{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:19:39Z","timestamp":1743142779573,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703775"},{"type":"electronic","value":"9783031703782"}],"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\/978-3-031-70378-2_27","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T09:02:05Z","timestamp":1725181325000},"page":"435-451","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["BESTMVQA: A Benchmark Evaluation System for\u00a0Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Xiaojie","family":"Hong","sequence":"first","affiliation":[]},{"given":"Zixin","family":"Song","sequence":"additional","affiliation":[]},{"given":"Liangzhi","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8677-9080","authenticated-orcid":false,"given":"Xiaoli","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Feiyan","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"27_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"27_CR2","unstructured":"Ben\u00a0Abacha, A., Hasan, S.A., Datla, V.V., Demner-Fushman, D., M\u00fcller, H.: VQA-med: Overview of the medical visual question answering task at imageclef 2019. In: CLEF, 9\u201312 September 2019 (2019)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Diao, S., Wang, B., Li, G., Wan, X.: Towards unifying medical vision-and-language pre-training via soft prompts. arXiv preprint arXiv:2302.08958 (2023)","DOI":"10.1109\/ICCV51070.2023.02139"},{"key":"27_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-030-87240-3_7","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"T Do","year":"2021","unstructured":"Do, T., Nguyen, B.X., Tjiputra, E., Tran, M., Tran, Q.D., Nguyen, A.: Multiple meta-model quantifying for medical visual question answering. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 64\u201374. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_7"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Dou, Z.Y., et al.: An empirical study of training end-to-end vision-and-language transformers. In: CVPR, pp. 18166\u201318176 (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"27_CR6","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":"27_CR7","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126\u20131135. PMLR (2017)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Gong, H., Chen, G., Liu, S., Yu, Y., Li, G.: Cross-modal self-attention with multi-task pre-training for medical visual question answering. In: ACM ICMR, pp. 456\u2013460 (2021)","DOI":"10.1145\/3460426.3463584"},{"issue":"11","key":"27_CR9","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.1109\/TMI.2022.3185008","volume":"41","author":"H Gong","year":"2022","unstructured":"Gong, H., Chen, G., Mao, M., Li, Z., Li, G.: VQAMix: conditional triplet mixup for medical visual question answering. IEEE Trans. Med. Imaging 41(11), 3332\u20133343 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"27_CR10","unstructured":"Han, T., et al.: Medalpaca\u2013an open-source collection of medical conversational AI models and training data. arXiv preprint arXiv:2304.08247 (2023)"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Pathological visual question answering. arXiv preprint arXiv:2010.12435 (2020)","DOI":"10.36227\/techrxiv.13127537.v1"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, X., Liu, F., Huang, G.: OVQA: a clinically generated visual question answering dataset. In: ACM SIGIR, pp. 2924\u20132938 (2022)","DOI":"10.1145\/3477495.3531724"},{"key":"27_CR13","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/978-3-031-46677-9_32","volume-title":"ADMA","author":"Y Huang","year":"2023","unstructured":"Huang, Y., Wang, X., Su, J.: An effective pre-trained visual encoder for medical visual question answering. In: Yang, X., et al. (eds.) ADMA. LNCS, vol. 14180, pp. 466\u2013481. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-46677-9_32"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Khare, Y., Bagal, V., Mathew, M., Devi, A., Priyakumar, U.D., Jawahar, C.: Mmbert: Multimodal BERT pretraining for improved medical VQA. In: ISBI, pp. 1033\u20131036. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434063"},{"issue":"1","key":"27_CR15","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":"27_CR16","unstructured":"Li, C., et al.: LLaVA-med: training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)"},{"key":"27_CR17","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: ISBI, pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"27_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-642-21735-7_7","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2011","author":"J Masci","year":"2011","unstructured":"Masci, J., Meier, U., Cire\u015fan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 52\u201359. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-21735-7_7"},{"key":"27_CR19","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":"27_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/978-3-030-01364-6_20","volume-title":"Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis","author":"O Pelka","year":"2018","unstructured":"Pelka, O., Koitka, S., R\u00fcckert, J., Nensa, F., Friedrich, C.M.: Radiology objects in COntext (ROCO): a multimodal image dataset. In: Stoyanov, D., et al. (eds.) LABELS\/CVII\/STENT -2018. LNCS, vol. 11043, pp. 180\u2013189. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01364-6_20"},{"key":"27_CR21","unstructured":"Sarrouti, M.: NLM at VQA-med 2020: visual question answering and generation in the medical domain (2020)"},{"issue":"1","key":"27_CR22","doi-asserted-by":"publisher","first-page":"19826","DOI":"10.1038\/s41598-021-98390-1","volume":"11","author":"D Sharma","year":"2021","unstructured":"Sharma, D., Purushotham, S., Reddy, C.K.: Medfusenet: an attention-based multimodal deep learning model for visual question answering in the medical domain. Sci. Rep. 11(1), 19826 (2021)","journal-title":"Sci. Rep."},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Srivastava, Y., Murali, V., Dubey, S.R., Mukherjee, S.: Visual Question Answering using Deep Learning: A Survey and Performance Analysis, pp. 75\u201386 (2021)","DOI":"10.1007\/978-981-16-1092-9_7"},{"key":"27_CR24","unstructured":"Wang, H., et al.: Huatuo: tuning llama model with Chinese medical knowledge. arXiv preprint arXiv:2304.06975 (2023)"},{"key":"27_CR25","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: PMC-llama: further finetuning llama on medical papers. arXiv preprint arXiv:2304.14454 (2023)"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Wu, Q., Teney, D., Wang, P., Shen, C., Dick, A., Hengel, A.: Visual question answering: a survey of methods and datasets. Cornell University - arXiv, Cornell University - arXiv (2016)","DOI":"10.1016\/j.cviu.2017.05.001"},{"issue":"5","key":"27_CR27","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1109\/JAS.2023.123618","volume":"10","author":"T Wu","year":"2023","unstructured":"Wu, T., et al.: A brief overview of ChatGPT: the history, status quo and potential future development. IEEE\/CAA J. Automatica Sinica 10(5), 1122\u20131136 (2023)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"27_CR28","unstructured":"Xiong, H., et al.: Doctorglm: fine-tuning your Chinese doctor is not a herculean task. arXiv preprint arXiv:2304.01097 (2023)"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Vision-language pre-training with triple contrastive learning. In: CVPR, pp. 15671\u201315680 (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Yasunaga, M., Leskovec, J., Liang, P.: LinkBERT: pretraining language models with document links. In: ACL, pp. 8003\u20138016 (2022)","DOI":"10.18653\/v1\/2022.acl-long.551"},{"key":"27_CR31","unstructured":"Yunxiang, L., Zihan, L., Kai, Z., Ruilong, D., You, Z.: Chatdoctor: a medical chat model fine-tuned on llama model using medical domain knowledge. arXiv preprint arXiv:2303.14070 (2023)"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Zhan, L.M., Liu, B., Fan, L., Chen, J., Wu, X.M.: Medical visual question answering via conditional reasoning. In: ACM MM, pp. 2345\u20132354 (2020)","DOI":"10.1145\/3394171.3413761"},{"key":"27_CR33","unstructured":"Zhang, X., et al.: PMC-VQA: visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"key":"27_CR34","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70378-2_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T09:07:48Z","timestamp":1725181668000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70378-2_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703775","9783031703782"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70378-2_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}