{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T17:19:52Z","timestamp":1787851192875,"version":"build-2784847793"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2021ZD0200800"],"award-info":[{"award-number":["2021ZD0200800"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0200800"],"award-info":[{"award-number":["2021ZD0200800"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neucom.2026.133946","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:08:33Z","timestamp":1778756913000},"page":"133946","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multimodal medical image segmentation paradigm based on language-assisted transformer"],"prefix":"10.1016","volume":"694","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4339-804X","authenticated-orcid":false,"given":"Longxuan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4868-1484","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7333-6822","authenticated-orcid":false,"given":"Changyu","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9526-2737","authenticated-orcid":false,"given":"Ence","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133946_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2023.105605","article-title":"HTC-net: a hybrid CNN-transformer framework for medical image segmentation","volume":"88","author":"Tang","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"issue":"4","key":"10.1016\/j.neucom.2026.133946_bib0010","doi-asserted-by":"crossref","first-page":"3162","DOI":"10.1109\/TETCI.2025.3547635","article-title":"PCDAL: a perturbation consistency-driven active learning approach for medical image segmentation and classification","volume":"9","author":"Wang","year":"2025","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.neucom.2026.133946_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126970","article-title":"A multi-attention and depthwise separable convolution network for medical image segmentation","volume":"564","author":"Zhou","year":"2024","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.neucom.2026.133946_bib0020","doi-asserted-by":"crossref","first-page":"9924","DOI":"10.1038\/s41598-025-94437-9","article-title":"A novel framework for segmentation of small targets in medical images","volume":"15","author":"Zhao","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.neucom.2026.133946_bib0025","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"481","article-title":"EGE-UNet: an efficient group enhanced UNet for skin lesion segmentation","author":"Ruan","year":"2023"},{"key":"10.1016\/j.neucom.2026.133946_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.107393","article-title":"MSAByNet: a multiscale subtraction attention network framework based on Bayesian loss for medical image segmentation","volume":"103","author":"Zhao","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.neucom.2026.133946_bib0035","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"649","article-title":"Spot the difference: difference visual question answering with residual alignment","author":"Lu","year":"2024"},{"issue":"8","key":"10.1016\/j.neucom.2026.133946_bib0040","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: a survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.neucom.2026.133946_bib0045","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/TMI.2023.3291719","article-title":"LViT: language meets vision transformer in medical image segmentation","volume":"43","author":"Li","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.neucom.2026.133946_bib0050","author":"Devlin"},{"key":"10.1016\/j.neucom.2026.133946_bib0055","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"18155","article-title":"LAVT: language-aware vision transformer for referring image segmentation","author":"Yang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133946_bib0060","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","first-page":"151","article-title":"TGANet: text-guided attention for improved polyp segmentation","author":"Tomar","year":"2022"},{"key":"10.1016\/j.neucom.2026.133946_bib0065","author":"Neha"},{"key":"10.1016\/j.neucom.2026.133946_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105846","article-title":"MTGT: multiscale text feature-guided transformer in medical image segmentation","volume":"165","author":"Zhao","year":"2026","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.neucom.2026.133946_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2026.133326","article-title":"DCFANet: merging dynamic context clustering Mamba and context-to-focus attention for medical image segmentation","author":"Kui","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133946_bib0080","article-title":"Smart CSWin-UNet: integrating prototype attention gate and mixture-of-experts skip connections for medical image segmentation","author":"Feng","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133946_bib0085","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1314","article-title":"Searching for MobileNetV3","author":"Howard","year":"2019"},{"key":"10.1016\/j.neucom.2026.133946_bib0090","article-title":"Segmentation-enhanced multi-scale deep hashing for chest X-Ray image retrieval","author":"Wang","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.neucom.2026.133946_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102745","article-title":"A novel multi-attention, multi-scale 3D deep network for coronary artery segmentation","volume":"85","author":"Dong","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.neucom.2026.133946_bib0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112101","article-title":"MSBP-net: a multi-scale boundary prediction network for automated polyp segmentation","volume":"170","author":"Pan","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133946_bib0105","first-page":"1","article-title":"Mrscfusion: joint residual swin transformer and multiscale CNN for unsupervised multimodal medical image fusion","volume":"72","author":"Xie","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"5","key":"10.1016\/j.neucom.2026.133946_bib0110","doi-asserted-by":"crossref","first-page":"3317","DOI":"10.1109\/JBHI.2024.3391620","article-title":"MACTFusion: lightweight cross transformer for adaptive multimodal medical image fusion","volume":"29","author":"Xie","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.neucom.2026.133946_bib0115","series-title":"Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.133946_bib0120","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3459","article-title":"Universal segmentation at arbitrary granularity with language instruction","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133946_bib0125","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"109","article-title":"Tpro: text-prompting-based weakly supervised histopathology tissue segmentation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133946_bib0130","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.neucom.2026.133946_bib0135","doi-asserted-by":"crossref","DOI":"10.1016\/j.health.2025.100416","article-title":"An analytics-driven review of U-Net for medical image segmentation","author":"Neha","year":"2025","journal-title":"Healthc. Anal."