{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:55:31Z","timestamp":1776275731010,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/jbhi.2025.3584802","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T13:45:31Z","timestamp":1751463931000},"page":"539-550","source":"Crossref","is-referenced-by-count":6,"title":["Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2268-2092","authenticated-orcid":false,"given":"Md Mamunur","family":"Rahaman","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ewan K. A.","family":"Millar","sequence":"additional","affiliation":[{"name":"Department of Anatomical Pathology, NSW Health Pathology, St. George Hospital, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8015-8358","authenticated-orcid":false,"given":"Erik","family":"Meijering","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.1405"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2020.2485"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635260"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2898044"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93000-8_88"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2019.00080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2022.07.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102264"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baac093"},{"key":"ref10","article-title":"Stain-invariant self supervised learning for histopathology image analysis","author":"Tiard","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102559"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102032"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2023.102534"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108827"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107070"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jare.2024.11.013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00915"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref23","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":"ref24","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"ref27","article-title":"Large-scale domain-specific pretraining for biomedical vision-language processing","author":"Zhang","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4"},{"key":"ref29","first-page":"154","article-title":"Visual classification via description from large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Menon","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"ref32","first-page":"28018","article-title":"Visual-text cross alignment: Refining the similarity score in vision-language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref35","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang","year":"2022"},{"key":"ref36","first-page":"2136","article-title":"TransMIL: Transformer based correlated multiple instance learning for whole slide image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shao","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3209652"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72086-4_14"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00923-0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.06.003"},{"key":"ref41","first-page":"2127","article-title":"Attention-based deep multiple instance learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ilse","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w"},{"key":"ref43","first-page":"20689","article-title":"Additive MIL: Intrinsically interpretable multiple instance learning for pathology","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Javed","year":"2022"},{"key":"ref44","first-page":"18009","article-title":"SCL-WC: Cross-slide contrastive learning for weakly-supervised whole-slide image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2022"},{"key":"ref45","first-page":"2023","article-title":"Exploring low-rank property in multiple instance learning for whole slide image classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiang"},{"key":"ref46","first-page":"2023","article-title":"Bayes-MIL: A new probabilistic perspective on attention-based multiple instance learning for whole slide images","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cui"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01824"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"ref49","first-page":"2022","article-title":"Masked autoencoders pre-training in multiple instance learning for whole slide image classification","volume-title":"Proc. Med. Imag. Deep Learn.","author":"An"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100198"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3056023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00069"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102743"},{"key":"ref54","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res"},{"key":"ref55","first-page":"37995","article-title":"Quilt-1 m: One million image-text pairs for histopathology","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ikezogwo","year":"2024"},{"key":"ref56","article-title":"100,000 histological images of human colorectal cancer and healthy tissue","author":"Kather","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102487"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref60","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref62","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01110"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1093"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105534"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103124"}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11338775\/11060654.pdf?arnumber=11060654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:30Z","timestamp":1768255350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11060654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":67,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3584802","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}