{"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/lvm-med-learning-large-scale-self-supervised-1","title":"LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching","arxiv_id":"2306.11925","date":"2023-06-20","proceeding":"NeurIPS 2023 11","authors":["Duy M. H. Nguyen","Hoang Nguyen","Nghiem T. Diep","Tan N. Pham","Tri Cao","Binh T. Nguyen","Paul Swoboda","Nhat Ho","Shadi Albarqouni","Pengtao Xie","Daniel Sonntag","Mathias Niepert"],"abstract":"Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge for medical imaging data. While pre-trained deep networks on ImageNet and vision-language foundation models trained on web-scale data are prevailing approaches, their effectiveness on medical tasks is limited due to the significant domain shift between natural and medical images. To bridge this gap, we introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets, covering a large number of organs and modalities such as CT, MRI, X-ray, and Ultrasound. We benchmark several state-of-the-art self-supervised algorithms on this dataset and propose a novel self-supervised contrastive learning algorithm using a graph-matching formulation. The proposed approach makes three contributions: (i) it integrates prior pair-wise image similarity metrics based on local and global information; (ii) it captures the structural constraints of feature embeddings through a loss function constructed via a combinatorial graph-matching objective; and (iii) it can be trained efficiently end-to-end using modern gradient-estimation techniques for black-box solvers. We thoroughly evaluate the proposed LVM-Med on 15 downstream medical tasks ranging from segmentation and classification to object detection, and both for the in and out-of-distribution settings. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models. For challenging tasks such as Brain Tumor Classification or Diabetic Retinopathy Grading, LVM-Med improves previous vision-language models trained on 1 billion masks by 6-7% while using only a ResNet-50.","url_abs":"https://arxiv.org/abs/2306.11925v3","url_pdf":"https://arxiv.org/pdf/2306.11925v3.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":"lvm-med-learning-large-scale-self-supervised-1","repo_url":"https://github.com/duyhominhnguyen/LVM-Med","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"brain-tumor-classification","task_name":"Brain Tumor Classification"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"diabetic-retinopathy-grading","task_name":"Diabetic Retinopathy Grading"},{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.11925","atlas_url":"https://app.syntology.ai/?focus=2306.11925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11925"}},"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":"deterministic:regex_extraction","url":"https://github.com/duyhominhnguyen/LVM-Med","reach":null}],"summary":{"ran":3,"ran_honours":1,"unverified":9},"by_repo_kind":{"official":{"samples":13,"ran":4,"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":13,"samples":[{"code_sha256_prefix":"1640f7756e6b5338","entry":"AugmentedSegmentationDataset","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1640f7756e6b5338"}},{"code_sha256_prefix":"9263ddc9515cd3c4","entry":"ResizeLongestSide","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9263ddc9515cd3c4"}},{"code_sha256_prefix":"6add128632e047e5","entry":"SegmentationDataset","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6add128632e047e5"}},{"code_sha256_prefix":"4718de1f1b711ea6","entry":"get_bbox_from_mask","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4718de1f1b711ea6"}},{"code_sha256_prefix":"427563d49b1f88e6","entry":"_build_sam","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"427563d49b1f88e6"}},{"code_sha256_prefix":"5bb7ac2f77d822c6","entry":"build_sam_vit_b","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5bb7ac2f77d822c6"}},{"code_sha256_prefix":"6437df869de8de01","entry":"build_sam_vit_h","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6437df869de8de01"}},{"code_sha256_prefix":"eaf0e28351ecdc2c","entry":"build_sam_vit_l","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"eaf0e28351ecdc2c"}},{"code_sha256_prefix":"b8f454a90cb08622","entry":"compute_dice_coefficient","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b8f454a90cb08622"}},{"code_sha256_prefix":"69289493b44ac63d","entry":"eval_dice","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"69289493b44ac63d"}},{"code_sha256_prefix":"5da7a0e57d058010","entry":"fit","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5da7a0e57d058010"}},{"code_sha256_prefix":"7322cdd668805472","entry":"lvm_medsam_2d","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7322cdd668805472"}},{"code_sha256_prefix":"0f117394dc788ff6","entry":"sam_dataloader","repo":"duyhominhnguyen/LVM-Med","repo_kind":"official","path":"segmentation_2d/LVMMed_SAM_2d.py","file_url":"https://github.com/duyhominhnguyen/LVM-Med/blob/HEAD/segmentation_2d/LVMMed_SAM_2d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0f117394dc788ff6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}