{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T18:04:10Z","timestamp":1770141850020,"version":"3.49.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01-EB029944"],"award-info":[{"award-number":["R01-EB029944"]}],"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":["R01-EB030582"],"award-info":[{"award-number":["R01-EB030582"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cincinnati Children's Hospital Medical Center: Academic and Research Committee (ARC) Awards"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3568036","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T14:05:45Z","timestamp":1748441145000},"page":"17613-17622","source":"Crossref","is-referenced-by-count":4,"title":["RadCLIP: Enhancing Radiologic Image Analysis Through Contrastive Language\u2013Image Pretraining"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9904-9741","authenticated-orcid":false,"given":"Zhixiu","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Radiology, Imaging Research Center, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5267-2875","authenticated-orcid":false,"given":"Hailong","family":"Li","sequence":"additional","affiliation":[{"name":"Imaging Research Center, Department of Radiology, the Artificial Intelligence Imaging Research Center, Neurodevelopmental Disorders Prevention Center, Perinatal Institute, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1375-1247","authenticated-orcid":false,"given":"Nehal A.","family":"Parikh","sequence":"additional","affiliation":[{"name":"Neurodevelopmental Disorders Prevention Center, Perinatal Institute, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0124-0164","authenticated-orcid":false,"given":"Jonathan R.","family":"Dillman","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5246-6107","authenticated-orcid":false,"given":"Lili","family":"He","sequence":"additional","affiliation":[{"name":"Imaging Research Center, Department of Radiology, the Artificial Intelligence Imaging Research Center, Neurodevelopmental Disorders Prevention Center, Perinatal Institute, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2020","journal-title":"arXiv:2010.00747"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-022-00793-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00901"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210315"},{"key":"ref6","article-title":"Holistic evaluation of GPT-4V for biomedical imaging","author":"Liu","year":"2023","journal-title":"arXiv:2312.05256"},{"key":"ref7","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref8","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"arXiv:2102.05918"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3331841"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00633"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20614"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029181"},{"key":"ref13","article-title":"BLIP: Bootstrapping language\u2013image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"arXiv:2201.12086"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2024.100103"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.41435"},{"key":"ref21","article-title":"Foundational models in medical imaging: A comprehensive survey and future vision","author":"Azad","year":"2023","journal-title":"arXiv:2310.18689"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106791","article-title":"MedViT: A robust vision transformer for generalized medical image classification","volume":"157","author":"Manzari","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref23","article-title":"Adapting pre-trained vision transformers from 2D to 3D through weight inflation improves medical image segmentation","author":"Zhang","year":"2023","journal-title":"arXiv:2302.04303"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"ref25","article-title":"VirTex: Learning visual representations from textual annotations","author":"Desai","year":"2020","journal-title":"arXiv:2006.06666"},{"key":"ref26","article-title":"Flamingo: A visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"arXiv:2204.14198"},{"key":"ref27","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref29","article-title":"Multimodal few-shot learning with frozen language models","author":"Tsimpoukelli","year":"2021","journal-title":"arXiv:2106.13884"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-bioeng071516-044442"},{"key":"ref32","article-title":"Can we solve 3D vision tasks starting from a 2D vision transformer?","author":"Wang","year":"2022","journal-title":"arXiv:2209.07026"},{"key":"ref33","article-title":"Fine-tuned CLIP models are efficient video learners","author":"Rasheed","year":"2022","journal-title":"arXiv:2212.03640"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107685"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.53941\/ijndi0201006"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3308712"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_20"},{"key":"ref39","article-title":"Learning to encode position for transformer with continuous dynamical model","author":"Liu","year":"2020","journal-title":"arXiv:2003.09229"},{"key":"ref40","article-title":"Representation learning with contrastive predictive coding","author":"Van Den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref41","article-title":"Merlin: A vision language foundation model for 3D computed tomography","author":"Blankemeier","year":"2024","journal-title":"arXiv:2406.06512"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3319661"},{"key":"ref44","volume-title":"Cancer Moonshot Biobank---Colorectal Cancer Collection (CMB-CRC) (Version 8)","year":"2022"},{"key":"ref45","volume-title":"Cancer Moonshot Biobank---Lung Cancer Collection (CMB-LCA) (Version 9)","year":"2022"},{"key":"ref46","article-title":"MosMedData: Chest CT scans with COVID-19 related findings dataset","author":"Morozov","year":"2020","journal-title":"arXiv:2005.06465"},{"key":"ref47","article-title":"Duke spleen data set: A publicly available spleen MRI and CT dataset for training segmentation","author":"Wang","year":"2023","journal-title":"arXiv:2305.05732"},{"key":"ref48","volume-title":"Multi-Center Breast DCE-MRI Data and Segmentations from Patients in the I-SPY 1\/ACRIN 6657 Trials","author":"Newitt","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020190007"},{"key":"ref50","article-title":"FastMRI: An open dataset and benchmarks for accelerated MRI","author":"Zbontar","year":"2018","journal-title":"arXiv:1811.08839"},{"key":"ref51","article-title":"ds000102","author":"Kelly","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/s1470-2045(24)00220-1"},{"key":"ref53","volume-title":"Prostate MRI and Ultrasound With Pathology and Coordinates of Tracked Biopsy (Prostate-MRI-U.S.-Biopsy) (Version 2)","author":"Natarajan","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26582"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref56","volume-title":"UNIFESP X-Ray Body Part Classifier Competition","author":"Farina","year":"2022"},{"key":"ref57","volume-title":"The Clinical Proteomic Tumor Analysis Consortium Pancreatic Ductal Adenocarcinoma Collection (CPTAC-PDA) (Version 15)","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref60","volume-title":"Crystal Clean: Brain Tumors MRI Dataset","author":"Hashemi","year":"2023"},{"key":"ref61","volume-title":"IXI Dataset","author":"Group","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00900-3"},{"key":"ref63","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref64","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref66","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv:2002.05709"},{"key":"ref67","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11016939.pdf?arnumber=11016939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:39:26Z","timestamp":1759945166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11016939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":67,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3568036","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}