{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/large-scale-domain-specific-pretraining-for","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","arxiv_id":"2303.00915","date":"2023-03-02","proceeding":null,"authors":["Sheng Zhang","Yanbo Xu","Naoto Usuyama","Hanwen Xu","Jaspreet Bagga","Robert Tinn","Sam Preston","Rajesh Rao","Mu Wei","Naveen Valluri","Cliff Wong","Andrea Tupini","Yu Wang","Matt Mazzola","Swadheen Shukla","Lars Liden","Jianfeng Gao","Angela Crabtree","Brian Piening","Carlo Bifulco","Matthew P. Lungren","Tristan Naumann","Sheng Wang","Hoifung Poon"],"abstract":"Biomedical data is inherently multimodal, comprising physical measurements and natural language narratives. A generalist biomedical AI model needs to simultaneously process different modalities of data, including text and images. Therefore, training an effective generalist biomedical model requires high-quality multimodal data, such as parallel image-text pairs. Here, we present PMC-15M, a novel dataset that is two orders of magnitude larger than existing biomedical multimodal datasets such as MIMIC-CXR, and spans a diverse range of biomedical image types. PMC-15M contains 15 million biomedical image-text pairs collected from 4.4 million scientific articles. Based on PMC-15M, we have pretrained BiomedCLIP, a multimodal foundation model, with domain-specific adaptations tailored to biomedical vision-language processing. We conducted extensive experiments and ablation studies on standard biomedical imaging tasks from retrieval to classification to visual question-answering (VQA). BiomedCLIP achieved new state-of-the-art results in a wide range of standard datasets, substantially outperforming prior approaches. Intriguingly, by large-scale pretraining on diverse biomedical image types, BiomedCLIP even outperforms state-of-the-art radiology-specific models such as BioViL in radiology-specific tasks such as RSNA pneumonia detection. In summary, BiomedCLIP is a fully open-access foundation model that achieves state-of-the-art performance on various biomedical tasks, paving the way for transformative multimodal biomedical discovery and applications. We release our models at https://aka.ms/biomedclip to facilitate future research in multimodal biomedical AI.","url_abs":"https://arxiv.org/abs/2303.00915v3","url_pdf":"https://arxiv.org/pdf/2303.00915v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"large-scale-domain-specific-pretraining-for","repo_url":"https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"large-scale-domain-specific-pretraining-for","repo_url":"https://github.com/kaihe-better/llm-for-healthcare","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"large-scale-domain-specific-pretraining-for","repo_url":"https://github.com/lighterswang/biomedclip-lora","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"large-scale-domain-specific-pretraining-for","repo_url":"https://github.com/mbzuai-oryx/unimed-clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"large-scale-domain-specific-pretraining-for","repo_url":"https://github.com/xikai97/med-mim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"medical-visual-question-answering","task_name":"Medical Visual Question Answering"},{"task_slug":"pneumonia-detection","task_name":"Pneumonia Detection"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.00915","atlas_url":"https://app.syntology.ai/?focus=2303.00915","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}