{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T01:07:15Z","timestamp":1793322435165,"version":"4.5.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031164422","type":"print"},{"value":"9783031164439","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16443-9_68","type":"book-chapter","created":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T09:30:11Z","timestamp":1663234211000},"page":"714-724","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["RepsNet: Combining Vision with\u00a0Language for\u00a0Automated Medical Reports"],"prefix":"10.1007","author":[{"given":"Ajay K.","family":"Tanwani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joelle","family":"Barral","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Freedman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,16]]},"reference":[{"key":"68_CR1","unstructured":"Abacha, A.B., Hasan, S.A., Datla, V., Liu, J., Demner-Fushman, D., M\u00fcller, H.: VQA-MED: overview of the medical visual question answering task at ImageCLEF 2019. In: CLEF (2019)"},{"key":"68_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100557","volume":"24","author":"O Alfarghaly","year":"2021","unstructured":"Alfarghaly, O., Khaled, R., Elkorany, A., Helal, M., Fahmy, A.: Automated radiology report generation using conditioned transformers. Inform. Med. Unlocked 24, 100557 (2021)","journal-title":"Inform. Med. Unlocked"},{"key":"68_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and VQA. CoRR abs\/1707.07998 (2017)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"68_CR4","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. CoRR abs\/1505.00468 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"68_CR5","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":"68_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. CoRR abs\/2002.05709 (2020)"},{"key":"68_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T., Wan, X.: Generating radiology reports via memory-driven transformer. CoRR abs\/2010.16056 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"issue":"2","key":"68_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., et al.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23(2), 304\u2013310 (2016)","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"68_CR9","doi-asserted-by":"crossref","unstructured":"Desai, K., Johnson, J.: VirTex: learning visual representations from textual annotations. CoRR abs\/2006.06666 (2020)","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"68_CR10","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805 (2018)"},{"key":"68_CR11","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":"68_CR12","unstructured":"Dong, L., et al.: Unified language model pre-training for natural language understanding and generation. In: NeurIPS. vol. 32 (2019)"},{"key":"68_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, T., Vahdat, A., Chechik, G., Yang, X., Kautz, J., Hoiem, D.: Contrastive learning for weakly supervised phrase grounding. CoRR abs\/2006.09920 (2020)","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"68_CR14","unstructured":"Huang, Z., Zeng, Z., Liu, B., Fu, D., Fu, J.: Pixel-BERT: aligning image pixels with text by deep multi-modal transformers. CoRR abs\/2004.00849 (2020)"},{"key":"68_CR15","doi-asserted-by":"crossref","unstructured":"Jing, B., Wang, Z., Xing, E.P.: Show, describe and conclude: on exploiting the structure information of chest X-ray reports. CoRR abs\/2004.12274 (2020)","DOI":"10.18653\/v1\/P19-1657"},{"key":"68_CR16","unstructured":"Jing, B., Xie, P., Xing, E.P.: On the automatic generation of medical imaging reports. CoRR abs\/1711.08195 (2017), http:\/\/arxiv.org\/abs\/1711.08195"},{"key":"68_CR17","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUS. arXiv preprint arXiv:1702.08734 (2017)"},{"key":"68_CR18","unstructured":"Kim, J.H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"68_CR19","doi-asserted-by":"crossref","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Nat. Sci. Data 5 (2018)","DOI":"10.1038\/sdata.2018.251"},{"key":"68_CR20","unstructured":"Li, C.Y., Liang, X., Hu, Z., Xing, E.P.: Hybrid retrieval-generation reinforced agent for medical image report generation. CoRR abs\/1805.08298 (2018)"},{"key":"68_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-87196-3_20","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"B Liu","year":"2021","unstructured":"Liu, B., Zhan, L.-M., Wu, X.-M.: Contrastive pre-training and\u00a0representation distillation for\u00a0medical visual question answering based on\u00a0radiology images. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 210\u2013220. