{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T07:01:15Z","timestamp":1771743675387,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049704","type":"print"},{"value":"9783032049711","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-04971-1_46","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:10:04Z","timestamp":1758301804000},"page":"487-497","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PedCLIP: A Vision-Language Model for\u00a0Pediatric X-Rays with\u00a0Mixture of\u00a0Body Part Experts"],"prefix":"10.1007","author":[{"given":"Ta Duc","family":"Huy","sequence":"first","affiliation":[]},{"given":"Abin","family":"Shoby","sequence":"additional","affiliation":[]},{"given":"Sen","family":"Tran","sequence":"additional","affiliation":[]},{"given":"Yutong","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Phi Le","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Akshay","family":"Gole","sequence":"additional","affiliation":[]},{"given":"Lingqiao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Antonios","family":"Perperidis","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Friswell","sequence":"additional","affiliation":[]},{"given":"Rebecca","family":"Linke","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Glynn","sequence":"additional","affiliation":[]},{"given":"Minh-Son","family":"To","sequence":"additional","affiliation":[]},{"given":"Anton","family":"van\u00a0den Hengel","sequence":"additional","affiliation":[]},{"given":"Johan","family":"Verjans","sequence":"additional","affiliation":[]},{"given":"Zhibin","family":"Liao","sequence":"additional","affiliation":[]},{"given":"Minh Hieu","family":"Phan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"46_CR1","unstructured":"Alsentzer, E., et al.: Publicly available clinical bert embeddings. arXiv preprint arXiv:1904.03323 (2019)"},{"key":"46_CR2","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":"46_CR3","unstructured":"Chopra, S., Mao, L., Sanchez-Rodriguez, G., Feola, A.J., Li, J., Kira, Z.: Medmoe: modality-specialized mixture of experts for medical vision-language understanding. arXiv preprint arXiv:2506.08356 (2025)"},{"key":"46_CR4","unstructured":"Dubey, A., Jauhri, A., Pandey, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"issue":"2","key":"46_CR5","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1148\/radiol.2018180736","volume":"290","author":"SS Halabi","year":"2019","unstructured":"Halabi, S.S., Prevedello, L.M., Kalpathy-Cramer, J., et al.: The rsna pediatric bone age machine learning challenge. Radiology 290(2), 498\u2013503 (2019)","journal-title":"Radiology"},{"key":"46_CR6","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":"46_CR7","doi-asserted-by":"crossref","unstructured":"Huy, T.D., Huyen, H.C., Nguyen, C.D., et\u00a0al.: Adversarial contrastive fourier domain adaptation for polyp segmentation. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pp.\u00a01\u20135. IEEE (2022)","DOI":"10.1109\/ISBI52829.2022.9761671"},{"key":"46_CR8","unstructured":"Huy, T.D., et\u00a0al.: Seeing the trees for the forest: rethinking weakly-supervised medical visual grounding. arXiv preprint arXiv:2505.15123 (2025)"},{"key":"46_CR9","doi-asserted-by":"crossref","unstructured":"Huy, T.D., et al.: Interactive medical image analysis with concept-based similarity reasoning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 30797\u201330806 (2025)","DOI":"10.1109\/CVPR52734.2025.02868"},{"key":"46_CR10","first-page":"69625","volume":"36","author":"Y Jain","year":"2023","unstructured":"Jain, Y., Behl, H., Kira, Z., Vineet, V.: Damex: dataset-aware mixture-of-experts for visual understanding of mixture-of-datasets. Adv. Neural. Inf. Process. Syst. 36, 69625\u201369637 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"46_CR11","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":"46_CR12","unstructured":"Khattak, M.U., Kunhimon, S., Naseer, M., Khan, S., Khan, F.S.: Unimed-clip: towards a unified image-text pretraining paradigm for diverse medical imaging modalities. arXiv preprint arXiv:2412.10372 (2024)"},{"key":"46_CR13","doi-asserted-by":"crossref","unstructured":"Lai, H., et al.: Carzero: cross-attention alignment for radiology zero-shot classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11137\u201311146 (2024)","DOI":"10.1109\/CVPR52733.2024.01059"},{"key":"46_CR14","unstructured":"Li, D., Nguyen, H., Zhang, H.R.: