{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:59:59Z","timestamp":1772823599602,"version":"3.50.1"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National Institute of Health","award":["R01CA251710"],"award-info":[{"award-number":["R01CA251710"]}]},{"name":"T.T. and W.F. Chao Foundation"},{"DOI":"10.13039\/100006988","name":"John S. Dunn Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006988","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/jbhi.2024.3507638","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:39:48Z","timestamp":1732736388000},"page":"3234-3246","source":"Crossref","is-referenced-by-count":8,"title":["Frozen Large-Scale Pretrained Vision-Language Models are the Effective Foundational Backbone for Multimodal Breast Cancer Prediction"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3764-2803","authenticated-orcid":false,"given":"Hung Q.","family":"Vo","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6042-2366","authenticated-orcid":false,"given":"Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Systems Medicine and Biomedical Engineering, Houston Methodist Cancer Center, Houston, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8329-6123","authenticated-orcid":false,"given":"Kelvin K.","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Systems Medicine and Biomedical Engineering, Houston Methodist Cancer Center, Houston, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8305-8272","authenticated-orcid":false,"given":"Chika F.","family":"Ezeana","sequence":"additional","affiliation":[{"name":"Department of Systems Medicine and Biomedical Engineering, Houston Methodist Cancer Center, Houston, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6180-7508","authenticated-orcid":false,"given":"Xiaohui","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Systems Medicine and Biomedical Engineering, Houston Methodist Cancer Center, Houston, TX, USA"}]},{"given":"Wei","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Breast Imaging, Division of Diagnostic Imaging, University of Texas MD Anderson Cancer Center, Houston, TX, USA"}]},{"given":"Jenny","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Medicine, Houston Methodist Neal Cancer Center, Houston, TX, USA"}]},{"given":"Hien V.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9188-6502","authenticated-orcid":false,"given":"Stephen T. C.","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Systems Medicine and Biomedical Engineering, Houston Methodist Cancer Center, Houston, TX, USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Breast cancer","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21763"},{"key":"ref3","article-title":"Breast cancer","year":"2023"},{"key":"ref4","article-title":"Breast cancer","year":"2023"},{"key":"ref5","article-title":"Bi-rads for mammography and ultrasound 2013 updated version","year":"2023"},{"key":"ref6","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref10","article-title":"EVA-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"ref11","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac","year":"2022"},{"key":"ref12","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref13","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.177"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220047.podcast"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3050040"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102083"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_12"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01286"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00385"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.19100"},{"key":"ref24","first-page":"6775","article-title":"Adding seemingly uninformative labels helps in low data regimes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Matsoukas","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109455"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3129068"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3102622"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3117272"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2945514"},{"key":"ref30","article-title":"High-resolution breast cancer screening with multi-view deep convolutional neural networks","author":"Geras","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101908"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102147"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102618"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102690"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3233535"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_61"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_38"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00423-x"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019182716"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-48995-4"},{"key":"ref43","article-title":"Self-supervised deep learning to enhance breast cancer detection on screening mammography","author":"Miller","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.0265"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-01174-9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-22437-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1799-6"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897885"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1200\/cci.18.00121"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3193250"},{"key":"ref51","article-title":"Learning domain-agnostic representation for disease diagnosis","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108858"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102138"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2021203758"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aba4373"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.21.01337"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3249404"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43990-2_7"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-45676-3_8"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_1"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_75"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00387"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2019182622"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.220027"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1038\/s41523-023-00517-2"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15102704"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08519-z"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-022-01352-y"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102825"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230227"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/BHI50953.2021.9508604"},{"key":"ref73","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref74","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref75","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani","year":"2023"},{"key":"ref76","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref77","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref78","first-page":"1059","article-title":"High-performance large-scale image recognition without normalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brock","year":"2021"},{"key":"ref79","first-page":"30016","article-title":"Training compute-optimal large language models","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Hoffmann","year":"2022"},{"key":"ref80","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"issue":"70","key":"ref81","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref82","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90 ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2400640"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02291"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-44201-8"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.123.044072"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3229161"},{"key":"ref90","article-title":"TabPFN: A transformer that solves small tabular classification problems in a second","author":"Hollmann","year":"2022"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00341-z"},{"key":"ref93","article-title":"Pytorch image models","author":"Wightman","year":"2019"},{"key":"ref94","article-title":"EVA-clip-18b: Scaling clip to 18 billion parameters","author":"Sun","year":"2024"},{"key":"ref95","article-title":"Breast imaging-reporting and data system (Bi-rads) assessment category 3","year":"2023"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/10989059\/10769012.pdf?arnumber=10769012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T17:54:28Z","timestamp":1746640468000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10769012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":95,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2024.3507638","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}