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_20"},{"key":"68_CR22","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, X., Ge, S., Fan, W., Zou, Y.: Exploring and distilling posterior and prior knowledge for radiology report generation. In: CVPR, pp. 13753\u201313762 (2021)","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"68_CR23","unstructured":"Liu, G., et al.: Clinically accurate chest X-ray report generation. CoRR abs\/1904.02633 (2019)"},{"key":"68_CR24","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VILBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. CoRR abs\/1908.02265 (2019)"},{"key":"68_CR25","doi-asserted-by":"crossref","unstructured":"Najdenkoska, I., Zhen, X., Worring, M., Shao, L.: Variational topic inference for chest X-ray report generation. CoRR abs\/2107.07314 (2021)","DOI":"10.1007\/978-3-030-87199-4_59"},{"key":"68_CR26","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"68_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. CoRR abs\/2103.00020 (2021)"},{"key":"68_CR28","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"68_CR29","doi-asserted-by":"publisher","first-page":"50626","DOI":"10.1109\/ACCESS.2020.2980024","volume":"8","author":"F Ren","year":"2020","unstructured":"Ren, F., Zhou, Y.: CGMVQA: a new classification and generative model for medical visual question answering. IEEE Access 8, 50626\u201350636 (2020)","journal-title":"IEEE Access"},{"key":"68_CR30","doi-asserted-by":"crossref","unstructured":"Sariyildiz, M.B., Perez, J., Larlus, D.: Learning visual representations with caption annotations. CoRR abs\/2008.01392 (2020)","DOI":"10.1007\/978-3-030-58598-3_10"},{"key":"68_CR31","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., et al.: Grad-CAM: why did you say that? Visual explanations from deep networks via gradient-based localization. CoRR abs\/1610.02391 (2016)","DOI":"10.1109\/ICCV.2017.74"},{"key":"68_CR32","doi-asserted-by":"publisher","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) (2021). https:\/\/doi.org\/10.1038\/s41598-021-98390-1","DOI":"10.1038\/s41598-021-98390-1"},{"key":"68_CR33","unstructured":"Sun, C., Baradel, F., Murphy, K., Schmid, C.: Contrastive bidirectional transformer for temporal representation learning. CoRR abs\/1906.05743 (2019)"},{"key":"68_CR34","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. CoRR abs\/1904.01766 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"68_CR35","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. CoRR abs\/1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"68_CR36","unstructured":"Xia, Q., et al.: XGPT: cross-modal generative pre-training for image captioning. CoRR abs\/2003.01473 (2020)"},{"key":"68_CR37","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. CoRR abs\/1611.05431 (2016)","DOI":"10.1109\/CVPR.2017.634"},{"key":"68_CR38","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, vol. 37, pp. 2048\u20132057 (2015)"},{"key":"68_CR39","unstructured":"Yu, W., et al.: A survey of knowledge-enhanced text generation. CoRR abs\/2010.04389 (2020)"},{"key":"68_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1007\/978-3-030-32226-7_80","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"J Yuan","year":"2019","unstructured":"Yuan, J., Liao, H., Luo, R., Luo, J.: Automatic radiology report generation based on multi-view image fusion and medical concept enrichment. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 721\u2013729. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32226-7_80"},{"key":"68_CR41","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: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2345\u20132354 (2020)","DOI":"10.1145\/3394171.3413761"},{"key":"68_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Xu, Z., Yu, Q., Yuille, A., Xu, D.: When radiology report generation meets knowledge graph. In: AAAI, vol. 34, pp. 12910\u201312917 (2020)","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"68_CR43","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive learning of medical visual representations from paired images and text. CoRR abs\/2010.00747 (2020)"},{"key":"68_CR44","unstructured":"Ziegler, Z.M., Melas-Kyriazi, L., Gehrmann, S., Rush, A.M.: Encoder-agnostic adaptation for conditional language generation. CoRR abs\/1908.06938 (2019)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16443-9_68","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:51:18Z","timestamp":1709830278000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16443-9_68"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164422","9783031164439"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16443-9_68","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft Conference","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1831","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"574","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}