{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T04:13:48Z","timestamp":1776226428963,"version":"3.50.1"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100016692","name":"Key Research and Development Program of Ningxia","doi-asserted-by":"publisher","award":["2023BEG03043"],"award-info":[{"award-number":["2023BEG03043"]}],"id":[{"id":"10.13039\/100016692","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016692","name":"Key Research and Development Program of Ningxia","doi-asserted-by":"publisher","award":["2024FRD05078"],"award-info":[{"award-number":["2024FRD05078"]}],"id":[{"id":"10.13039\/100016692","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82472116"],"award-info":[{"award-number":["82472116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["24ZR1404100"],"award-info":[{"award-number":["24ZR1404100"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Biomedical Signal Processing and Control"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.bspc.2026.110225","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T08:53:43Z","timestamp":1775120023000},"page":"110225","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["FCUFormer: A multi-view informed vision-language foundation model for interpreting fetal cardiac ultrasound abnormalities"],"prefix":"10.1016","volume":"120","author":[{"given":"Benshuang","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenkang","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueli","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-0678","authenticated-orcid":false,"given":"Xinrong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.bspc.2026.110225_b1","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1016\/j.jacc.2019.10.002","volume":"75","author":"Sachdeva","year":"2020","journal-title":"J. Am. Coll. Cardiol."},{"issue":"8","key":"10.1016\/j.bspc.2026.110225_b2","doi-asserted-by":"crossref","first-page":"1911","DOI":"10.1109\/TMI.2022.3151606","article-title":"Motion estimation by deep learning in 2D echocardiography: Synthetic dataset and validation","volume":"41","author":"Evain","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"5","key":"10.1016\/j.bspc.2026.110225_b3","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1109\/TMI.2022.3226274","article-title":"A machine learning method for automated description and workflow analysis of first trimester ultrasound scans","volume":"42","author":"Yasrab","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"10.1016\/j.bspc.2026.110225_b4","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1038\/s41746-017-0013-1","article-title":"Fast and accurate view classification of echocardiograms using deep learning","volume":"1","author":"Madani","year":"2018","journal-title":"NPJ Digit. Med."},{"issue":"1","key":"10.1016\/j.bspc.2026.110225_b5","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2400640","article-title":"A multimodal biomedical foundation model trained from fifteen million image\u2013text pairs","volume":"2","author":"Zhang","year":"2025","journal-title":"NEJM AI"},{"issue":"1","key":"10.1016\/j.bspc.2026.110225_b6","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1007\/s40846-024-00849-9","article-title":"Enhancing diagnostic accuracy and efficiency with GPT-4-Generated structured reports: A comprehensive study","volume":"44","author":"Wang","year":"2024","journal-title":"J. Med. Biol. Eng."},{"key":"10.1016\/j.bspc.2026.110225_b7","unstructured":"S. Lee, W.J. Kim, J. Chang, J.C. Ye, LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.bspc.2026.110225_b8","doi-asserted-by":"crossref","unstructured":"S.-C. Huang, L. Shen, M.P. Lungren, S. Yeung, Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 3942\u20133951.","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"10.1016\/j.bspc.2026.110225_b9","doi-asserted-by":"crossref","unstructured":"M.Y. Lu, B. Chen, A. Zhang, D.F.K. Williamson, R.J. Chen, T. Ding, L.P. Le, Y.-S. Chuang, F. Mahmood, Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 19764\u201319775.","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"10.1016\/j.bspc.2026.110225_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.103001","article-title":"OphGLM: An ophthalmology large language-and-vision assistant","volume":"157","author":"Deng","year":"2024","journal-title":"Artif. Intell. Med."},{"issue":"6","key":"10.1016\/j.bspc.2026.110225_b11","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1002\/uog.26224","article-title":"ISUOG practice guidelines (updated): fetal cardiac screening","volume":"61","author":"Carvalho","year":"2023","journal-title":"Ultrasound. Obstet. Gynecol"},{"key":"10.1016\/j.bspc.2026.110225_b12","series-title":"European Conference on Computer Vision","first-page":"685","article-title":"Joint learning of localized representations from medical images and reports","author":"M\u00fcller","year":"2022"},{"key":"10.1016\/j.bspc.2026.110225_b13","series-title":"FetalCLIP: Towards fetal ultrasound foundation models via contrastive language-image Pre-training","author":"Christensen","year":"2024"},{"issue":"1","key":"10.1016\/j.bspc.2026.110225_b14","first-page":"220","article-title":"SonoNet: Real-Time detection and localisation of fetal standard scan planes in freehand ultrasound","volume":"37","author":"Baumgartner","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"9","key":"10.1016\/j.bspc.2026.110225_b15","doi-asserted-by":"crossref","first-page":"2198","DOI":"10.1109\/TMI.2019.2900516","article-title":"Deep learning for segmentation using an open Large-Scale dataset in 2D echocardiography","volume":"38","author":"Leclerc","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.bspc.2026.110225_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127443","article-title":"Fetal cardiac ultrasound standard section detection model based on multitask learning and mixed attention mechanism","volume":"579","author":"He","year":"2024","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.bspc.2026.110225_b17","first-page":"1123","article-title":"Multi-View Multi-Instance learning based on joint sparse representation for diagnosis of cardiovascular diseases","volume":"25","author":"Chen","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.bspc.2026.110225_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2019.101548","article-title":"Multi-task learning for quality assessment of fetal head ultrasound images","volume":"58","author":"Lin","year":"2019","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.bspc.2026.110225_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103470","article-title":"Multiple token rearrangement transformer network with explicit superpixel constraint for segmentation of echocardiography","volume":"101","author":"Ding","year":"2025","journal-title":"Med. Image Anal."