{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:15:41Z","timestamp":1783152941810,"version":"3.54.6"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"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":["U25A20443"],"award-info":[{"award-number":["U25A20443"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82472070"],"award-info":[{"award-number":["82472070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015640","name":"Tongji Hospital","doi-asserted-by":"publisher","award":["62225113"],"award-info":[{"award-number":["62225113"]}],"id":[{"id":"10.13039\/501100015640","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015640","name":"Tongji Hospital","doi-asserted-by":"publisher","award":["AI2024A03"],"award-info":[{"award-number":["AI2024A03"]}],"id":[{"id":"10.13039\/501100015640","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC2705700"],"award-info":[{"award-number":["2023YFC2705700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015286","name":"Hebei Provincial Key Research Projects","doi-asserted-by":"publisher","award":["2024BCB036"],"award-info":[{"award-number":["2024BCB036"]}],"id":[{"id":"10.13039\/501100015286","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":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104438","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T23:15:07Z","timestamp":1777590907000},"page":"104438","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TGC-Net: a structure-aware and semantically-aligned framework for text-guided medical image segmentation"],"prefix":"10.1016","volume":"135","author":[{"given":"Gaoren","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huangxuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-2280","authenticated-orcid":false,"given":"Lefei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wentao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104438_bib0001","unstructured":"R. Azad, E. K. Aghdam, A. Rauland, Y. Jia, A. H. Avval, A. Bozorgpour, S. Karimijafarbigloo, J. P. Cohen, E. Adeli, D. Merhof, Medical Image Segmentation Review: The Success of U-Net, 2022, arXiv: 2211.14830."},{"key":"10.1016\/j.inffus.2026.104438_bib0002","series-title":"Multi-aspect fusion in foundational large vision model for visible light medical imaging segmentation","author":"Huang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104438_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102634","article-title":"CSWin-UNet: transformer unet with cross-shaped windows for medical image segmentation","volume":"113","author":"Liu","year":"2025","journal-title":"Inf. Fusion"},{"issue":"4","key":"10.1016\/j.inffus.2026.104438_bib0004","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.1109\/TMI.2024.3523333","article-title":"Cross-modal conditioned reconstruction for language-guided medical image segmentation","volume":"44","author":"Huang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.inffus.2026.104438_bib0005","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":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.inffus.2026.104438_bib0006","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"724","article-title":"Ariadne\u2019s thread: using text prompts to improve segmentation of infected areas from chest X-ray images","author":"Zhong","year":"2023"},{"key":"10.1016\/j.inffus.2026.104438_bib0007","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"253","article-title":"Enhancing label-efficient medical image segmentation with text-guided diffusion models","author":"Feng","year":"2024"},{"key":"10.1016\/j.inffus.2026.104438_bib0008","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"636","article-title":"Towards robust medical image referring segmentation with incomplete textual prompts","author":"Wang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104438_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102719","article-title":"Attention-guided hierarchical fusion U-Net for uncertainty-driven medical image segmentation","volume":"115","author":"Munia","year":"2025","journal-title":"Inf. Fusion"},{"issue":"2","key":"10.1016\/j.inffus.2026.104438_bib0010","doi-asserted-by":"crossref","first-page":"020508-1","DOI":"10.2352\/J.ImagingSci.Technol.2020.64.2.020508","article-title":"Medical image segmentation based on U-Net: a review","volume":"64","author":"Du","year":"2020","journal-title":"J. Imaging Sci. Technol."},{"key":"10.1016\/j.inffus.2026.104438_bib0011","series-title":"2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS)","first-page":"558","article-title":"DoubleU-Net: a deep convolutional neural network for medical image segmentation","author":"Jha","year":"2020"},{"key":"10.1016\/j.inffus.2026.104438_bib0012","unstructured":"B. Kayalibay, G. Jensen, P. Van Der Smagt, CNN-Based Segmentation of Medical Imaging Data, 2017, arXiv: 1701.03056."},{"key":"10.1016\/j.inffus.2026.104438_bib0013","series-title":"International Conference on Medical image Computing and cOmputer-Assisted Intervention","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"issue":"2","key":"10.1016\/j.inffus.2026.104438_bib0014","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"10.1016\/j.inffus.2026.104438_bib0015","series-title":"Advances in Neural Information Processing Systems","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.inffus.2026.104438_bib0016","unstructured":"J. Chen, Y. Lu, Q. Yu, X. Luo, E. Adeli, Y. Wang, L. Lu, A.L. Yuille, Y. Zhou, TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation, 2021, arXiv: 2102.04306."},{"key":"10.1016\/j.inffus.2026.104438_bib0017","series-title":"International MICCAI Brainlesion Workshop","first-page":"272","article-title":"Swin UNETR: swin transformers for semantic segmentation of brain tumors in MRI images","author":"Hatamizadeh","year":"2021"},{"key":"10.1016\/j.inffus.2026.104438_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128740","article-title":"A comprehensive review of deep learning for medical image segmentation","volume":"613","author":"Xia","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.inffus.2026.104438_bib0019","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.2026.104438_bib0020","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3942","article-title":"GLoRIA: a multimodal global-local representation learning framework for label-efficient medical image recognition","author":"Huang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104438_bib0021","series-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing.","first-page":"3876","article-title":"MedCLIP: contrastive learning from unpaired medical images and text","volume":"2022","author":"Wang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104438_bib0022","series-title":"Advances in Neural Information Processing Systems 37","first-page":"3588","article-title":"CAT: coordinating anatomical-textual prompts for multi-organ and tumor segmentation","author":"Huang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104438_bib0023","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, Deformable DETR: Deformable Transformers for End-to-End Object Detection, 2020, arXiv: 2010.04159."