},{"key":"10.1016\/j.neucom.2026.133946_bib0140","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVIII 16","first-page":"52","article-title":"Accurate RGB-D salient object detection via collaborative learning","author":"Ji","year":"2020"},{"key":"10.1016\/j.neucom.2026.133946_bib0145","series-title":"The Thirty-Ninth Annual Conference on Neural Information Processing Systems","article-title":"A TRIANGLE enables multimodal alignment beyond cosine similarity","author":"Cicchetti","year":"2026"},{"key":"10.1016\/j.neucom.2026.133946_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4113","article-title":"CAT-Seg: cost aggregation for open-vocabulary semantic segmentation","author":"Cho","year":"2024"},{"key":"10.1016\/j.neucom.2026.133946_bib0155","author":"Morozov"},{"issue":"1","key":"10.1016\/j.neucom.2026.133946_bib0160","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s41747-020-00173-2","article-title":"Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem","volume":"4","author":"Hofmanninger","year":"2020","journal-title":"European Radiology Experimental"},{"key":"10.1016\/j.neucom.2026.133946_bib0165","series-title":"2022 IEEE International Conference on Image Processing (ICIP)","first-page":"2306","article-title":"Osegnet: operational segmentation network for COVID-19 detection using chest X-Ray images","author":"Degerli","year":"2022"},{"key":"10.1016\/j.neucom.2026.133946_bib0170","series-title":"MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26","first-page":"451","article-title":"Kvasir-seg: a segmented polyp dataset","author":"Jha","year":"2020"},{"key":"10.1016\/j.neucom.2026.133946_bib0175","series-title":"2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)","first-page":"168","article-title":"Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (isic)","author":"Codella","year":"2018"},{"key":"10.1016\/j.neucom.2026.133946_bib0180","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data Br."},{"key":"10.1016\/j.neucom.2026.133946_bib0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102680","article-title":"The liver tumor segmentation benchmark (lits)","volume":"84","author":"Bilic","year":"2023","journal-title":"Med. Image Anal."},{"issue":"2","key":"10.1016\/j.neucom.2026.133946_bib0190","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1109\/TMI.2013.2284099","article-title":"Automatic tuberculosis screening using chest radiographs","volume":"33","author":"Jaeger","year":"2013","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"2","key":"10.1016\/j.neucom.2026.133946_bib0195","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1109\/TMI.2013.2290491","article-title":"Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration","volume":"33","author":"Candemir","year":"2013","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.neucom.2026.133946_bib0200","series-title":"European Congress on Digital Pathology","first-page":"11","article-title":"PanNuke: an open pan-cancer histology dataset for nuclei instance segmentation and classification","author":"Gamper","year":"2019"},{"issue":"10","key":"10.1016\/j.neucom.2026.133946_bib0205","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The multimodal brain tumor image segmentation benchmark (BRATS)","volume":"34","author":"Menze","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.neucom.2026.133946_bib0210","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2017.117","article-title":"Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features","volume":"4","author":"Bakas","year":"2017","journal-title":"Sci. Data"},{"key":"10.1016\/j.neucom.2026.133946_bib0215","author":"Bakas"},{"issue":"1","key":"10.1016\/j.neucom.2026.133946_bib0220","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1038\/s41597-024-03844-6","article-title":"AMD-SD: an optical coherence tomography image dataset for wet AMD lesions segmentation","volume":"11","author":"Hu","year":"2024","journal-title":"Sci. Data"},{"key":"10.1016\/j.neucom.2026.133946_bib0225","series-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","first-page":"23","article-title":"UNeXt: MLP-based rapid medical image segmentation network","author":"Valanarasu","year":"2022"},{"key":"10.1016\/j.neucom.2026.133946_bib0230","author":"Chen"},{"key":"10.1016\/j.neucom.2026.133946_bib0235","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102430","article-title":"EH-former: regional easy-hard-aware transformer for breast lesion segmentation in ultrasound images","volume":"109","author":"Qu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133946_bib0240","doi-asserted-by":"crossref","DOI":"10.3389\/fbioe.2024.1398237","article-title":"DA-TransUNet: integrating spatial and channel dual attention with transformer U-Net for medical image segmentation","volume":"12","author":"Sun","year":"2024","journal-title":"Front. Bioeng. Biotechnol."},{"key":"10.1016\/j.neucom.2026.133946_bib0245","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103347","article-title":"UM-net: rethinking ICGNet for polyp segmentation with uncertainty modeling","volume":"99","author":"Du","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.neucom.2026.133946_bib0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103241","article-title":"I2U-net: a dual-path U-Net with rich information interaction for medical image segmentation","volume":"97","author":"Dai","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.neucom.2026.133946_bib0255","author":"Zhao"},{"key":"10.1016\/j.neucom.2026.133946_bib0260","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103719","article-title":"HELPNet: hierarchical perturbations consistency and entropy-guided ensemble for scribble supervised medical image segmentation","volume":"105","author":"Zhang","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.neucom.2026.133946_bib0265","series-title":"Computer Vision \u2013 ECCV 2022 Workshops","first-page":"205","article-title":"Swin-Unet: UNET-like pure transformer for medical image segmentation","author":"Cao","year":"2023"},{"key":"10.1016\/j.neucom.2026.133946_bib0270","author":"Liu"},{"key":"10.1016\/j.neucom.2026.133946_bib0275","series-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2526","article-title":"Smarter, better, faster, longer: a modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference","author":"Warner","year":"2025"},{"key":"10.1016\/j.neucom.2026.133946_bib0280","author":"Nussbaum"},{"key":"10.1016\/j.neucom.2026.133946_bib0285","author":"Breton"},{"key":"10.1016\/j.neucom.2026.133946_bib0290","series-title":"EuroVis Workshop on Visual Analytics (EuroVA)","article-title":"Integrating layer-wise relevance propagation with stable diffusion for enhanced interpretability","author":"Auman","year":"2025"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226013433?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226013433?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T16:27:19Z","timestamp":1787848039000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226013433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":58,"alternative-id":["S0925231226013433"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133946","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multimodal medical image segmentation paradigm based on language-assisted transformer","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133946","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":"133946"}}