{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:16:24Z","timestamp":1783055784752,"version":"3.54.6"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100000836","name":"University of Liverpool","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000836","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976239"],"award-info":[{"award-number":["61976239"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004052","name":"King Abdullah University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000737","name":"University of Exeter","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000737","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.inffus.2026.104502","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T07:02:27Z","timestamp":1780038147000},"page":"104502","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Knowledge-enhanced explicitly disentangled representation with missing modality for medical image diagnosis"],"prefix":"10.1016","volume":"136","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4002-2311","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyuan","family":"Diao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6526-0928","authenticated-orcid":false,"given":"Qinkai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feixiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaorou","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7873-0922","authenticated-orcid":false,"given":"Yalin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanda","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0153-850X","authenticated-orcid":false,"given":"Shoubin","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104502_bib0001","article-title":"A review of deep learning-based information fusion techniques for multimodal medical image classification","author":"Li","year":"2024","journal-title":"Comput. Biol. Med."},{"issue":"5","key":"10.1016\/j.inffus.2026.104502_bib0002","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.3390\/diagnostics12051100","article-title":"Combining optical coherence tomography and fundus photography to improve glaucoma screening","volume":"12","author":"Watanabe","year":"2022","journal-title":"Diagnostics"},{"key":"10.1016\/j.inffus.2026.104502_bib0003","unstructured":"R. Wu, H. Wang, H.-T. Chen, G. Carneiro, Deep multimodal learning with missing modality: a survey, arXiv preprint arXiv:2409.07825(2024)."},{"issue":"7","key":"10.1016\/j.inffus.2026.104502_bib0004","doi-asserted-by":"crossref","first-page":"2587","DOI":"10.1109\/TMI.2024.3368664","article-title":"Multi-modal modality-masked diffusion network for brain mri synthesis with random modality missing","volume":"43","author":"Meng","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.inffus.2026.104502_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127367","article-title":"A missing multimodal imputation diffusion model for 2D X-ray and 3D CT in COVID-19 diagnosis","volume":"279","author":"Gao","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.inffus.2026.104502_bib0006","unstructured":"S.J. Wetzel, S. Ha, R. Iten, M. Klopotek, Z. Liu, Interpretable machine learning in physics: a review, arXiv preprint arXiv:2503.23616(2025)."},{"key":"10.1016\/j.inffus.2026.104502_bib0007","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15878","article-title":"Multi-modal learning with missing modality via shared-specific feature modelling","author":"Wang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104502_bib0008","series-title":"European Conference on Computer Vision","first-page":"38","article-title":"Robust multimodal learning via representation decoupling","author":"Wei","year":"2024"},{"key":"10.1016\/j.inffus.2026.104502_bib0009","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"16416","article-title":"DRFuse: learning disentangled representation for clinical multi-modal fusion with missing modality and modal inconsistency","volume":"38","author":"Yao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104502_bib0010","series-title":"International Conference on Machine Learning","first-page":"41753","article-title":"Provable dynamic fusion for low-quality multimodal data","author":"Zhang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104502_bib0011","article-title":"Deep equilibrium models","volume":"32","author":"Bai","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104502_bib0012","first-page":"1","article-title":"Concept-aware adaptive multimodal fusion with knowledge distillation for medical image diagnosis","author":"Li","year":"2026","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.inffus.2026.104502_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2787","article-title":"Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval","author":"Jiang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104502_bib0014","series-title":"European Conference on Computer Vision","first-page":"256","article-title":"DriveLM: driving with graph visual question answering","author":"Sima","year":"2024"},{"key":"10.1016\/j.inffus.2026.104502_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102307","article-title":"FusionM4Net: a multi-stage multi-modal learning algorithm for multi-label skin lesion classification","volume":"76","author":"Tang","year":"2022","journal-title":"Med. Image Anal."