{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:10:35Z","timestamp":1760159435572,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032080080","type":"print"},{"value":"9783032080097","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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\/978-3-032-08009-7_11","type":"book-chapter","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T04:37:20Z","timestamp":1760157440000},"page":"105-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lesion-Aware Visual-Language Fusion for\u00a0Automated Image Captioning of\u00a0Ulcerative Colitis Endoscopic Examinations"],"prefix":"10.1007","author":[{"given":"Alexis Iv\u00e1n L\u00f3pez","family":"Escamilla","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gilberto","family":"Ochoa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sharib","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"11_CR1","unstructured":"Abacha, A.B., Shivade, C., Hasan, S.A., Datla, V., Liu, J.D., Demner-Fushman, D.: VQA-Med: overview of the medical visual question answering task at imageCLEF 2019. In: CEUR Workshop Proceedings (2019)"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Bhambhvani, H., Zamora, A.: Deep learning model for automated mayo endoscopic subscore classification. Europ. J. Gastroenterol. Hepat. 33(5), 645\u2013649 (2021)","DOI":"10.1097\/MEG.0000000000001952"},{"key":"11_CR3","unstructured":"Boag, W., Lou, J., Zech, J.R., Hughes, M.C., McDermott, M.B.A., Ghassemi, M.: Baselines for chest X-ray report generation. In: Proceedings of the Machine Learning for Healthcare Conference, pp. 371\u2013385 (2020)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"11_CR5","volume":"65","author":"X Chen","year":"2020","unstructured":"Chen, X., Zhang, Z., Kalpathy-Cramer, J., Xing, E.: Generating radiology reports via memory-driven transformer. Med. Image Anal. 65, 101786 (2020)","journal-title":"Med. Image Anal."},{"key":"11_CR6","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.neucom.2019.10.053","volume":"378","author":"X Huang","year":"2020","unstructured":"Huang, X., Wang, R., Xu, L., Gao, Z.: Biomedical image captioning with multi-level attention. Neurocomputing 378, 303\u2013312 (2020)","journal-title":"Neurocomputing"},{"key":"11_CR7","unstructured":"Jiang, X.E.A.: Deep learning-based endoscopic assessment of ulcerative colitis severity. J. Gastroenterol. 16, 17562848231215579 (2022)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Jing, B., Xie, P., Xing, E.: Show, describe and conclude: on exploiting the structure information of chest X-ray reports. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)","DOI":"10.18653\/v1\/P19-1657"},{"key":"11_CR9","volume":"73","author":"X Li","year":"2022","unstructured":"Li, X., Zhang, Z., Huang, X., Zhao, Q., Metaxas, D.N.: Medical visual question answering via modular co-attention learning. Med. Image Anal. 73, 102196 (2022)","journal-title":"Med. Image Anal."},{"key":"11_CR10","unstructured":"Liu, F., Jin, D., Liu, T., Yu, H.: Clinically accurate chest X-ray report generation. arXiv preprint arXiv:1904.02633 (2019)"},{"key":"11_CR11","unstructured":"Lo, C.E.A.: Automatic grading of ulcerative colitis from endoscopic images using efficientnet. Med. Image Anal. (2022)"},{"issue":"140","key":"11_CR12","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Shin, H.C., Roberts, K., Lu, L., Demner-Fushman, D., Yao, J., Summers, R.M.: Learning to read chest X-rays: recurrent neural cascade model for automated image annotation (2016)","DOI":"10.1109\/CVPR.2016.274"},{"key":"11_CR15","unstructured":"Valencia, H.E.A.: Lesion-aware image captioning and MES prediction in ulcerative colitis. In: Proceedings of the MICCAI (2023)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"11_CR17","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning (ICML) (2015)"},{"key":"11_CR18","unstructured":"Yuan, Y., Chen, X., Wang, J.: HRFormer: high-resolution vision transformer for dense predictive tasks. Adv. Neural Info. Process. Syst. 35 (2022)"},{"key":"11_CR19","unstructured":"Zhang, Z., Liu, T., Chen, Y.: Hierarchical medical image understanding through multi-scale and multi-modal transformer networks. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI) (2021)"}],"container-title":["Lecture Notes in Computer Science","Data Engineering in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-08009-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T04:37:26Z","timestamp":1760157446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-08009-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"ISBN":["9783032080080","9783032080097"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-08009-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"12 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DEMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"MICCAI Workshop on Data Engineering 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":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"demi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}