Identification of negative transfers in multitask learning using surrogate models. Trans. Mach. Learn. Res. (2023)"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Liu, S., Liang, Y., Gitter, A.: Loss-balanced task weighting to reduce negative transfer in multi-task learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 9977\u20139978 (2019)","DOI":"10.1609\/aaai.v33i01.33019977"},{"issue":"1","key":"46_CR16","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1038\/s41597-022-01328-z","volume":"9","author":"E Nagy","year":"2022","unstructured":"Nagy, E., Janisch, M., Hr\u017ei\u0107, F., Sorantin, E., Tschauner, S.: A pediatric wrist trauma x-ray dataset (grazpedwri-dx) for machine learning. Sci. Data 9(1), 222 (2022)","journal-title":"Sci. Data"},{"key":"46_CR17","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"issue":"1","key":"46_CR18","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1038\/s41597-023-02102-5","volume":"10","author":"HH Pham","year":"2023","unstructured":"Pham, H.H., Nguyen, N.H., Tran, T.T., Nguyen, T.N., Nguyen, H.Q.: Pedicxr: an open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children. Sci. Data 10(1), 240 (2023)","journal-title":"Sci. Data"},{"key":"46_CR19","doi-asserted-by":"crossref","unstructured":"Phan, V.M.H., et al.: Decomposing disease descriptions for enhanced pathology detection: a multi-aspect vision-language pre-training framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11492\u201311501 (2024)","DOI":"10.1109\/CVPR52733.2024.01092"},{"key":"46_CR20","doi-asserted-by":"crossref","unstructured":"Quan, T.M., Thanh, H.M., et\u00a0al.: Xpgan: X-ray projected generative adversarial network for improving covid-19 image classification. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1509\u20131513. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434159"},{"key":"46_CR21","unstructured":"Rajpurkar, P., Irvin, J., Zhu, K., et\u00a0al.: Chexnet: radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017)"},{"key":"46_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"12","key":"46_CR23","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","volume":"6","author":"E Tiu","year":"2022","unstructured":"Tiu, E., Talius, E., Patel, P., Langlotz, C.P., Ng, A.Y., Rajpurkar, P.: Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning. Nat. Biomed. Eng. 6(12), 1399\u20131406 (2022)","journal-title":"Nat. Biomed. Eng."},{"key":"46_CR24","unstructured":"U.S. Food and Drug Administration: Pediatric x-ray imaging (2025). https:\/\/www.fda.gov\/radiation-emitting-products\/medical-imaging\/pediatric-x-ray-imaging. Accessed 12 Feb 2025"},{"key":"46_CR25","unstructured":"Wang, F., Zhou, Y., Wang, S., Vardhanabhuti, V., Yu, L.: Multi-granularity cross-modal alignment for generalized medical visual representation learning (supplementary material). In: Advances in Neural Information Processing Systems (2022)"},{"key":"46_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: Medclip: contrastive learning from unpaired medical images and text. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing, vol.\u00a02022, p.\u00a03876 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"46_CR27","unstructured":"Zhang, S., Xu, Y., Usuyama, N., et\u00a0al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"46_CR28","doi-asserted-by":"publisher","first-page":"1351965","DOI":"10.3389\/fcvm.2024.1351965","volume":"11","author":"L Zhixin","year":"2024","unstructured":"Zhixin, L., Gang, L., Zhixian, J., Sibao, W., Silin, P.: Chd-cxr: a de-identified publicly available dataset of chest x-ray for congenital heart disease. Front. Cardiovasc. Med. 11, 1351965 (2024)","journal-title":"Front. Cardiovasc. Med."}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04971-1_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T06:46:25Z","timestamp":1771742785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04971-1_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049704","9783032049711"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04971-1_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare\u00a0that 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":"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":"23 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":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}