{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:23:29Z","timestamp":1783059809598,"version":"3.54.6"},"reference-count":43,"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":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002920","name":"University Grants Committee Research Grants Council","doi-asserted-by":"publisher","award":["15102222"],"award-info":[{"award-number":["15102222"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"University Grants Committee Research Grants Council","doi-asserted-by":"publisher","award":["15102524"],"award-info":[{"award-number":["15102524"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132560","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T23:57:20Z","timestamp":1777161440000},"page":"132560","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Adapting vision-Language foundation model for next generation medical ultrasound image analysis"],"prefix":"10.1016","volume":"325","author":[{"given":"Jingguo","family":"Qu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyang","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tonghuan","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Ning","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7059-0929","authenticated-orcid":false,"given":"Jing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ann Dorothy","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Winnie Chiu-Wing","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5979-6072","authenticated-orcid":false,"given":"Michael Tin-Cheung","family":"Ying","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.eswa.2026.132560_bib0001","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.2214\/ajr.184.5.01841691","article-title":"Sonographic evaluation of cervical lymph nodes","volume":"184","author":"Ahuja","year":"2005","journal-title":"American Journal of Roentgenology"},{"issue":"1","key":"10.1016\/j.eswa.2026.132560_bib0002","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1102\/1470-7330.2008.0006","article-title":"Ultrasound of malignant cervical lymph nodes","volume":"8","author":"Ahuja","year":"2008","journal-title":"Cancer Imaging"},{"key":"10.1016\/j.eswa.2026.132560_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data in Brief"},{"key":"10.1016\/j.eswa.2026.132560_bib0004","unstructured":"Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M.S., Bohg, J., Bosselut, A., Brunskill, E. et al. (2021). On the opportunities and risks of foundation models. arXiv: 2108.07258."},{"issue":"2","key":"10.1016\/j.eswa.2026.132560_bib0005","doi-asserted-by":"crossref","first-page":"234","DOI":"10.2214\/AJR.13.12072","article-title":"Screening breast ultrasound: Past, present, and future","volume":"204","author":"Brem","year":"2015","journal-title":"American Journal of Roentgenology"},{"key":"10.1016\/j.eswa.2026.132560_bib0006","doi-asserted-by":"crossref","first-page":"16664","DOI":"10.52202\/068431-1212","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132560_bib0007","series-title":"North American chapter of the association for computational linguistics","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.eswa.2026.132560_bib0008","unstructured":"Dosovitskiy, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929."},{"key":"10.1016\/j.eswa.2026.132560_bib0009","unstructured":"Eslami, S., de Melo, G., & Meinel, C. (2021). Does CLIP benefit visual question answering in the medical domain as much as it does in the general domain?arxiv: 2112.13906."},{"key":"10.1016\/j.eswa.2026.132560_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.106389","article-title":"Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules","volume":"155","author":"Gong","year":"2023","journal-title":"Computers in Biology and Medicine"},{"issue":"3","key":"10.1016\/j.eswa.2026.132560_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.jmir.2024.101544","article-title":"Differentiation of benign and malignant lymph nodes using ultrasound-based radiomics and machine learning","volume":"55","author":"Han","year":"2024","journal-title":"Journal of Medical Imaging and Radiation Sciences"},{"issue":"1","key":"10.1016\/j.eswa.2026.132560_bib0012","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1186\/s12885-025-13447-y","article-title":"Artificial intelligence performance in ultrasound-based lymph node diagnosis: A systematic review and meta-analysis","volume":"25","author":"Han","year":"2025","journal-title":"BMC cancer"},{"key":"10.1016\/j.eswa.2026.132560_bib0013","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.eswa.2026.132560_bib0014","series-title":"International conference on machine learning","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"issue":"2","key":"10.1016\/j.eswa.2026.132560_bib0015","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.eswa.2026.132560_bib0016","series-title":"European conference on computer vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.eswa.2026.132560_bib0017","article-title":"MicroSegNet: A deep learning approach for prostate segmentation on micro-ultrasound images","volume":"112","author":"Jiang","year":"2023","journal-title":"Computerized Medical Imaging and Graphics: The Official Journal of the Computerized Medical Imaging Society"},{"key":"10.1016\/j.eswa.2026.132560_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103202","article-title":"USFM: A universal ultrasound foundation model generalized to tasks and organs towards label efficient image analysis","volume":"96","author":"Jiao","year":"2024","journal-title":"Medical Image Analysis"},{"key":"10.1016\/j.eswa.2026.132560_bib0019","unstructured":"Khattak, M. U., Kunhimon, S., Naseer, M., Khan, S., & Khan, F.S. (2024). Unimed-clip: Towards a unified image-text pretraining paradigm for diverse medical imaging modalities. arXiv preprint arXiv: 2412.10372."