{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T19:50:48Z","timestamp":1791921048904,"version":"4.3.4"},"reference-count":62,"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":[[2026,10,10]],"date-time":"2026-10-10T00:00:00Z","timestamp":1791590400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01EB034692"],"award-info":[{"award-number":["R01EB034692"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01AG078250"],"award-info":[{"award-number":["R01AG078250"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computerized Medical Imaging and Graphics"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.compmedimag.2026.102828","type":"journal-article","created":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T15:17:57Z","timestamp":1791645477000},"page":"102828","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CDPDNet: Integrating text guidance with hybrid vision encoders for medical image segmentation"],"prefix":"10.1016","volume":"136","author":[{"given":"Jiong","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boxiao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2669-2610","authenticated-orcid":false,"given":"Kuang","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compmedimag.2026.102828_b1","doi-asserted-by":"crossref","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","article-title":"The medical segmentation decathlon","volume":"13","author":"Antonelli","year":"2022","journal-title":"Nat. Commun."},{"key":"10.1016\/j.compmedimag.2026.102828_b2","series-title":"Towards general purpose vision foundation models for medical image analysis: An experimental study of dinov2 on radiology benchmarks","author":"Baharoon","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102828_b3","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."},{"key":"10.1016\/j.compmedimag.2026.102828_b4","series-title":"ICCV","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.compmedimag.2026.102828_b5","series-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"10.1016\/j.compmedimag.2026.102828_b6","series-title":"Med3d: Transfer learning for 3d medical image analysis","author":"Chen","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102828_b7","series-title":"Sam on medical images: A comprehensive study on three prompt modes","author":"Cheng","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102828_b8","doi-asserted-by":"crossref","unstructured":"Chollet, F., 2017. Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"10.1016\/j.compmedimag.2026.102828_b9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"ICLR"},{"key":"10.1016\/j.compmedimag.2026.102828_b10","doi-asserted-by":"crossref","first-page":"110746","DOI":"10.52202\/079017-3516","article-title":"Segvol: Universal and interactive volumetric medical image segmentation","volume":"37","author":"Du","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2026.102828_b11","doi-asserted-by":"crossref","first-page":"3619","DOI":"10.1109\/TMI.2020.3001036","article-title":"Multi-organ segmentation over partially labeled datasets with multi-scale feature abstraction","volume":"39","author":"Fang","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2026.102828_b12","doi-asserted-by":"crossref","unstructured":"Gao, Y., 2024. Training like a medical resident: Context-prior learning toward universal medical image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 11194\u201311204.","DOI":"10.1109\/CVPR52733.2024.01064"},{"key":"10.1016\/j.compmedimag.2026.102828_b13","series-title":"International Workshop on Reconstruction and Analysis of Moving Body Organs","first-page":"215","article-title":"Multi-structure segmentation from partially labeled datasets. application to body composition measurements on ct scans","author":"Gonz\u00e1lez","year":"2018"},{"key":"10.1016\/j.compmedimag.2026.102828_b14","doi-asserted-by":"crossref","unstructured":"Guo, H., Zhang, J., Huang, J., Mok, T.C., Guo, D., Yan, K., Lu, L., Jin, D., Xu, M., 2025. Towards a comprehensive, efficient and promptable anatomic structure segmentation model using 3d whole-body ct scans. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 3247\u20133256.","DOI":"10.1609\/aaai.v39i3.32335"},{"key":"10.1016\/j.compmedimag.2026.102828_b15","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.compmedimag.2026.102828_b16","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H.R., Xu, D., 2022. Unetr: Transformers for 3d medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 574\u2013584.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"10.1016\/j.compmedimag.2026.102828_b17","series-title":"An international challenge to use artificial intelligence to define the state-of-the-art in kidney and kidney tumor segmentation in ct imaging","author":"Heller","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102828_b18","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1109\/TMI.2022.3213983","article-title":"Learn2reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning","volume":"42","author":"Hering","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.compmedimag.2026.102828_b19","doi-asserted-by":"crossref","first-page":"3588","DOI":"10.52202\/079017-0119","article-title":"Cat: Coordinating anatomical-textual prompts for multi-organ and tumor segmentation","volume":"37","author":"Huang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2026.102828_b20","series-title":"MICCAI","first-page":"146","article-title":"Multi-organ segmentation via co-training weight-averaged models from few-organ datasets","author":"Huang","year":"2020"},{"key":"10.1016\/j.compmedimag.2026.102828_b21","unstructured":"Igelsias, J., Styner, M., Langerak, T., Landman, B., Xu, Z., Klein, A., 2015. Miccai multi-atlas labeling beyond the cranial vault\u2013workshop and challenge. In: Proc. MICCAI Multi-Atlas Labeling beyond Cranial Vault\u2014Workshop Challenge."