},{"key":"10.1016\/j.inffus.2026.104438_bib0024","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4113","article-title":"CAT-Seg: cost aggregation for open-vocabulary semantic segmentation","author":"Cho","year":"2024"},{"key":"10.1016\/j.inffus.2026.104438_bib0025","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.inffus.2026.104438_bib0026","doi-asserted-by":"crossref","unstructured":"S.P. Morozov, A.E. Andreychenko, N.A. Pavlov, A. Vladzymyrskyy, N.V. Ledikhova, V.A. Gombolevskiy, I.A. Blokhin, P.B. Gelezhe, A. Gonchar, V.Y. Chernina, MosMedData: Chest CT Scans with COVID-19 Related Findings Dataset, 2020, arXiv: 2005.06465.","DOI":"10.1101\/2020.05.20.20100362"},{"issue":"1","key":"10.1016\/j.inffus.2026.104438_bib0027","doi-asserted-by":"crossref","first-page":"50","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":"Eur. Radio. Exp."},{"key":"10.1016\/j.inffus.2026.104438_bib0028","unstructured":"A.L. Simpson, M. Antonelli, S. Bakas, M. Bilello, K. Farahani, B. Van Ginneken, A. Kopp-Schneider, B.A. Landman, G. Litjens, B. Menze, et al., A Large Annotated Medical Image Dataset for the Development and Evaluation of Segmentation Algorithms, 2019, arXiv: 1902.09063."},{"key":"10.1016\/j.inffus.2026.104438_bib0029","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"1298","article-title":"CRISP-SAM2: SAM2 with cross-modal interaction and semantic prompting for multi-organ segmentation","author":"Yu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104438_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102642","article-title":"WORD: a large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image","volume":"82","author":"Luo","year":"2022","journal-title":"Med. Image Anal."},{"issue":"10","key":"10.1016\/j.inffus.2026.104438_bib0031","doi-asserted-by":"crossref","first-page":"6695","DOI":"10.1109\/TPAMI.2021.3100536","article-title":"AbdomenCT-1K: is abdominal organ segmentation a solved problem?","volume":"44","author":"Ma","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.inffus.2026.104438_bib0032","first-page":"8024","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104438_bib0033","series-title":"International Workshop on Deep Learning in Medical Image Analysis","first-page":"3","article-title":"UNet++: A nested U-Net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"10.1016\/j.inffus.2026.104438_bib0034","series-title":"European Conference on Computer Vision","first-page":"205","article-title":"Swin-UNet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"10.1016\/j.inffus.2026.104438_bib0035","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2441","article-title":"UCTransNet: rethinking the skip connections in U-Net from a channel-wise perspective with transformer","volume":"36","author":"Wang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104438_bib0036","series-title":"International Conference on Machine Learning","first-page":"5583","article-title":"ViLT: vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.inffus.2026.104438_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18155","article-title":"LAVT: language-aware vision transformer for referring image segmentation","author":"Yang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104438_bib0038","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"151","article-title":"TGANet: text-guided attention for improved polyp segmentation","author":"Tomar","year":"2022"},{"key":"10.1016\/j.inffus.2026.104438_bib0039","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"610","article-title":"LGA: a language guide adapter for advancing the SAM model\u2019s capabilities in medical image segmentation","author":"Hu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104438_bib0040","doi-asserted-by":"crossref","first-page":"1782","DOI":"10.1109\/TIP.2024.3371348","article-title":"Toward robust referring image segmentation","volume":"33","author":"Wu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104438_bib0041","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.inffus.2026.104438_bib0042","unstructured":"N. Ravi, V. Gabeur, Y.-T. Hu, R. Hu, C. Ryali, T. Ma, H. Khedr, R. R\u00e4dle, C. Rolland, L. Gustafson, et al., SAM 2: Segment Anything in Images and Videos, 2024, arXiv: 2408.00714."},{"issue":"1","key":"10.1016\/j.inffus.2026.104438_bib0043","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.inffus.2026.104438_bib0044","series-title":"European Conference on Computer Vision","first-page":"90","article-title":"I-MedSAM: implicit medical image segmentation with segment anything","author":"Wei","year":"2024"},{"key":"10.1016\/j.inffus.2026.104438_bib0045","unstructured":"J. Zhu, A. Hamdi, Y. Qi, Y. Jin, J. Wu, Medical SAM 2: Segment Medical Images as Video Via Segment Anything Model 2, 2024, arXiv: 2408.00874."},{"key":"10.1016\/j.inffus.2026.104438_bib0046","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3247","article-title":"Towards a comprehensive, efficient and promptable anatomic structure segmentation model using 3D whole-body CT scans","volume":"39","author":"Guo","year":"2025"},{"key":"10.1016\/j.inffus.2026.104438_bib0047","series-title":"Advances in Neural Information Processing Systems","first-page":"110746","article-title":"SegVol: universal and interactive volumetric medical image segmentation","volume":"37","author":"Du","year":"2024"},{"key":"10.1016\/j.inffus.2026.104438_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11386","article-title":"ZePT: zero-shot pan-tumor segmentation via query-disentangling and self-prompting","author":"Jiang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104438_bib0049","doi-asserted-by":"crossref","first-page":"2018","DOI":"10.1109\/TIP.2025.3566300","article-title":"Perceive-IR: learning to perceive degradation better for all-in-one image restoration","volume":"35","author":"Zhang","year":"2026","journal-title":"IEEE Trans. Image Process."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003180?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003180?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:20:06Z","timestamp":1783149606000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003180"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":49,"alternative-id":["S1566253526003180"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104438","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TGC-Net: a structure-aware and semantically-aligned framework for text-guided medical image segmentation","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104438","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":"104438"}}