{"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/biomedica-an-open-biomedical-image-caption","title":"BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature","arxiv_id":"2501.07171","date":"2025-01-13","proceeding":"CVPR 2025 1","authors":["Alejandro Lozano","Min Woo Sun","James Burgess","Liangyu Chen","Jeffrey J Nirschl","Jeffrey Gu","Ivan Lopez","Josiah Aklilu","Austin Wolfgang Katzer","Collin Chiu","Anita Rau","Xiaohan Wang","Yuhui Zhang","Alfred Seunghoon Song","Robert Tibshirani","Serena Yeung-Levy"],"abstract":"The development of vision-language models (VLMs) is driven by large-scale and diverse multimodal datasets. However, progress toward generalist biomedical VLMs is limited by the lack of annotated, publicly accessible datasets across biology and medicine. Existing efforts are restricted to narrow domains, missing the full diversity of biomedical knowledge encoded in scientific literature. To address this gap, we introduce BIOMEDICA, a scalable, open-source framework to extract, annotate, and serialize the entirety of the PubMed Central Open Access subset into an easy-to-use, publicly accessible dataset. Our framework produces a comprehensive archive with over 24 million unique image-text pairs from over 6 million articles. Metadata and expert-guided annotations are also provided. We demonstrate the utility and accessibility of our resource by releasing BMCA-CLIP, a suite of CLIP-style models continuously pre-trained on the BIOMEDICA dataset via streaming, eliminating the need to download 27 TB of data locally. On average, our models achieve state-of-the-art performance across 40 tasks - spanning pathology, radiology, ophthalmology, dermatology, surgery, molecular biology, parasitology, and cell biology - excelling in zero-shot classification with a 6.56% average improvement (as high as 29.8% and 17.5% in dermatology and ophthalmology, respectively), and stronger image-text retrieval, all while using 10x less compute. To foster reproducibility and collaboration, we release our codebase and dataset for the broader research community.","url_abs":"https://arxiv.org/abs/2501.07171v2","url_pdf":"https://arxiv.org/pdf/2501.07171v2.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":"biomedica-an-open-biomedical-image-caption","repo_url":"https://github.com/ale9806/open_clip_with_biomedica","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"biomedica-an-open-biomedical-image-caption","repo_url":"https://github.com/minwoosun/biomedica-etl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.07171","atlas_url":"https://app.syntology.ai/?focus=2501.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07171"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ale9806/open_clip_with_biomedica","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/minwoosun/biomedica-etl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":16,"unverified":4},"by_repo_kind":{"official":{"samples":20,"ran":16,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ff59295bb51c26d9","entry":"aggregate_publications_from_json","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/data_loaders/loader_utils.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/data_loaders/loader_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff59295bb51c26d9"}},{"code_sha256_prefix":"bcffe5ae51595c56","entry":"collect_tar_files","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/data_loaders/wd_loader.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/data_loaders/wd_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcffe5ae51595c56"}},{"code_sha256_prefix":"bbb9d8b536ae3d83","entry":"collect_tar_files_from_labels","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/data_loaders/wd_loader.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/data_loaders/wd_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bbb9d8b536ae3d83"}},{"code_sha256_prefix":"cb97752db69a8eba","entry":"compare_csv_row_counts","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/download_batch.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/download_batch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb97752db69a8eba"}},{"code_sha256_prefix":"d83d88e5f98e49d5","entry":"create_log_file_path","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/build_json.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/build_json.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d83d88e5f98e49d5"}},{"code_sha256_prefix":"ac1c2471664def4c","entry":"extract_features_from_dataloader","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/feature_extractors/extract_features.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/feature_extractors/extract_features.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac1c2471664def4c"}},{"code_sha256_prefix":"e0bc84a5913a68cd","entry":"extract_image_caption_pairs","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/data_loaders/loader_utils.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/data_loaders/loader_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0bc84a5913a68cd"}},{"code_sha256_prefix":"38a36c2da131f507","entry":"filter_no_caption_or_no_image","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/data_loaders/wd_loader.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/data_loaders/wd_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38a36c2da131f507"}},{"code_sha256_prefix":"42b8eab2675d547e","entry":"get_image_identifier","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/caption.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/caption.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42b8eab2675d547e"}},{"code_sha256_prefix":"7a900ce20281ac4b","entry":"get_image_paths","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/caption.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/caption.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a900ce20281ac4b"}},{"code_sha256_prefix":"544ccd5b57784198","entry":"get_kmeans","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/label_utils/models.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/label_utils/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"544ccd5b57784198"}},{"code_sha256_prefix":"2e665f86d4a45067","entry":"get_main_batch_index","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/download_batch.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/download_batch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e665f86d4a45067"}},{"code_sha256_prefix":"180bb7762557abf2","entry":"get_next_index","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/build_json.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/build_json.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"180bb7762557abf2"}},{"code_sha256_prefix":"b1a84bc8eee5b294","entry":"get_pca","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/label_utils/models.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/label_utils/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1a84bc8eee5b294"}},{"code_sha256_prefix":"cca1e5f8e9f7b0e0","entry":"load_and_process_media_filelist_csv","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/download.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/download.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cca1e5f8e9f7b0e0"}},{"code_sha256_prefix":"97c7f58efcfba433","entry":"read_json_file","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/data_loaders/loader_utils.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/data_loaders/loader_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97c7f58efcfba433"}},{"code_sha256_prefix":"7a342b3fd8f33439","entry":"download_media","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/download.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/download.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a342b3fd8f33439"}},{"code_sha256_prefix":"f2f23afd2de6f9dc","entry":"load_and_concatenate_subset","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/data_loaders/dino_features_loader.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/data_loaders/dino_features_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2f23afd2de6f9dc"}},{"code_sha256_prefix":"ae69a8e47ba31b5d","entry":"load_and_concatenate_subsets","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/data_loaders/dino_features_loader.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/data_loaders/dino_features_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae69a8e47ba31b5d"}},{"code_sha256_prefix":"1a9cc446f390c491","entry":"reconnect_ftp","repo":"minwoosun/biomedica-etl","repo_kind":"official","path":"src/pmc_oa/download.py","file_url":"https://github.com/minwoosun/biomedica-etl/blob/HEAD/src/pmc_oa/download.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a9cc446f390c491"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}