},{"key":"10.1016\/j.compmedimag.2026.102828_b22","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":"Nature Methods"},{"key":"10.1016\/j.compmedimag.2026.102828_b23","doi-asserted-by":"crossref","first-page":"36722","DOI":"10.52202\/068431-2661","article-title":"Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation","volume":"35","author":"Ji","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compmedimag.2026.102828_b24","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Huang, Z., Zhang, R., Zhang, X., Zhang, S., 2024. Zept: Zero-shot pan-tumor segmentation via query-disentangling and self-prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11386\u201311397.","DOI":"10.1109\/CVPR52733.2024.01082"},{"key":"10.1016\/j.compmedimag.2026.102828_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2026.102811","article-title":"Enhancing semi-supervised skin lesion segmentation with text-guided pseudo descriptions","author":"Jiang","year":"2026","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102828_b26","doi-asserted-by":"crossref","DOI":"10.1148\/radiol.233029","article-title":"Automated deep learning-based detection and segmentation of lung tumors at ct","volume":"314","author":"Kashyap","year":"2025","journal-title":"Radiology"},{"key":"10.1016\/j.compmedimag.2026.102828_b27","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et al., 2023. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.compmedimag.2026.102828_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102642","article-title":"Towards generic abdominal multi-organ segmentation with multiple partially labeled datasets","author":"Li","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102828_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2026.102816","article-title":"Tef-sam: Prototype memory for medical lesion segmentation with text-free inference","author":"Liang","year":"2026","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102828_b30","series-title":"European Conference on Computer Vision","first-page":"38","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.compmedimag.2026.102828_b31","series-title":"ICCV","first-page":"21152","article-title":"Clip-driven universal model for organ segmentation and tumor detection","author":"Liu","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102828_b32","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."},{"key":"10.1016\/j.compmedimag.2026.102828_b33","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.compmedimag.2026.102828_b34","series-title":"Unleashing the strengths of unlabeled data in pan-cancer abdominal organ quantification: the flare22 challenge","author":"Ma","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102828_b35","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 Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compmedimag.2026.102828_b36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"TMLR"},{"key":"10.1016\/j.compmedimag.2026.102828_b37","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1148\/radiol.2021203387","article-title":"Computer-aided detection of subsolid nodules at chest ct: improved performance with deep learning\u2013based ct section thickness reduction","volume":"299","author":"Park","year":"2021","journal-title":"Radiology"},{"key":"10.1016\/j.compmedimag.2026.102828_b38","first-page":"1","article-title":"Exploring scalable medical image encoders beyond text supervision","author":"P\u00e9rez-Garc\u00eda","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.compmedimag.2026.102828_b39","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.compmedimag.2026.102828_b40","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1038\/s41597-020-00715-8","article-title":"Ct-org, a new dataset for multiple organ segmentation in computed tomography","volume":"7","author":"Rister","year":"2020","journal-title":"Sci. Data"},{"key":"10.1016\/j.compmedimag.2026.102828_b41","series-title":"MICCAI","first-page":"556","article-title":"Deeporgan: Multi-level deep convolutional networks for automated pancreas segmentation","author":"Roth","year":"2015"},{"key":"10.1016\/j.compmedimag.2026.102828_b42","doi-asserted-by":"crossref","first-page":"e1","DOI":"10.1002\/mp.13264","article-title":"Deep learning in medical imaging and radiation therapy","volume":"46","author":"Sahiner","year":"2019","journal-title":"Med. Phys."