{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T18:04:17Z","timestamp":1771005857437,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032176103","type":"print"},{"value":"9783032176110","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-17611-0_1","type":"book-chapter","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T17:13:15Z","timestamp":1771002795000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Distribution-Based Masked Medical Vision-Language Model Using Structured Reports"],"prefix":"10.1007","author":[{"given":"Shreyank N.","family":"Gowda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruichi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,14]]},"reference":[{"key":"1_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"1_CR2","unstructured":"Alsentzer, E., et al.: Publicly available clinical bert embeddings. arXiv preprint arXiv:1904.03323 (2019)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Boecking, B., et\u00a0al.: Making the most of text semantics to improve biomedical vision\u2013language processing. In: European Conference on Computer Vision, pp. 1\u201321. Springer (2022)","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"1_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-030-59713-9_51","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"G Chauhan","year":"2020","unstructured":"Chauhan, G., et al.: Joint modeling of chest radiographs and radiology reports for pulmonary edema assessment. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 529\u2013539. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59713-9_51"},{"key":"1_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, P., Lin, L., Lyu, J., Huang, Y., Luo, W., Tang, X.: Prior: prototype representation joint learning from medical images and reports. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21361\u201321371 (2023)","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Clifton, D.A.: Masks and manuscripts: advancing medical pre-training with end-to-end masking and narrative structuring. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 426\u2013436. Springer (2024)","DOI":"10.1007\/978-3-031-72120-5_40"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Unified medical image pre-training in language-guided common semantic space. In: European Conference on Computer Vision, pp. 123\u2013139. Springer (2025)","DOI":"10.1007\/978-3-031-73004-7_8"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Shen, L., Lungren, M.P., Yeung, S.: 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, pp. 3942\u20133951 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Irvin, J., et\u00a0al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence,vol.\u00a033, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"1_CR17","unstructured":"Kwon, G., Cai, Z., Ravichandran, A., Bas, E., Bhotika, R., Soatto, S.: Masked vision and language modeling for multi-modal representation learning. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Mlip: enhancing medical visual representation with divergence encoder and knowledge-guided contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11704\u201311714 (2024)","DOI":"10.1109\/CVPR52733.2024.01112"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Liu, C., Cheng, S., Shi, M., Shah, A., Bai, W., Arcucci, R.: Imitate: clinical prior guided hierarchical vision-language pre-training. IEEE Trans. Med. Imaging (2024)","DOI":"10.1109\/TMI.2024.3449690"},{"key":"1_CR20","unstructured":"for imaging informatics\u00a0in medicine, S.: Siim-acr pneumothorax segmentation (2019). https:\/\/www.kaggle.com\/ c\/siim-acr-pneumothorax-segmentation"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Kaissis, G., Zou, C., Rueckert, D.: Joint learning of localized representations from medical images and reports. In: European Conference on Computer Vision, pp. 685\u2013701. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"1_CR22","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"1_CR23","doi-asserted-by":"publisher","first-page":"861680","DOI":"10.3389\/fmed.2022.861680","volume":"9","author":"M Pavlova","year":"2022","unstructured":"Pavlova, M., et al.: Covid-net cxr-2: an enhanced deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Front. Med. 9, 861680 (2022)","journal-title":"Front. Med."},{"key":"1_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":"1_CR25","doi-asserted-by":"crossref","unstructured":"Shih, G., et\u00a0al.: Augmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia. Radiol. Artif. Intell. 1(1), e180041 (2019)","DOI":"10.1148\/ryai.2019180041"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097\u20132106 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"1_CR27","doi-asserted-by":"publisher","first-page":"103145","DOI":"10.1016\/j.jvcir.2021.103145","volume":"78","author":"Y Wen","year":"2021","unstructured":"Wen, Y., Chen, L., Deng, Y., Zhou, C.: Rethinking pre-training on medical imaging. J. Vis. Commun. Image Represent. 78, 103145 (2021)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Medklip: medical knowledge enhanced language-image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1101\/2023.01.10.23284412"},{"key":"1_CR29","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive learning of medical visual representations from paired images and text. In: Machine Learning for Healthcare Conference, pp. 2\u201325. PMLR (2022)"}],"container-title":["Lecture Notes in Computer Science","Interpretability of Machine Intelligence in Medical Image Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-17611-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T17:13:26Z","timestamp":1771002806000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-17611-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032176103","9783032176110"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-17611-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"iMIMIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Interpretability of Machine Intelligence in Medical Image Computing","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":"27 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":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"imimic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/imimic-workshop.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}