{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:56:41Z","timestamp":1771955801278,"version":"3.50.1"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031721106","type":"print"},{"value":"9783031721113","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72111-3_23","type":"book-chapter","created":{"date-parts":[[2024,10,5]],"date-time":"2024-10-05T21:01:34Z","timestamp":1728162094000},"page":"242-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enabling Text-Free Inference in\u00a0Language-Guided Segmentation of\u00a0Chest X-Rays via\u00a0Self-guidance"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1935-1953","authenticated-orcid":false,"given":"Shuchang","family":"Ye","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9562-1613","authenticated-orcid":false,"given":"Mingyuan","family":"Meng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5591-5385","authenticated-orcid":false,"given":"Mingjian","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3381-214X","authenticated-orcid":false,"given":"Dagan","family":"Feng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5960-1060","authenticated-orcid":false,"given":"Jinman","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,6]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15(1), 654 (2024). Nature Publishing Group UK London","DOI":"10.1038\/s41467-024-44824-z"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Sharma, N.N., Saba, L., Khanna, N.N., Kalra, M.K., Fouda, M.M., Suri, J.S.: Segmentation-based classification deep learning model embedded with explainable AI for COVID-19 detection in chest X-ray scans. Diagnostics 12(9), 2132 (2022)","DOI":"10.3390\/diagnostics12092132"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Mahmood, T., Rehman, A., Saba, T., Nadeem, L., Bahaj, S.A.O.: Recent advancements and future prospects in active deep learning for medical image segmentation and classification. IEEE Access 11, 113623\u2013113652 (2023). IEEE","DOI":"10.1109\/ACCESS.2023.3313977"},{"key":"23_CR4","doi-asserted-by":"publisher","unstructured":"Asgari Taghanaki, S., Abhishek, K., Cohen, J.P., Cohen-Adad, J., Hamarneh, G.: Deep semantic segmentation of natural and medical images: a review. Artif. Intell. Rev. 54(1), 137\u2013178 (2020). https:\/\/doi.org\/10.1007\/s10462-020-09854-1","DOI":"10.1007\/s10462-020-09854-1"},{"key":"23_CR5","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Siddique, N., Paheding, S., Elkin, C.P., Devabhaktuni, V.: U-Net and its variants for medical image segmentation: a review of theory and applications. IEEE Access 9, 82031\u201382057 (2021). IEEE","DOI":"10.1109\/ACCESS.2021.3086020"},{"key":"23_CR7","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., Liang, J.: UNet++: a nested U-Net architecture for medical image segmentation. In: Stoyanov, D., et al. (eds.) DLMIA\/ML-CDS -2018. LNCS, vol. 11045, pp. 3\u201311. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00889-5_1","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"23_CR8","unstructured":"Oktay, O., et al.: Attention U-Net: Learning where to look for the pancreas (2018). arXiv preprint arXiv:1804.03999"},{"key":"23_CR9","unstructured":"Chen, J., et al.: TransUNet: Transformers make strong encoders for medical image segmentation (2021). arXiv preprint arXiv:2102.04306"},{"key":"23_CR10","doi-asserted-by":"publisher","unstructured":"Cao, H., et al.: Swin-Unet: Unet-like pure transformer for medical image segmentation. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. LNCS, vol. 13803. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"23_CR11","first-page":"10944","volume":"34","author":"Y Huang","year":"2021","unstructured":"Huang, Y., Du, C., Xue, Z., Chen, X., Zhao, H., Huang, L.: What makes multi-modal learning better than single (provably). Adv. Neural Inf. Process. Syst. 34, 10944\u201310956 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Gan, Z., Li, L., Li, C., Wang, L., Liu, Z., Gao, J., et al.: Vision-language pre-training: basics, recent advances, and future trends. Found. Trends\u00ae Comput. Graph. Vis. 14(3\u20134), 163\u2013352 (2022). Now Publishers, Inc","DOI":"10.1561\/0600000105"},{"key":"23_CR13","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021). PMLR"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: LViT: language meets vision transformer in medical image segmentation. IEEE Trans. Med. Imaging 43(1), 96\u2013107 (2023). IEEE","DOI":"10.1109\/TMI.2023.3291719"},{"key":"23_CR15","doi-asserted-by":"publisher","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: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention - MICCAI 2023. MICCAI 2023. LNCS, vol. 14223, pp. 724\u2013733. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43901-8_69","DOI":"10.1007\/978-3-031-43901-8_69"},{"key":"23_CR16","doi-asserted-by":"publisher","unstructured":"Degerli, A., Kiranyaz, S., Chowdhury, M.E.H., Gabbouj, M.: Osegnet: operational segmentation network for COVID-19 detection using chest X-ray images. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 2306\u20132310 (2022). https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897412","DOI":"10.1109\/ICIP46576.2022.9897412"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"23_CR18","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding (2018). arXiv preprint arXiv:1810.04805"},{"key":"23_CR19","unstructured":"Boecking, B., et al.: Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing (2022). arXiv preprint arXiv:2204.09817. https:\/\/arxiv.org\/abs\/2204.09817"},{"key":"23_CR20","doi-asserted-by":"publisher","unstructured":"Campello, R.J.G.B., Moulavi, D., Sander, J.: Density-based clustering based on hierarchical density estimates. In: Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (eds.) PAKDD 2013. LNCS (LNAI), vol. 7819, pp. 160\u2013172. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37456-2_14","DOI":"10.1007\/978-3-642-37456-2_14"},{"key":"23_CR21","unstructured":"Lv, W., et al.: DETRs Beat YOLOs on Real-time Object Detection (2023). arXiv preprint arXiv:2304.08069"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR23","doi-asserted-by":"publisher","unstructured":"Bertels, J., et al.: Optimizing the dice score and Jaccard index for medical image segmentation: theory and practice. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 92\u2013100. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32245-8_11","DOI":"10.1007\/978-3-030-32245-8_11"},{"key":"23_CR24","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"23_CR25","unstructured":"Falcon, W.A.: PyTorch lightning. GitHub, vol. 3 (2019)"},{"key":"23_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017). arXiv preprint arXiv:1711.05101"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72111-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,5]],"date-time":"2024-10-05T21:03:48Z","timestamp":1728162228000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72111-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031721106","9783031721113"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72111-3_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"6 October 2024","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":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}