},{"issue":"6","key":"10.1016\/j.bspc.2026.110225_b20","doi-asserted-by":"crossref","first-page":"2215","DOI":"10.1109\/TMI.2024.3362964","article-title":"Embedding tasks into the latent space: Cross-space consistency for multi-dimensional analysis in echocardiography","volume":"43","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.bspc.2026.110225_b21","series-title":"GPT-4o system card","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.bspc.2026.110225_b22","series-title":"International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.bspc.2026.110225_b23","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10.1016\/j.bspc.2026.110225_b24","doi-asserted-by":"crossref","unstructured":"X. Chen, K. He, Exploring simple siamese representation learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15750\u201315758.","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"10.1016\/j.bspc.2026.110225_b25","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20792","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2022"},{"key":"10.1016\/j.bspc.2026.110225_b26","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Making the most of text semantics to improve biomedical vision-language processing","author":"Boecking","year":"2022"},{"key":"10.1016\/j.bspc.2026.110225_b27","unstructured":"Z. Huang, C. Wu, T. Chen, et al., Visual-language pre-training for pathology, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 21529\u201321540."},{"key":"10.1016\/j.bspc.2026.110225_b28","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"222","article-title":"UniBrain: Universal brain MRI diagnosis with hierarchical knowledge-enhanced Pre-training","author":"Lei","year":"2023"},{"key":"10.1016\/j.bspc.2026.110225_b29","series-title":"OphGLM: Training an ophthalmology large Language-and-Vision assistant based on instructions and dialogue","author":"Deng","year":"2024"},{"key":"10.1016\/j.bspc.2026.110225_b30","doi-asserted-by":"crossref","unstructured":"Z. Wang, Z. Wu, D. Agarwal, J. Sun, Medclip: Contrastive learning from unpaired medical images and text, in: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing, Vol. 2022, 2022, p. 3876.","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"10.1016\/j.bspc.2026.110225_b31","first-page":"28541","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.bspc.2026.110225_b32","doi-asserted-by":"crossref","unstructured":"S. Bannur, S. Hyland, Q. Liu, F. Perez-Garcia, M. Ilse, D.C. Castro, B. Boecking, H. Sharma, K. Bouzid, A. Thieme, et al., Learning to exploit temporal structure for biomedical vision-language processing, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15016\u201315027.","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"10.1016\/j.bspc.2026.110225_b33","first-page":"56186","article-title":"Med-unic: Unifying cross-lingual medical vision-language pre-training by diminishing bias","volume":"36","author":"Wan","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.bspc.2026.110225_b34","series-title":"EchoCLIP: Towards multi-modal echocardiography video understanding via contrastive learning","author":"Christensen","year":"2024"},{"key":"10.1016\/j.bspc.2026.110225_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103536","article-title":"Bridging multi-level gaps: Bidirectional reciprocal cycle framework for text-guided label-efficient segmentation in echocardiography","volume":"102","author":"Zhang","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.bspc.2026.110225_b36","series-title":"EchoPrime: A multi-video view-informed vision-language model for comprehensive echocardiography interpretation","author":"Vukadinovic","year":"2024"},{"issue":"1","key":"10.1016\/j.bspc.2026.110225_b37","first-page":"123","article-title":"Heterogeneity in fetal ultrasound reporting: Challenges and opportunities for standardization","volume":"28","author":"Wang","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.bspc.2026.110225_b38","series-title":"FOCUS: Four-chamber ultrasound image dataset for fetal cardiac biometric measurement","author":"Songxiong","year":"2025"},{"key":"10.1016\/j.bspc.2026.110225_b39","first-page":"1","article-title":"Vision\u2013language foundation model for echocardiogram interpretation","author":"Christensen","year":"2024","journal-title":"Nature Med."},{"key":"10.1016\/j.bspc.2026.110225_b40","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"}],"container-title":["Biomedical Signal Processing and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426007792?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1746809426007792?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T03:31:34Z","timestamp":1776223894000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1746809426007792"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":40,"alternative-id":["S1746809426007792"],"URL":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110225","relation":{},"ISSN":["1746-8094"],"issn-type":[{"value":"1746-8094","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FCUFormer: A multi-view informed vision-language foundation model for interpreting fetal cardiac ultrasound abnormalities","name":"articletitle","label":"Article Title"},{"value":"Biomedical Signal Processing and Control","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110225","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"110225"}}