{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:20:16Z","timestamp":1767320416614,"version":"3.48.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032095121","type":"print"},{"value":"9783032095138","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\/978-3-032-09513-8_36","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:17:01Z","timestamp":1767320221000},"page":"369-378","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Medical Referring Image Segmentation: Addressing Multi-Lesion Reference and\u00a0Annotation Uncertainty via\u00a0Vision-Language Fusion"],"prefix":"10.1007","author":[{"given":"Yuanyang","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3025-8964","authenticated-orcid":false,"given":"Chun-Mei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0873-619X","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1068-7868","authenticated-orcid":false,"given":"Lionel","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anh","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gideon","family":"Ooi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3687-1265","authenticated-orcid":false,"given":"Choon","family":"Thng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1590-2029","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1468-6758","authenticated-orcid":false,"given":"Juergen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1271\u20131280 (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16321\u201316330 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Lavt: language-aware vision transformer for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vlt: vision-language transformer and query generation for referring segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Shi, H., Li, H., Meng, F., Wu, Q.: Key-word-aware network for referring expression image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 38\u201354 (2018)","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10502\u201310511 (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D. J., Jia, S., Lo, Y. C., Chen, H. T., Liu, T. L.: See-through-text grouping for referring image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7454\u20137463 (2019)","DOI":"10.1109\/ICCV.2019.00755"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Wang, Z., Lu, Y., Li, Q., Tao, X., Guo, Y., Gong, M., Liu, T.: Cris: clip-driven referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"36_CR9","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"issue":"1","key":"36_CR10","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1162\/neco.1992.4.1.131","volume":"4","author":"J Schmidhuber","year":"1992","unstructured":"Schmidhuber, J.: Learning to control fast-weight memories: an alternative to dynamic recurrent networks. Neural Comput. 4(1), 131\u2013139 (1992)","journal-title":"Neural Comput."},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Lvit: language meets vision transformer in medical image segmentation. IEEE Trans. Med. Imaging (2023)","DOI":"10.1109\/TMI.2023.3291719"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Xu, M., Liang, K., Chen, K., Wu, M.: Ariadne\u2019s thread: Using text prompts to improve segmentation of infected areas from chest x-ray images. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 724\u2013733. Springer (2024)","DOI":"10.1007\/978-3-031-43901-8_69"},{"key":"36_CR13","unstructured":"Ouyang, S., et al.: Lsms: Language-guided scale-aware medsegmentor for medical image referring segmentation. arXiv preprint arXiv:2408.17347 (2024)"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Guo, Y., et al.: Common vision-language attention for text-guided medical image segmentation of pneumonia. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 192\u2013201. Springer (2024)","DOI":"10.1007\/978-3-031-72114-4_19"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Causalclipseg: unlocking clip\u2019s potential in referring medical image segmentation with causal intervention. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 77\u201387. Springer (2024)","DOI":"10.1007\/978-3-031-72384-1_8"},{"key":"36_CR16","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.media.2016.04.007","volume":"32","author":"D-Y Liu","year":"2016","unstructured":"Liu, D.-Y., et al.: Identification of lesion images from gastrointestinal endoscope based on feature extraction of combinational methods with and without learning process. Med. Image Anal. 32, 281\u2013294 (2016)","journal-title":"Med. Image Anal."},{"key":"36_CR17","first-page":"20331","volume":"33","author":"S Liu","year":"2020","unstructured":"Liu, S., Niles-Weed, J., Razavian, N., Fernandez-Granda, C.: Early-learning regularization prevents memorization of noisy labels. Adv. Neural. Inf. Process. Syst. 33, 20331\u201320342 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: Generalized referring expression segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"36_CR20","unstructured":"Johnson, A., Pollard, T., Mark, R.: MIMIC-III Clinical Database (version 1.4) (2016)"},{"issue":"10","key":"36_CR21","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1038\/s42256-022-00536-x","volume":"4","author":"A Saporta","year":"2022","unstructured":"Saporta, A., et al.: Benchmarking saliency methods for chest x-ray interpretation. Nat. Mach. Intell. 4(10), 867\u2013878 (2022)","journal-title":"Nat. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Machine Learning in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09513-8_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:17:04Z","timestamp":1767320224000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09513-8_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032095121","9783032095138"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09513-8_36","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":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MLMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Machine Learning in Medical Imaging","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":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mlmi-med2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/mlmi2025\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}