{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:36:17Z","timestamp":1782394577283,"version":"3.54.5"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Fundamental Research Funds for Central Universities"},{"name":"EPSRC DeepGeM","award":["EP\/W01842X\/1"],"award-info":[{"award-number":["EP\/W01842X\/1"]}]},{"DOI":"10.13039\/501100013342","name":"NIHR Imperial Biomedical Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013342","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tmi.2024.3449690","type":"journal-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T17:29:06Z","timestamp":1724693346000},"page":"519-529","source":"Crossref","is-referenced-by-count":14,"title":["IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-Training"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3738-7998","authenticated-orcid":false,"given":"Che","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Earth Science and Engineering and the Data Science Institute, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8707-2589","authenticated-orcid":false,"given":"Sibo","family":"Cheng","sequence":"additional","affiliation":[{"name":"CEREA, École des Ponts, Champs-sur-Marne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4933-0073","authenticated-orcid":false,"given":"Miaojing","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering and Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5257-520X","authenticated-orcid":false,"given":"Anand","family":"Shah","sequence":"additional","affiliation":[{"name":"Department of Infectious Disease Epidemiology, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2943-7698","authenticated-orcid":false,"given":"Wenjia","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Computing and the Department of Brain Science and the Data Science Institute, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9471-0585","authenticated-orcid":false,"given":"Rossella","family":"Arcucci","sequence":"additional","affiliation":[{"name":"Department of Earth Science and Engineering and the Data Science Institute, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"arXiv:2010.00747","author":"Zhang","year":"2020"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref4","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"arXiv:2210.06044","author":"Wang","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00376-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100134"},{"key":"ref7","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00273"},{"key":"ref9","article-title":"Benchmarking and boosting radiology report generation for 3D high-resolution medical images","volume-title":"arXiv:2406.07146","author":"Liu","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72120-5_12"},{"key":"ref11","article-title":"T3D: Towards 3D medical image understanding through vision-language pre-training","volume-title":"arXiv:2312.01529","author":"Liu","year":"2023"},{"key":"ref12","article-title":"Utilizing synthetic data for medical vision-language pre-training: Bypassing the need for real images","volume-title":"arXiv:2310.07027","author":"Liu","year":"2023"},{"key":"ref13","article-title":"G2D: From global to dense radiography representation learning via vision-language pre-training","volume-title":"arXiv:2312.01522","author":"Liu","year":"2023"},{"key":"ref14","first-page":"1","article-title":"Zero-shot ecg classification with multimodal learning and test-time clinical knowledge enhancement","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref15","article-title":"UniCLIP: Unified framework for contrastive language-image pre-training","volume-title":"arXiv:2209.13430","author":"Lee","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref18","first-page":"1","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref20","article-title":"Florence: A new foundation model for computer vision","volume-title":"arXiv:2111.11432","author":"Yuan","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref22","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref23","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","volume-title":"arXiv:2111.02114","author":"Schuhmann","year":"2021"},{"key":"ref24","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"arXiv:2210.08402","author":"Schuhmann","year":"2022"},{"key":"ref25","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","volume-title":"arXiv:2208.10442","author":"Wang","year":"2022"},{"key":"ref26","article-title":"Stare at what you see: Masked image modeling without reconstruction","volume-title":"arXiv:2211.08887","author":"Xue","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref28","article-title":"PyramidCLIP: Hierarchical feature alignment for vision-language model pretraining","volume-title":"arXiv:2204.14095","author":"Gao","year":"2022"},{"key":"ref29","article-title":"Exploring image augmentations for Siamese representation learning with chest X-Rays","volume-title":"arXiv:2301.12636","author":"van der Sluijs","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78191-0_51"},{"key":"ref31","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume-title":"arXiv:2206.08155","author":"Yang","year":"2022"},{"key":"ref32","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"arXiv:2301.12597","author":"Li","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447326"},{"key":"ref34","first-page":"11","article-title":"Medklip: Medical knowledge enhanced language-image pre-training","volume":"1","author":"Wu","year":"2023","journal-title":"MedRxiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref36","article-title":"Med-UniC: Unifying cross-lingual medical vision-language pre-training by diminishing bias","volume-title":"arXiv:2305.19894","author":"Wan","year":"2023"},{"key":"ref37","first-page":"1","article-title":"Advancing radiograph representation learning with masked record modeling","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","article-title":"Publicly available clinical BERT embeddings","volume-title":"arXiv:1904.03323","author":"Alsentzer","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"11","key":"ref41","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Probab.","volume":"1","author":"MacQueen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"1","key":"ref44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"ref45","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"arXiv:2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref46","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","volume-title":"arXiv:1901.07042","author":"Johnson","year":"2019"},{"key":"ref47","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"arXiv:1608.03983","author":"Loshchilov","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76550-z"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref52","article-title":"SIIM-ACR pneumothorax segmentation","author":"Steven","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"},{"key":"ref55","volume-title":"Object-cxr-automatic detection of foreign objects on chest x-rays","author":"Healthcare","year":"2020"},{"key":"ref56","article-title":"YOLOv3: An incremental improvement","volume-title":"arXiv:1804.02767","author":"Redmon","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref59","article-title":"ClinicalBERT: Modeling clinical notes and predicting hospital readmission","volume-title":"arXiv:1904.05342","author":"Huang","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-022-00714-8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00536-x"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/10820125\/10646593.pdf?arnumber=10646593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T05:24:27Z","timestamp":1735881867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10646593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2024.3449690","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}