{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:13:28Z","timestamp":1772907208018,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031723896","type":"print"},{"value":"9783031723902","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\/978-3-031-72390-2_72","type":"book-chapter","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T10:03:14Z","timestamp":1729591394000},"page":"773-783","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["XCoOp: Explainable Prompt Learning for\u00a0Computer-Aided Diagnosis via\u00a0Concept-Guided Context Optimization"],"prefix":"10.1007","author":[{"given":"Yequan","family":"Bie","sequence":"first","affiliation":[]},{"given":"Luyang","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Zhixuan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,23]]},"reference":[{"key":"72_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"72_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et\u00a0al.: Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"72_CR3","doi-asserted-by":"crossref","unstructured":"Bie, Y., Luo, L., Chen, H.: Mica: towards explainable skin lesion diagnosis via multi-level image-concept alignment. arXiv preprint arXiv:2401.08527 (2024)","DOI":"10.1609\/aaai.v38i2.27842"},{"key":"72_CR4","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: Lasp: Text-to-text optimization for language-aware soft prompting of vision & language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23232\u201323241 (2023)","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"72_CR5","doi-asserted-by":"crossref","unstructured":"Carvalho, D.V., Pereira, E.M., Cardoso, J.S.: Machine learning interpretability: a survey on methods and metrics. Electronics 8(8), \u00a0832 (2019)","DOI":"10.3390\/electronics8080832"},{"key":"72_CR6","unstructured":"Chen, Z., Luo, L., Bie, Y., Chen, H.: Dia-llama: Towards large language model-driven CT report generation. arXiv preprint arXiv:2403.16386 (2024)"},{"key":"72_CR7","unstructured":"Daneshjou, R., Yuksekgonul, M., Cai, Z.R., Novoa, R., Zou, J.Y.: Skincon: A skin disease dataset densely annotated by domain experts for fine-grained debugging and analysis. Adv. Neural Inf. Process. Syst. 35, 18157\u201318167 (2022)"},{"issue":"2","key":"72_CR8","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman, D., Kohli, M.D., Rosenman, M.B., Shooshan, S.E., Rodriguez, L., Antani, S., Thoma, G.R., McDonald, C.J.: Preparing a collection of radiology examinations for distribution and retrieval. Journal of the American Medical Informatics Association 23(2), 304\u2013310 (2016)","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"72_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"5","key":"72_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2018","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM computing surveys (CSUR) 51(5), 1\u201342 (2018)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"72_CR11","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"},{"key":"72_CR12","unstructured":"Hsiao, J.H.W., Ngai, H.H.T., Qiu, L., Yang, Y., Cao, C.C.: Roadmap of designing cognitive metrics for explainable artificial intelligence (XAI). arXiv preprint arXiv:2108.01737 (2021)"},{"key":"72_CR13","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"72_CR14","doi-asserted-by":"crossref","unstructured":"Jin, W., Li, X., Fatehi, M., Hamarneh, G.: Guidelines and evaluation of clinical explainable AI in medical image analysis. Med. Image Anal. 84, 102684 (2023)","DOI":"10.1016\/j.media.2022.102684"},{"issue":"2","key":"72_CR15","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 journal of biomedical and health informatics 23(2), 538\u2013546 (2018)","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"72_CR16","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":"72_CR17","doi-asserted-by":"crossref","unstructured":"Lakkaraju, H., Kamar, E., Caruana, R., Leskovec, J.: Faithful and customizable explanations of black box models. In: Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, pp. 131\u2013138 (2019)","DOI":"10.1145\/3306618.3314229"},{"key":"72_CR18","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":"72_CR19","doi-asserted-by":"publisher","unstructured":"Lin, Y., Nie, D., Liu, Y., Yang, M., Zhang, D., Wen, X.: Multi-target domain adaptation with prompt learning for medical image segmentation. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention - MICCAI 2023, MICCAI 2023, LNCS, vol. 14220, pp. 717\u2013727. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43907-0_68","DOI":"10.1007\/978-3-031-43907-0_68"},{"key":"72_CR20","unstructured":"Lipton, Z.C.: The doctor just won\u2019t accept that! arXiv preprint arXiv:1711.08037 (2017)"},{"key":"72_CR21","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"72_CR22","unstructured":"Luo, L., Huang, X., Wang, M., Wan, Z., Chen, H.: Medical image debiasing by learning adaptive agreement from a biased council. arXiv preprint arXiv:2401.11713 (2024)"},{"issue":"11","key":"72_CR23","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-sne. Journal of machine learning research 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"72_CR24","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":"72_CR25","unstructured":"Rigotti, M., Miksovic, C., Giurgiu, I., Gschwind, T., Scotton, P.: Attention-based interpretability with concept transformers. In: International Conference on Learning Representations (2021)"},{"key":"72_CR26","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. The annals of mathematical statistics 22, 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"issue":"5","key":"72_CR27","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"C Rudin","year":"2019","unstructured":"Rudin, C.: Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nature machine intelligence 1(5), 206\u2013215 (2019)","journal-title":"Nat. Mach. Intell."},{"key":"72_CR28","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":"72_CR29","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: contrastive captioners are image-text foundation models. arxiv 2022. arXiv preprint arXiv:2205.01917"},{"key":"72_CR30","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":"72_CR31","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. International Journal of Computer Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis."}],"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\/978-3-031-72390-2_72","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T10:16:24Z","timestamp":1729592184000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72390-2_72"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723896","9783031723902"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72390-2_72","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":"23 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 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":"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"}}]}}