},{"issue":"8","key":"10.1016\/j.inffus.2026.104502_bib0016","doi-asserted-by":"crossref","first-page":"4111","DOI":"10.1109\/JBHI.2022.3171523","article-title":"Learning two-stream CNN for multi-modal age-related macular degeneration categorization","volume":"26","author":"Wang","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.inffus.2026.104502_bib0017","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.inffus.2026.104502_bib0018","article-title":"Unsupervised SAM-guided mixture-of-multimodal-experts fusion network for medical image diagnosis","author":"Li","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.inffus.2026.104502_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2022.107315","article-title":"Skin lesion classification based on two-modal images using a multi-scale fully-shared fusion network","volume":"229","author":"Yang","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"issue":"6","key":"10.1016\/j.inffus.2026.104502_bib0020","doi-asserted-by":"crossref","first-page":"3699","DOI":"10.1364\/BOE.516764","article-title":"Cross-modal attention network for retinal disease classification based on multi-modal images","volume":"15","author":"Liu","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"10.1016\/j.inffus.2026.104502_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103225","article-title":"MMGPL: multimodal medical data analysis with graph prompt learning","volume":"97","author":"Peng","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.inffus.2026.104502_bib0022","series-title":"Companion Publication of the 2020 International Conference on Multimodal Interaction","first-page":"400","article-title":"Training strategies to handle missing modalities for audio-visual expression recognition","author":"Parthasarathy","year":"2020"},{"key":"10.1016\/j.inffus.2026.104502_bib0023","unstructured":"J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F.L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al., Gpt-4 technical report, arXiv preprint arXiv:2303.08774(2023)."},{"key":"10.1016\/j.inffus.2026.104502_sbref0024","article-title":"Text descriptions are compressive and invariant representations for visual learning","author":"Feng","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.inffus.2026.104502_bib0025","unstructured":"J. Liu, T. Hu, Y. Zhang, X. Gai, Y. Feng, Z. Liu, A chatgpt aided explainable framework for zero-shot medical image diagnosis, arXiv preprint arXiv:2307.01981(2023)."},{"key":"10.1016\/j.inffus.2026.104502_bib0026","unstructured":"T. Oikarinen, S. Das, L.M. Nguyen, T.-W. Weng, Label-free concept bottleneck models, arXiv preprint arXiv:2304.06129(2023)."},{"key":"10.1016\/j.inffus.2026.104502_bib0027","unstructured":"C. Zhao, Y. Xu, F. Zhou, Y. Wang, H. Chen, LLM-driven knowledge enhancement for multimodal cancer survival prediction, arXiv preprint arXiv:2512.14594(2025)."},{"key":"10.1016\/j.inffus.2026.104502_bib0028","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"15590","article-title":"Focus: knowledge-enhanced adaptive visual compression for few-shot whole slide image classification","author":"Guo","year":"2025"},{"issue":"6","key":"10.1016\/j.inffus.2026.104502_bib0029","doi-asserted-by":"crossref","first-page":"2235","DOI":"10.1007\/s00371-021-02354-5","article-title":"Pairwise feature-based generative adversarial network for incomplete multi-modal Alzheimer\u2019s disease diagnosis","volume":"39","author":"Ye","year":"2023","journal-title":"Vis. Comput."},{"key":"10.1016\/j.inffus.2026.104502_bib0030","series-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"2418","article-title":"M3care: learning with missing modalities in multimodal healthcare data","author":"Zhang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104502_bib0031","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5361","article-title":"Incomplete modality disentangled representation for ophthalmic disease grading and diagnosis","volume":"39","author":"Liu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104502_bib0032","series-title":"International Conference on Medical Image Computing and Computer-assisted Intervention","first-page":"447","article-title":"Robust multimodal brain tumor segmentation via feature disentanglement and gated fusion","author":"Chen","year":"2019"},{"key":"10.1016\/j.inffus.2026.104502_bib0033","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"438","article-title":"Leveraging knowledge of modality experts for incomplete multimodal learning","author":"Xu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104502_bib0034","series-title":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"1820","article-title":"Disentangling and generating modalities for recommendation in missing modality scenarios","author":"Kim","year":"2025"},{"key":"10.1016\/j.inffus.2026.104502_bib0035","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"553","article-title":"Robust incomplete-modality alignment for ophthalmic disease grading and diagnosis via labeled optimal transport","author":"Yu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104502_bib0036","series-title":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","first-page":"557","article-title":"Synthesize missing modality based on latent space