{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T22:30:53Z","timestamp":1774996253584,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439926","type":"print"},{"value":"9783031439933","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43993-3_51","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:08:57Z","timestamp":1696115337000},"page":"525-536","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":123,"title":["PMC-CLIP: Contrastive Language-Image Pre-training Using Biomedical Documents"],"prefix":"10.1007","author":[{"given":"Weixiong","family":"Lin","sequence":"first","affiliation":[]},{"given":"Ziheng","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Xiaoman","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Chaoyi","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"51_CR1","doi-asserted-by":"publisher","first-page":"D267","DOI":"10.1093\/nar\/gkh061","volume":"32","author":"Olivier Bodenreider","year":"2004","unstructured":"Bodenreider, Olivier: The unified medical language system (umls): integrating biomedical terminology. Nucleic Acids Research 32, D267\u2013D270 (2004)","journal-title":"Nucleic Acids Research"},{"key":"51_CR2","first-page":"1877","volume":"33","author":"Tom Brown","year":"2020","unstructured":"Brown, Tom, et al.: Language models are few-shot learners. Advances in Neural Information Processing Systems 33, 1877\u20131901 (2020)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"51_CR3","doi-asserted-by":"crossref","unstructured":"Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. End-to-end object detection with transformers. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16, pages 213\u2013229. Springer, 2020","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"51_CR4","doi-asserted-by":"crossref","unstructured":"Zhihong Chen, Yuhao Du, Jinpeng Hu, Yang Liu, Guanbin Li, Xiang Wan, and Tsung-Hui Chang. Multi-modal masked autoencoders for medical vision-and-language pre-training. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part V, pages 679\u2013689. Springer, 2022","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"51_CR5","doi-asserted-by":"crossref","unstructured":"Zhihong Chen, Guanbin Li, and Xiang Wan. Align, reason and learn: Enhancing medical vision-and-language pre-training with knowledge. In Proceedings of the 30th ACM International Conference on Multimedia, pages 5152\u20135161, 2022","DOI":"10.1145\/3503161.3547948"},{"key":"51_CR6","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.future.2022.04.025","volume":"135","author":"Jianhong Cheng","year":"2022","unstructured":"Cheng, Jianhong, Kuang, Hulin, Zhao, Qichang, Wang, Yahui, Lei, Xu., Liu, Jin, Wang, Jianxin: Dwt-cv: Dense weight transfer-based cross validation strategy for model selection in biomedical data analysis. Future Generation Computer Systems 135, 20\u201329 (2022)","journal-title":"Future Generation Computer Systems"},{"key":"51_CR7","unstructured":"Jacob Devlin et al. Bert: Pre-training of deep bidirectional transformers for language understanding. ArXiv preprint ArXiv:1810.04805, 2018"},{"key":"51_CR8","unstructured":"Ming Ding et al. Cogview2: Faster and better text-to-image generation via hierarchical transformers. ArXiv preprint ArXiv:2204.14217, 2022"},{"key":"51_CR9","doi-asserted-by":"crossref","unstructured":"Zi-Yi Dou et al. An empirical study of training end-to-end vision-and-language transformers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 18166\u201318176, 2022","DOI":"10.1109\/CVPR52688.2022.01763"},{"issue":"12","key":"51_CR10","doi-asserted-by":"publisher","first-page":"8875","DOI":"10.1109\/TCSVT.2022.3195727","volume":"32","author":"Xiaolong Ge","year":"2022","unstructured":"Ge, Xiaolong, et al.: A self-adaptive discriminative autoencoder for medical applications. IEEE Transactions on Circuits and Systems for Video Technology 32(12), 8875\u20138886 (2022)","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"1","key":"51_CR11","first-page":"1","volume":"3","author":"Gu Yu","year":"2021","unstructured":"Yu, Gu., Tinn, Robert, Cheng, Hao, Lucas, Michael, Usuyama, Naoto, Liu, Xiaodong, Naumann, Tristan, Gao, Jianfeng, Poon, Hoifung: Domain-specific language model pretraining for biomedical natural language processing. ACM Transactions on Computing for Healthcare (HEALTH) 3(1), 1\u201323 (2021)","journal-title":"ACM Transactions on Computing for Healthcare (HEALTH)"},{"key":"51_CR12","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770\u2013778, 2016"},{"key":"51_CR13","doi-asserted-by":"crossref","unstructured":"Shih-Cheng Huang, Liyue Shen, Matthew P Lungren, and Serena Yeung. Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pages 3942\u20133951, 2021","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"51_CR14","doi-asserted-by":"crossref","unstructured":"KV Jobin, Ajoy Mondal, and CV Jawahar. Docfigure: A dataset for scientific document figure classification. In 2019 International Conference on Document Analysis and Recognition Workshops, volume 1, pages 74\u201379. IEEE, 2019","DOI":"10.1109\/ICDARW.2019.00018"},{"issue":"1","key":"51_CR15","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"Alistair EW Johnson","year":"2019","unstructured":"Johnson, Alistair EW., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Scientific Data 6(1), 317 (2019)","journal-title":"Scientific Data"},{"key":"51_CR16","unstructured":"Wonjae Kim et al. Vilt: Vision-and-language transformer without convolution or region supervision. In International Conference on Machine Learning, pages 5583\u20135594. PMLR, 2021"},{"key":"51_CR17","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"Ranjay Krishna","year":"2017","unstructured":"Krishna, Ranjay, et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision 123, 32\u201373 (2017)","journal-title":"International Journal of Computer Vision"},{"key":"51_CR18","doi-asserted-by":"crossref","unstructured":"Jason J Lau et al. A dataset of clinically generated visual questions and answers about radiology images. Scientific Data, 5(1), 1\u201310, 2018","DOI":"10.1038\/sdata.2018.251"},{"key":"51_CR19","first-page":"9694","volume":"34","author":"Junnan Li","year":"2021","unstructured":"Li, Junnan, Selvaraju, Ramprasaath, Gotmare, Akhilesh, Joty, Shafiq, Xiong, Caiming, Hoi, Steven Chu Hong.: Align before fuse: Vision and language representation learning with momentum distillation. Advances in Neural Information Processing Systems 34, 9694\u20139705 (2021)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"51_CR20","doi-asserted-by":"crossref","unstructured":"Tsung-Yi Lin et al. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13, pages 740\u2013755. Springer, 2014","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"51_CR21","doi-asserted-by":"crossref","unstructured":"Bo Liu et al. Contrastive pre-training and representation distillation for medical visual question answering based on radiology images. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2021: 24th International Conference, Strasbourg, France, September 27-October 1, 2021, Proceedings, Part II 24, pages 210\u2013220. Springer, 2021","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"51_CR22","doi-asserted-by":"crossref","unstructured":"Bo Liu et al. Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pages 1650\u20131654. IEEE, 2021","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"51_CR23","unstructured":"Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. In International Conference on Learning Representations, 2017"},{"key":"51_CR24","doi-asserted-by":"crossref","unstructured":"Binh D Nguyen et al. Overcoming data limitation in medical visual question answering. In Medical Image Computing and Computer Assisted Intervention-MICCAI 2019, pages 522\u2013530. Springer, 2019","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"51_CR25","unstructured":"Aaron van den Oord et al. Representation learning with contrastive predictive coding. ArXiv preprint ArXiv:1807.03748, 2018"},{"key":"51_CR26","unstructured":"Vicente Ordonez et al. Im2text: Describing images using 1 million captioned photographs. Advances in Neural Information Processing Systems, 24, 2011"},{"key":"51_CR27","unstructured":"Long Ouyang et al. Training language models to follow instructions with human feedback. ArXiv preprint ArXiv:2203.02155, 2022"},{"key":"51_CR28","doi-asserted-by":"crossref","unstructured":"Obioma Pelka, Sven Koitka, Johannes R\u00fcckert, Felix Nensa, and Christoph M Friedrich. Radiology objects in context (roco): a multimodal image dataset. In MICCAI Workshop on Large-scale Annotation of Biomedical Data and Expert Label Synthesis (LABELS) 2018, pages 180\u2013189. Springer, 2018","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"51_CR29","unstructured":"Alec Radford et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, pages 8748\u20138763. PMLR, 2021"},{"key":"51_CR30","unstructured":"Aditya Ramesh et al. Hierarchical text-conditional image generation with clip latents. ArXiv preprint ArXiv:2204.06125, 2022"},{"key":"51_CR31","doi-asserted-by":"crossref","unstructured":"Richard J Roberts. Pubmed central: The genbank of the published literature, 2001","DOI":"10.1073\/pnas.98.2.381"},{"key":"51_CR32","unstructured":"Eric Schwenker et al. Exsclaim!-an automated pipeline for the construction of labeled materials imaging datasets from literature. ArXiv preprint ArXiv:2103.10631, 2021"},{"key":"51_CR33","doi-asserted-by":"crossref","unstructured":"Piyush Sharma et al. Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2556\u20132565, 2018","DOI":"10.18653\/v1\/P18-1238"},{"key":"51_CR34","doi-asserted-by":"crossref","unstructured":"Sanjay Subramanian et al. Medicat: A dataset of medical images, captions, and textual references. In Findings of EMNLP, 2020","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"51_CR35","doi-asserted-by":"crossref","unstructured":"Zifeng Wang, Zhenbang Wu, Dinesh Agarwal, and Jimeng Sun. Medclip: Contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163, 2022","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"51_CR36","unstructured":"Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, and Weidi Xie. Medklip: Medical knowledge enhanced language-image pre-training. MedRxiv, pages 2023\u201301, 2023"},{"issue":"1","key":"51_CR37","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41597-022-01721-8","volume":"10","author":"Jiancheng Yang","year":"2023","unstructured":"Yang, Jiancheng, et al.: Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification. Scientific Data 10(1), 41 (2023)","journal-title":"Scientific Data"},{"key":"51_CR38","doi-asserted-by":"crossref","unstructured":"Zheng Yuan, Qiao Jin, Chuanqi Tan, Zhengyun Zhao, Hongyi Yuan, Fei Huang, and Songfang Huang. Ramm: Retrieval-augmented biomedical visual question answering with multi-modal pre-training. arXiv preprint arXiv:2303.00534, 2023","DOI":"10.1145\/3581783.3611830"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43993-3_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T16:11:42Z","timestamp":1712074302000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43993-3_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439926","9783031439933"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43993-3_51","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","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":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","order":11,"name":"conference_url","label":"Conference URL","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","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":"730","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":"32% - 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)"}}]}}