},{"key":"10.1016\/j.compmedimag.2026.102828_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.101979","article-title":"Marginal loss and exclusion loss for partially supervised multi-organ segmentation","volume":"70","author":"Shi","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.compmedimag.2026.102828_b44","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1007\/s11263-024-02167-8","article-title":"Unsupervised object localization in the era of self-supervised vits: A survey","volume":"133","author":"Simeoni","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.compmedimag.2026.102828_b45","series-title":"3D image reconstruction for comparison of algorithm database","author":"Soler","year":"2010"},{"key":"10.1016\/j.compmedimag.2026.102828_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2026.102698","article-title":"Ta-medsam: Text-augmented improved medsam for pulmonary lesion segmentation","author":"Tang","year":"2026","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102828_b47","series-title":"WACV","first-page":"547","article-title":"Multi-modal learning from unpaired images: Application to multi-organ segmentation in ct and mri","author":"Valindria","year":"2018"},{"key":"10.1016\/j.compmedimag.2026.102828_b48","series-title":"CVPR","first-page":"3124","article-title":"Cut and learn for unsupervised object detection and instance segmentation","author":"Wang","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102828_b49","doi-asserted-by":"crossref","DOI":"10.1109\/TNNLS.2025.3586694","article-title":"Sam-med3d: A vision foundation model for general-purpose segmentation on volumetric medical images","author":"Wang","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.compmedimag.2026.102828_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2025.102650","article-title":"Collect vascular specimens in one cabinet: A hierarchical prompt-guided universal model for 3d vascular segmentation","author":"Wang","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.compmedimag.2026.102828_b51","series-title":"CVPR","first-page":"14543","article-title":"Self-supervised transformers for unsupervised object discovery using normalized cut","author":"Wang","year":"2022"},{"key":"10.1016\/j.compmedimag.2026.102828_b52","doi-asserted-by":"crossref","first-page":"15790","DOI":"10.1109\/TPAMI.2023.3305122","article-title":"Tokencut: Segmenting objects in images and videos with self-supervised transformer and normalized cut","volume":"45","author":"Wang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compmedimag.2026.102828_b53","doi-asserted-by":"crossref","first-page":"14905","DOI":"10.1109\/TPAMI.2023.3312587","article-title":"Learning from partially labeled data for multi-organ and tumor segmentation","volume":"45","author":"Xie","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.compmedimag.2026.102828_b54","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De Mello, S., 2023. Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2955\u20132966.","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"10.1016\/j.compmedimag.2026.102828_b55","series-title":"MICCAI","first-page":"508","article-title":"Uniseg: A prompt-driven universal segmentation model as well as a strong representation learner","author":"Ye","year":"2023"},{"key":"10.1016\/j.compmedimag.2026.102828_b56","doi-asserted-by":"crossref","first-page":"4060","DOI":"10.1109\/TIP.2019.2905537","article-title":"Crossbar-net: A novel convolutional neural network for kidney tumor segmentation in ct images","volume":"28","author":"Yu","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.compmedimag.2026.102828_b57","series-title":"CVPR","first-page":"1195","article-title":"Dodnet: Learning to segment multi-organ and tumors from multiple partially labeled datasets","author":"Zhang","year":"2021"},{"key":"10.1016\/j.compmedimag.2026.102828_b58","series-title":"IJCAI","first-page":"4271","article-title":"Light-weight hybrid convolutional network for liver tumor segmentation","author":"Zhang","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102828_b59","series-title":"ICCV","first-page":"10672","article-title":"Prior-aware neural network for partially-supervised multi-organ segmentation","author":"Zhou","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102828_b60","series-title":"DLMIA","first-page":"3","article-title":"Unet++: A nested u-net architecture for medical image segmentation","author":"Zhou","year":"2018"},{"key":"10.1016\/j.compmedimag.2026.102828_b61","series-title":"MICCAI2019","first-page":"3","article-title":"Multi-scale coarse-to-fine segmentation for screening pancreatic ductal adenocarcinoma","author":"Zhu","year":"2019"},{"key":"10.1016\/j.compmedimag.2026.102828_b62","doi-asserted-by":"crossref","first-page":"19769","DOI":"10.52202\/075280-0868","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Computerized Medical Imaging and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089561112600131X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089561112600131X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T19:28:14Z","timestamp":1791919694000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089561112600131X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":62,"alternative-id":["S089561112600131X"],"URL":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102828","relation":{},"ISSN":["0895-6111"],"issn-type":[{"value":"0895-6111","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CDPDNet: Integrating text guidance with hybrid vision encoders for medical image segmentation","name":"articletitle","label":"Article Title"},{"value":"Computerized Medical Imaging and Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compmedimag.2026.102828","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"102828"}}