model","author":"Zhang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104502_bib0037","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"13492","article-title":"Leveraging contrastive learning and knowledge distillation for incomplete modality rumor detection","author":"Xu","year":"2023"},{"issue":"9","key":"10.1016\/j.inffus.2026.104502_bib0038","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3711860","article-title":"Multimodal cascaded framework with multimodal latent loss functions robust to missing modalities","volume":"21","author":"John","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.inffus.2026.104502_bib0039","unstructured":"H. Zhou, Y. Wei, J. Yang, Z. Zhang, Towards robust and realible multimodal fake news detection with incomplete modality, arXiv preprint arXiv:2510.05839(2025)."},{"issue":"1","key":"10.1016\/j.inffus.2026.104502_bib0040","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1137\/060659624","article-title":"The Sinkhorn\u2013Knopp algorithm: convergence and applications","volume":"30","author":"Knight","year":"2008","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"4","key":"10.1016\/j.inffus.2026.104502_bib0041","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1137\/0716047","article-title":"Some convergence properties of Broyden\u2019s method","volume":"16","author":"Gay","year":"1979","journal-title":"SIAM J. Numer. Anal."},{"key":"10.1016\/j.inffus.2026.104502_bib0042","series-title":"Proceedings of the 2nd Clinical Natural Language Processing Workshop","first-page":"72","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019"},{"key":"10.1016\/j.inffus.2026.104502_bib0043","unstructured":"S. Patel, The latent space hypothesis: toward universal medical representation learning, arXiv preprint arXiv:2506.04515(2025)."},{"key":"10.1016\/j.inffus.2026.104502_bib0044","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"5519","article-title":"HeLo: heterogeneous multi-modal fusion with label correlation for emotion distribution learning","author":"Zheng","year":"2025"},{"key":"10.1016\/j.inffus.2026.104502_bib0045","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"21241","article-title":"Multimodal optimal transport-based co-attention transformer with global structure consistency for survival prediction","author":"Xu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104502_bib0046","series-title":"Clinical Trials in Age-Related Macular Degeneration Treatment","first-page":"1","article-title":"Introduction to age-related macular degeneration","author":"Weiss","year":"2024"},{"key":"10.1016\/j.inffus.2026.104502_bib0047","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20707","article-title":"Multimodal dynamics: dynamical fusion for trustworthy multimodal classification","author":"Han","year":"2022"},{"issue":"3","key":"10.1016\/j.inffus.2026.104502_bib0048","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1109\/TAFFC.2023.3340924","article-title":"Dynamic confidence-aware multi-modal emotion recognition","volume":"15","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.inffus.2026.104502_bib0049","series-title":"Proceedings of the 41st International Conference on Machine Learning","first-page":"5608","article-title":"Predictive dynamic fusion","author":"Cao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104502_bib0050","unstructured":"J. Ni, Y. Bai, W. Zhang, T. Yao, T. Mei, Deep equilibrium multimodal fusion, arXiv preprint arXiv:2306.16645(2023)."},{"key":"10.1016\/j.inffus.2026.104502_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103138","article-title":"ADFusion: multi-modal adaptive deep fusion for cancer subtype prediction","volume":"121","author":"Zhang","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104502_bib0052","unstructured":"Y. Luo, M.O. Khan, Y. Tian, M. Shi, Z. Dou, T. Elze, Y. Fang, M. Wang, Fairvision: equitable deep learning for eye disease screening via fair identity scaling, arXiv preprint arXiv:2310.02492(2023)."},{"issue":"2","key":"10.1016\/j.inffus.2026.104502_bib0053","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1109\/JBHI.2018.2824327","article-title":"Seven-point checklist and skin lesion classification using multitask multimodal neural nets","volume":"23","author":"Kawahara","year":"2018","journal-title":"IEEE J. Biomed. Health Inf."},{"issue":"7981","key":"10.1016\/j.inffus.2026.104502_bib0054","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.inffus.2026.104502_bib0055","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14943","article-title":"Multimodal prompting with missing modalities for visual recognition","author":"Lee","year":"2023"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003817?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003817?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:22:52Z","timestamp":1783052572000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":55,"alternative-id":["S1566253526003817"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104502","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Knowledge-enhanced explicitly disentangled representation with missing modality for medical image diagnosis","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104502","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104502"}}