{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T08:49:22Z","timestamp":1769849362272,"version":"3.49.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031720857","type":"print"},{"value":"9783031720864","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\/978-3-031-72086-4_39","type":"book-chapter","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:34:45Z","timestamp":1727987685000},"page":"415-425","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Coarse-to-Fine Grained Representations in\u00a0Contrastive Learning for\u00a0Differential Medical Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Xiao","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicheng","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodi","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,4]]},"reference":[{"key":"39_CR1","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2019), https:\/\/api.semanticscholar.org\/CorpusID:52967399"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Eslami, S., Meinel, C., de\u00a0Melo, G.: Pubmedclip: How much does clip benefit visual question answering in the medical domain? In: Findings (2023), https:\/\/api.semanticscholar.org\/CorpusID:258378275","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Farhan, A.M.Q., Yang, S.: Automatic lung disease classification from the chest x-ray images using hybrid deep learning algorithm. Multimedia Tools and Applications pp. 1 \u2013 27 (2023), https:\/\/api.semanticscholar.org\/CorpusID:257690179","DOI":"10.1007\/s11042-024-20022-3"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Gu, Y., Tinn, R., Cheng, H., Lucas, M.R., Usuyama, N., Liu, X., Naumann, T., Gao, J., Poon, H.: Domain-specific language model pretraining for biomedical natural language processing. ACM Transactions on Computing for Healthcare (HEALTH) 3, 1 \u2013 23 (2020), https:\/\/api.semanticscholar.org\/CorpusID:220919723","DOI":"10.1145\/3458754"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 770\u2013778 (2015), https:\/\/api.semanticscholar.org\/CorpusID:206594692","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Hu, X., Gu, L., An, Q.A., Zhang, M., Liu, L., Kobayashi, K., Harada, T., Summers, R.M., Zhu, Y.: Expert knowledge-aware image difference graph representation learning for difference-aware medical visual question answering. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2023), https:\/\/api.semanticscholar.org\/CorpusID:260125237","DOI":"10.1145\/3580305.3599819"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhang, X., Zhang, S.: Kiut: Knowledge-injected u-transformer for radiology report generation. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 19809\u201319818 (2023), https:\/\/api.semanticscholar.org\/CorpusID:259203473","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Irvin, J.A., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R.L., Shpanskaya, K.S., Seekins, J., Mong, D.A., Halabi, S.S., Sandberg, J.K., Jones, R., Larson, D.B., Langlotz, C., Patel, B.N., Lungren, M.P., Ng, A.: Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI Conference on Artificial Intelligence (2019), https:\/\/api.semanticscholar.org\/CorpusID:58981871","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Johnson, A.E.W., Pollard, T.J., Berkowitz, S.J., Greenbaum, N.R., Lungren, M.P., ying Deng, C., Mark, R.G., Horng, S.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Scientific Data 6 (2019), https:\/\/api.semanticscholar.org\/CorpusID:209342303","DOI":"10.1038\/s41597-019-0322-0"},{"key":"39_CR10","unstructured":"Kipf, T., Welling, M.: Semi-supervised classification with graph convolutional networks. ArXiv abs\/1609.02907 (2016), https:\/\/api.semanticscholar.org\/CorpusID:3144218"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Kougia, V., Pavlopoulos, J., Androutsopoulos, I.: A survey on biomedical image captioning. ArXiv abs\/1905.13302 (2019), https:\/\/api.semanticscholar.org\/CorpusID:173188095","DOI":"10.18653\/v1\/W19-1803"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Lau, J.J., Gayen, S., Abacha, A.B., Demner-Fushman, D.: Descriptor : A dataset of clinically generated visual questions and answers about radiology images (2018), https:\/\/api.semanticscholar.org\/CorpusID:53712941","DOI":"10.1038\/sdata.2018.251"},{"key":"39_CR13","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (2022), https:\/\/api.semanticscholar.org\/CorpusID:246411402"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, B., Chen, Z., Lin, H., Liang, X., Chang, X.: Dynamic graph enhanced contrastive learning for chest x-ray report generation. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 3334\u20133343 (2023), https:\/\/api.semanticscholar.org\/CorpusID:257631847","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Nguyen, H.Q., Lam, K., Le, L.T., Pham, H., Tran, D.Q., Nguyen, D.B., Le, D.D., Pham, C.M., Tong, H., Dinh, D.H., Do, C.D., Doan, L.T., Nguyen, C.N., Nguyen, B.T., Nguyen, Q.V., Hoang, A.D., Phan, H.N., Nguyen, A.T., Ho, P., Ngo, D.T., Nguyen, N.T., Nguyen, N.T., Dao, M.S., Vu, V.: Vindr-cxr: An open dataset of chest x-rays with radiologist\u2019s annotations. Scientific Data 9 (2020), https:\/\/api.semanticscholar.org\/CorpusID:229923729","DOI":"10.1038\/s41597-022-01498-w"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Annual Meeting of the Association for Computational Linguistics (2002), https:\/\/api.semanticscholar.org\/CorpusID:11080756","DOI":"10.3115\/1073083.1073135"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Park, D.H., Darrell, T., Rohrbach, A.: Robust change captioning. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) pp. 4623\u20134632 (2019), https:\/\/api.semanticscholar.org\/CorpusID:119189647","DOI":"10.1109\/ICCV.2019.00472"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Qiu, Y., Yamamoto, S., Nakashima, K., Suzuki, R., Iwata, K., Kataoka, H., Satoh, Y.: Describing and localizing multiple changes with transformers. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) pp. 1951\u20131960 (2021), https:\/\/api.semanticscholar.org\/CorpusID:232380403","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"39_CR19","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018), https:\/\/api.semanticscholar.org\/CorpusID:49313245"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 1137\u20131149 (2015), https:\/\/api.semanticscholar.org\/CorpusID:10328909","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Tanida, T., M\u00fcller, P., Kaissis, G., Rueckert, D.: Interactive and explainable region-guided radiology report generation. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 7433\u20137442 (2023), https:\/\/api.semanticscholar.org\/CorpusID:258179419","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Tu, Y., Li, L., Su, L., Zha, Z.J., Yan, C., Huang, Q.: Self-supervised cross-view representation reconstruction for change captioning. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) pp. 2793\u20132803 (2023), https:\/\/api.semanticscholar.org\/CorpusID:263136677","DOI":"10.1109\/ICCV51070.2023.00263"},{"key":"39_CR23","unstructured":"Wu, J.T., Agu, N.N., Lourentzou, I., Sharma, A., Paguio, J.A., Yao, J.S., Dee, E.C., Mitchell, W., Kashyap, S., Giovannini, A., Celi, L.A., Moradi, M.: Chest imagenome dataset for clinical reasoning. ArXiv abs\/2108.00316 (2021), https:\/\/api.semanticscholar.org\/CorpusID:235420881"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Yao, L., Wang, W., Jin, Q.: Image difference captioning with pre-training and contrastive learning. In: AAAI Conference on Artificial Intelligence (2022), https:\/\/api.semanticscholar.org\/CorpusID:246680391","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Xu, Z., Yu, Q., Yuille, A.L., Xu, D.: When radiology report generation meets knowledge graph. In: AAAI Conference on Artificial Intelligence (2020), https:\/\/api.semanticscholar.org\/CorpusID:211171529","DOI":"10.1609\/aaai.v34i07.6989"}],"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\/978-3-031-72086-4_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:39:13Z","timestamp":1727987953000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72086-4_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720857","9783031720864"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72086-4_39","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":"4 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 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":"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"}}]}}