risk factors, screening, prevention, and diagnosis. In: Mayo Clinic Proceedings, vol.\u00a082, pp. 364\u2013380. Elsevier (2007)","DOI":"10.1016\/S0025-6196(11)61033-1"},{"key":"6_CR18","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Patr\u00edcio, C., Neves, J.C., Teixeira, L.F.: Coherent concept-based explanations in medical image and its application to skin lesion diagnosis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3798\u20133807 (2023)","DOI":"10.1109\/CVPRW59228.2023.00394"},{"key":"6_CR20","unstructured":"Qin, Z., Yi, H.H., Lao, Q., Li, K.: Medical image understanding with pretrained vision language models: a comprehensive study. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"6_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":"6_CR22","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., Xu, C.: Visual-language prompt tuning with knowledge-guided context optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6757\u20136767 (2023)","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"6_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-030-87199-4_7","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"D You","year":"2021","unstructured":"You, D., Liu, F., Ge, S., Xie, X., Zhang, J., Wu, X.: AlignTransformer: hierarchical alignment of visual regions and disease tags for medical report generation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 72\u201382. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87199-4_7"},{"key":"6_CR24","doi-asserted-by":"publisher","first-page":"110250","DOI":"10.1016\/j.patcog.2024.110250","volume":"149","author":"F Zheng","year":"2024","unstructured":"Zheng, F., Cao, J., Yu, W., Chen, Z., Xiao, N., Lu, Y.: Exploring low-resource medical image classification with weakly supervised prompt learning. Pattern Recogn. 149, 110250 (2024)","journal-title":"Pattern Recogn."},{"key":"6_CR25","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"},{"issue":"9","key":"6_CR26","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72117-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:23:08Z","timestamp":1732839788000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72117-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031721168","9783031721175"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72117-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this paper.","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":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}