},{"key":"10.1016\/j.eswa.2026.132560_bib0020","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., Doll\u00e1r, P., & Girshick, R. (2023). Segment anything. arXiv: 2304.02643.","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"1","key":"10.1016\/j.eswa.2026.132560_bib0021","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TMI.2024.3424978","article-title":"Ultrasound report generation with cross-modality feature alignment via unsupervised guidance","volume":"44","author":"Li","year":"2024","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.132560_bib0022","series-title":"European conference on computer vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.eswa.2026.132560_bib0023","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"525","article-title":"PMC-Clip: Contrastive language-image pre-training using biomedical documents","author":"Lin","year":"2023"},{"key":"10.1016\/j.eswa.2026.132560_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7086","article-title":"Image segmentation using text and image prompts","author":"L\u00fcddecke","year":"2022"},{"key":"10.1016\/j.eswa.2026.132560_bib0025","unstructured":"Meyer, A., Murali, A., Mutter, D., & Padoy, N. (2024). UltraSam: A foundation model for ultrasound using large open-access segmentation datasets. hrefhttp:\/\/arxiv.org\/abs\/2411.16222arXiv:2411.16222."},{"key":"10.1016\/j.eswa.2026.132560_bib0026","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A. et al. (2023). Dinov2: Learning robust visual features without supervision. arXiv: 2304.07193."},{"key":"10.1016\/j.eswa.2026.132560_bib0027","article-title":"An open access thyroid ultrasound image database","volume":"vol. 9287","author":"Pedraza","year":"2015"},{"key":"10.1016\/j.eswa.2026.132560_bib0028","series-title":"International conference on medical imaging with deep learning","article-title":"Exploring transfer learning in medical image segmentation using vision-language models","author":"Poudel","year":"2023"},{"key":"10.1016\/j.eswa.2026.132560_bib0029","doi-asserted-by":"crossref","first-page":"97208","DOI":"10.1109\/ACCESS.2025.3575454","article-title":"The application of deep learning for lymph node segmentation: A systematic review","volume":"13","author":"Qu","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132560_bib0030","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.eswa.2026.132560_bib0031","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I. et al. (2018). Improving language understanding by generative pre-training. https:\/\/api.semanticscholar.org\/CorpusID:49313245."},{"key":"10.1016\/j.eswa.2026.132560_bib0032","series-title":"Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5\u20139, 2015, proceedings, part III 18","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"issue":"1","key":"10.1016\/j.eswa.2026.132560_bib0033","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1038\/s41597-024-03496-6","article-title":"Rocov2: Radiology objects in context version 2, an updated multimodal image dataset","volume":"11","author":"R\u00fcckert","year":"2024","journal-title":"Scientific Data"},{"key":"10.1016\/j.eswa.2026.132560_sbref0034","first-page":"1","article-title":"Medpix 2.0: A comprehensive multimodal biomedical data set for advanced AI applications with retrieval augmented generation and knowledge graphs","author":"Siragusa","year":"2025","journal-title":"Data Science and Engineering"},{"issue":"3","key":"10.1016\/j.eswa.2026.132560_bib0035","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1002\/jcu.1870230306","article-title":"Thyroid nodules: Re-evaluation with ultrasound","volume":"23","author":"Takashima","year":"1995","journal-title":"Journal of Clinical Ultrasound"},{"key":"10.1016\/j.eswa.2026.132560_bib0036","doi-asserted-by":"crossref","first-page":"5696","DOI":"10.52202\/068431-0412","article-title":"OmniVL: One foundation model for image-language and video-language tasks","volume":"35","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132560_bib0037","first-page":"3876","article-title":"MedCLIP: Contrastive learning from unpaired medical images and text","volume":"2022","author":"Wang","year":"2022","journal-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing"},{"key":"10.1016\/j.eswa.2026.132560_bib0038","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7959","article-title":"Robust fine-tuning of zero-shot models","author":"Wortsman","year":"2022"},{"key":"10.1016\/j.eswa.2026.132560_bib0039","unstructured":"Xu, H., Xie, S., Tan, X.E., Huang, P.-Y., Howes, R., Sharma, V., Li, S.-W., Ghosh, G., Zettlemoyer, L., & Feichtenhofer, C. (2023). Demystifying clip data. arXiv preprint arXiv: 2309.16671."},{"key":"10.1016\/j.eswa.2026.132560_bib0040","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C. et al. (2025). Qwen3 technical report. arXiv preprint arXiv: 2505.09388."},{"key":"10.1016\/j.eswa.2026.132560_bib0041","doi-asserted-by":"crossref","unstructured":"Yin, D., Hu, L., Li, B., Zhang, Y., & Yang, X. (2024). 5%> 100%: Breaking performance shackles of full fine-tuning on visual recognition tasks. arXiv preprint arXiv: 2408.08345.","DOI":"10.1109\/CVPR52734.2025.01869"},{"issue":"5","key":"10.1016\/j.eswa.2026.132560_bib0042","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/S0009-9260(02)00584-6","article-title":"Sonography of neck lymph nodes. Part I: Normal lymph nodes","volume":"58","author":"Ying","year":"2003","journal-title":"Clinical Radiology"},{"key":"10.1016\/j.eswa.2026.132560_bib0043","unstructured":"Zhang, S., Xu, Y., Usuyama, N., Xu, H., Bagga, J., Tinn, R., Preston, S., Rao, R., Wei, M., Valluri, N. et al. (2023). BiomedCLIP: A multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv: 2303.00915."}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426014739?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426014739?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:50:32Z","timestamp":1783057832000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426014739"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":43,"alternative-id":["S0957417426014739"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132560","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adapting vision-Language foundation model for next generation medical ultrasound image analysis","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132560","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":"132560"}}