{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T07:47:10Z","timestamp":1758268030125,"version":"3.44.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049773","type":"print"},{"value":"9783032049780","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"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\/978-3-032-04978-0_19","type":"book-chapter","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T16:16:49Z","timestamp":1758212209000},"page":"194-204","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Eliminating Language Bias for\u00a0Medical Visual Question Answering with\u00a0Counterfactual Contrastive Training"],"prefix":"10.1007","author":[{"given":"Xingyu","family":"Wan","sequence":"first","affiliation":[]},{"given":"Qiaoying","family":"Teng","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yonghan","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Deqi","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"issue":"3","key":"19_CR1","doi-asserted-by":"publisher","first-page":"316","DOI":"10.3390\/jcm8030316","volume":"8","author":"M Aiello","year":"2019","unstructured":"Aiello, M., Cavaliere, C., D\u2019Albore, A., Salvatore, M.: The challenges of diagnostic imaging in the era of big data. J. Clin. Med. 8(3), 316 (2019)","journal-title":"J. Clin. Med."},{"key":"19_CR2","unstructured":"Cadene, R., Dancette, C., Cord, M., Parikh, D., et\u00a0al.: Rubi: reducing unimodal biases for visual question answering. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Cai, L., Fang, H., Xu, N., Ren, B.: Counterfactual causal-effect intervention for interpretable medical visual question answering. Authorea Preprints (2024)","DOI":"10.36227\/techrxiv.171440904.49751293\/v1"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Yang, D., Jiang, Y., Lei, Y., Zhang, L.: Miss: a generative pre-training and fine-tuning approach for med-vqa. In: International Conference on Artificial Neural Networks, pp. 299\u2013313. Springer (2024)","DOI":"10.1007\/978-3-031-72353-7_22"},{"issue":"11","key":"19_CR5","doi-asserted-by":"crossref","first-page":"13218","DOI":"10.1109\/TPAMI.2023.3289667","volume":"45","author":"L Chen","year":"2023","unstructured":"Chen, L., Zheng, Y., Niu, Y., Zhang, H., Xiao, J.: Counterfactual samples synthesizing and training for robust visual question answering. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13218\u201313234 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 679\u2013689. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, G., Wan, X.: Align, reason and learn: enhancing medical vision-and-language pre-training with knowledge. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5152\u20135161 (2022)","DOI":"10.1145\/3503161.3547948"},{"key":"19_CR8","unstructured":"Eslami, S., de\u00a0Melo, G., Meinel, C.: Does clip benefit visual question answering in the medical domain as much as it does in the general domain? arXiv preprint arXiv:2112.13906 (2021)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Gu, T., Yang, K., Liu, D., Cai, W.: Lapa: latent prompt assist model for medical visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4971\u20134980 (2024)","DOI":"10.1109\/CVPRW63382.2024.00502"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Han, X., Wang, S., Su, C., Huang, Q., Tian, Q.: Greedy gradient ensemble for robust visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1584\u20131593 (2021)","DOI":"10.1109\/ICCV48922.2021.00161"},{"issue":"2","key":"19_CR11","doi-asserted-by":"publisher","first-page":"103241","DOI":"10.1016\/j.ipm.2022.103241","volume":"60","author":"J Huang","year":"2023","unstructured":"Huang, J., Chen, Y., Li, Y., Yang, Z., Gong, X., Wang, F.L., Xu, X., Liu, W.: Medical knowledge-based network for patient-oriented visual question answering. Inf. Process. Manag. 60(2), 103241 (2023)","journal-title":"Inf. Process. Manag."},{"issue":"3","key":"19_CR12","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1007\/s00146-020-01085-w","volume":"36","author":"M Kiener","year":"2021","unstructured":"Kiener, M.: Artificial intelligence in medicine and the disclosure of risks. AI Soc. 36(3), 705\u2013713 (2021)","journal-title":"AI Soc."},{"issue":"1","key":"19_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5(1), 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., He, J., Zhao, Z., Zhong, S.: Masked vision and language pre-training with unimodal and multimodal contrastive losses for medical visual question answering. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 374\u2013383. Springer (2023)","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., Tan, L., Liao, J., Zhong, S.: Self-supervised vision-language pretraining for medial visual question answering. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Liang, Z., Hu, H., Zhu, J.: Lpf: a language-prior feedback objective function for de-biased visual question answering. In: Proceedings of the 44th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1955\u20131959 (2021)","DOI":"10.1145\/3404835.3462981"},{"key":"19_CR17","doi-asserted-by":"publisher","first-page":"102611","DOI":"10.1016\/j.artmed.2023.102611","volume":"143","author":"Z Lin","year":"2023","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. Artif. Intell. Med. 143, 102611 (2023)","journal-title":"Artif. Intell. Med."},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Wu, X.M.: Contrastive pre-training and representation distillation for medical visual question answering based on radiology images. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part II 24, pp. 210\u2013220. Springer (2021)","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"19_CR20","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"19_CR21","doi-asserted-by":"publisher","unstructured":"Neumann, M., King, D., Beltagy, I., Ammar, W.: ScispaCy: fast and robust models for biomedical natural language processing. In: Proceedings of the 18th BioNLP Workshop and Shared Task, pp. 319\u2013327. ACL, Florence, Italy, August 2019. https:\/\/doi.org\/10.18653\/v1\/W19-5034, https:\/\/www.aclweb.org\/anthology\/W19-5034","DOI":"10.18653\/v1\/W19-5034"},{"key":"19_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/978-3-030-32251-9_57","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"BD Nguyen","year":"2019","unstructured":"Nguyen, B.D., Do, T.-T., Nguyen, B.X., Do, T., Tjiputra, E., Tran, Q.D.: Overcoming data limitation in medical visual question answering. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 522\u2013530. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32251-9_57"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual vqa: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"19_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":"19_CR25","doi-asserted-by":"crossref","unstructured":"Vosoughi, A., Deng, S., Zhang, S., Tian, Y., Xu, C., Luo, J.: Cross modality bias in visual question answering: a causal view with possible worlds vqa. IEEE Trans. Multimedia (2024)","DOI":"10.1109\/TMM.2024.3380259"},{"key":"19_CR26","unstructured":"Yuan, D.: Language bias in visual question answering: a survey and taxonomy. arXiv preprint arXiv:2111.08531 (2021)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Zhan, C., et al.: Debiasing medical visual question answering via counterfactual training. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 382\u2013393. Springer (2023)","DOI":"10.1007\/978-3-031-43895-0_36"},{"key":"19_CR28","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)"}],"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\/978-3-032-04978-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T22:07:08Z","timestamp":1758233228000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04978-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"ISBN":["9783032049773","9783032049780"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04978-0_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]},"assertion":[{"value":"19 September 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":"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"}}]}}