{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:48:12Z","timestamp":1767084492890,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032049834"},{"type":"electronic","value":"9783032049841"}],"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\/978-3-032-04984-1_43","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T16:25:22Z","timestamp":1758299122000},"page":"447-456","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Robust Multimodal Learning for\u00a0Ophthalmic Disease Grading via\u00a0Disentangled Representation"],"prefix":"10.1007","author":[{"given":"Xinkun","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yifang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Senwei","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Feilong","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Chengzhi","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Junjun","family":"He","sequence":"additional","affiliation":[]},{"given":"Zongyuan","family":"Ge","sequence":"additional","affiliation":[]},{"given":"Imran","family":"Razzak","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Berlinet, A., Thomas, C.: Reproducing Kernel Hilbert Spaces in Probability and Statistics. Kluwer Academic Publishers (2004)","DOI":"10.1007\/978-1-4419-9096-9"},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Chen, R.J., et al.: Multimodal co-attention transformer for survival prediction in gigapixel whole slide images. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00398"},{"key":"43_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, https:\/\/arxiv.org\/abs\/2010.11929 (2020)"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et al.: Unetr: transformers for 3d medical image segmentation. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"issue":"8","key":"43_CR5","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"GE Hinton","year":"2002","unstructured":"Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771\u20131800 (2002)","journal-title":"Neural Comput."},{"key":"43_CR6","unstructured":"Hosseini, M.S., et\u00a0al.: Computational pathology: a survey review and the way forward. arXiv preprint arXiv:2304.05482, https:\/\/arxiv.org\/abs\/2304.05482 (2023)"},{"issue":"5035","key":"43_CR7","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1126\/science.1957169","volume":"254","author":"D Huang","year":"1991","unstructured":"Huang, D., et al.: Optical coherence tomography. Science 254(5035), 1178\u20131181 (1991)","journal-title":"Science"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Lam, C., et\u00a0al.: Performance of artificial intelligence in detecting diabetic macular edema from fundus photography and optical coherence tomography images: a systematic review and meta-analysis. Diabetes Care (2024)","DOI":"10.2337\/figshare.24518287.v1"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: A unified self-distillation framework for multimodal sentiment analysis with uncertain missing modalities. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i9.28871"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: Incomplete modality disentangled representation for ophthalmic disease grading and diagnosis. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i5.32570"},{"key":"43_CR11","unstructured":"Luo, Y., Tian, Y., Shi, M., Elze, T., Wang, M.: Eye fairness: a large-scale 3d imaging dataset for equitable eye diseases screening and fair identity scaling (2024), https:\/\/openreview.net\/forum?id=Lv9KZ5qCSG"},{"key":"43_CR12","unstructured":"der Maaten, L.V., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008), http:\/\/jmlr.org\/papers\/volume9\/VDMaaten08a\/VDMaaten08a.pdf"},{"key":"43_CR13","doi-asserted-by":"publisher","unstructured":"Meleppat, R., et al.: In vivo multimodal retinal imaging of disease-related pigmentary changes in retinal pigment epithelium. Sci. Rep. 11(1), 16252 (2021). https:\/\/doi.org\/10.1038\/s41598-021-95756-3","DOI":"10.1038\/s41598-021-95756-3"},{"key":"43_CR14","doi-asserted-by":"publisher","unstructured":"Mleppat, R., et al.: Directional optical coherence tomography reveals melanin concentration dependent scattering properties of retinal pigment epithelium. J. Biomed. Opt. 24(6), 066011 (2019). https:\/\/doi.org\/10.1117\/1.JBO.24.6.066011","DOI":"10.1117\/1.JBO.24.6.066011"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Wolf, S., Dolz-Marco, R., Tafreshi, A., Schmitz-Valckenberg, S., Holz, F.: Ophthalmic diagnostic imaging: retina, pp. 87\u2013106. Springer (2019)","DOI":"10.1007\/978-3-030-16638-0_4"},{"key":"43_CR16","unstructured":"Okutmustur, B.: Reproducing kernel hilbert spaces. Master\u2019s thesis, Bilkent University, August 2005, http:\/\/www.thesis.bilkent.edu.tr\/0002953.pdf"},{"key":"43_CR17","unstructured":"Rippel, O., Paluri, M., Dollar, P., Bourdev, L.: Metric learning with adaptive density discrimination. arXiv preprint arXiv:1511.05939 (2015)"},{"key":"43_CR18","unstructured":"Tang, F., Huang, Z., Liu, C., Sun, Q., Yang, H., Lim, S.N.: Intervening anchor token: decoding strategy in alleviating hallucinations for mllms. In: ICLR (2025)"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Tang, F., et al.: Seeing far and clearly: mitigating hallucinations in mllms with attention causal decoding. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02435"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Tang, F., Xu, Z., Qu, Z., Feng, W., Jiang, X., Ge, Z.: Hunting attributes: Context prototype-aware learning for weakly supervised semantic segmentation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00320"},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Udandarao, V., Gupta, A., Albanie, S.: Sus-x: Training-free name-only transfer of vision-language models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"43_CR22","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Learnable cross-modal knowledge distillation for multi-modal learning with missing modality. In: MICCAI (2023)","DOI":"10.1007\/978-3-031-43901-8_21"},{"key":"43_CR23","unstructured":"Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: International Conference on Machine Learning, pp. 9929\u20139939. PMLR (2020)"},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y., Albrecht, C.M., Braham, N.A.A., Liu, C., Xiong, Z., Zhu, X.X.: Decoupling common and unique representations for multimodal self-supervised learning. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73397-0_17"},{"issue":"5","key":"43_CR25","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.3390\/diagnostics12051100","volume":"12","author":"T Watanabe","year":"2022","unstructured":"Watanabe, T., et al.: Combining optical coherence tomography and fundus photography to improve glaucoma screening. Diagnostics 12(5), 1100 (2022)","journal-title":"Diagnostics"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: convolutional block attention module. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"43_CR27","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Yuan, Y., Wang, Q.: Ask: adaptively selecting key local features for rgb-d scene recognition. In: TIP (2021)","DOI":"10.1109\/TIP.2021.3053459"},{"key":"43_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Y., Chen, H.: Multimodal optimal transport-based co-attention transformer with global structure consistency for survival prediction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01942"},{"key":"43_CR29","doi-asserted-by":"crossref","unstructured":"Xue, H., et al.: Mmrc: a large-scale benchmark for understanding multimodal large language model in real-world conversation (2025)","DOI":"10.18653\/v1\/2025.acl-long.1096"},{"key":"43_CR30","doi-asserted-by":"publisher","first-page":"107307","DOI":"10.1016\/j.cmpb.2022.107307","volume":"229","author":"J Zheng","year":"2023","unstructured":"Zheng, J., Liu, H., Feng, Y., Xu, J., Zhao, L.: Casf-net: cross-attention and cross-scale fusion network for medical image segmentation. Comput. Methods Programs Biomed. 229, 107307 (2023)","journal-title":"Comput. Methods Programs Biomed."},{"key":"43_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103214","author":"K Zou","year":"2024","unstructured":"Zou, K., Lin, T., Han, Z., Wang, M., Yuan, X., Chen, H., Zhang, C., Shen, X., Fu, H.: Confidence-aware multi-modality learning for eye disease screening. MIA (2024). https:\/\/doi.org\/10.1016\/j.media.2024.103214","journal-title":"MIA"}],"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\/978-3-032-04984-1_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T16:25:31Z","timestamp":1758299131000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04984-1_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049834","9783032049841"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04984-1_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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 declare that they have no competing interests.","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"}}]}}