Papers › LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via...

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

20 Jun 2023NeurIPS 2023 11arXiv:2306.11925archive 2025-07-28

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

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.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

duyhominhnguyen/LVM-Med officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 4 ran (0 instrument-failed) · 9 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran
9unverified

Licence: 13 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from duyhominhnguyen/LVM-Med. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

duyhominhnguyen/LVM-Med official repository 13 samples, 4 ran (0 instrument-failed) · 9 unverified
AugmentedSegmentationDataset segmentation_2d/LVMMed_SAM_2d.py ran licence not identified · pointer only · 1640f7756e6b5338 · report fixture: returned AugmentedSegmentationDataset · level recorded 2026-09-22
ResizeLongestSide segmentation_2d/LVMMed_SAM_2d.py ran licence not identified · pointer only · 9263ddc9515cd3c4 · report fixture: returned ResizeLongestSide · level recorded 2026-09-22
SegmentationDataset segmentation_2d/LVMMed_SAM_2d.py ran licence not identified · pointer only · 6add128632e047e5 · report fixture: returned SegmentationDataset · level recorded 2026-09-22
get_bbox_from_mask in 5 papers segmentation_2d/LVMMed_SAM_2d.py ran · honoured contract fingerprinted licence not identified · pointer only · 4718de1f1b711ea6 · report fixture: signature mask:ndarray/2/int · returned ndarray · level recorded 2026-09-22
_build_sam segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · 427563d49b1f88e6 · report
build_sam_vit_b in 53 papers segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · 5bb7ac2f77d822c6 · report
build_sam_vit_h in 54 papers segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · 6437df869de8de01 · report
build_sam_vit_l in 53 papers segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · eaf0e28351ecdc2c · report
compute_dice_coefficient segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · b8f454a90cb08622 · report
eval_dice segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · 69289493b44ac63d · report
fit in 23 papers segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · 5da7a0e57d058010 · report
lvm_medsam_2d segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · 7322cdd668805472 · report
sam_dataloader segmentation_2d/LVMMed_SAM_2d.py unverified licence not identified · pointer only · 0f117394dc788ff6 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for LVM-Med (graph method: LVM-Med). 13 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. lvm_medsam_2d entry · level 0 · unverified · 7322cdd668805472
  2. eval_dice metric · level 0 · unverified · 69289493b44ac63d
  3. fit helper · level 0 · unverified · 5da7a0e57d058010
  4. sam_dataloader helper · level 0 · unverified · 0f117394dc788ff6
  5. ResizeLongestSide helper · level 1 · ran · 9263ddc9515cd3c4
  6. compute_dice_coefficient helper · level 0 · unverified · b8f454a90cb08622
  7. AugmentedSegmentationDataset helper · level 1 · ran · 1640f7756e6b5338
  8. SegmentationDataset helper · level 1 · ran · 6add128632e047e5
  9. get_bbox_from_mask helper · level 1 · ran · honoured contract · 4718de1f1b711ea6
  10. _build_sam helper · level 0 · unverified · 427563d49b1f88e6
  11. build_sam_vit_b helper · level 0 · unverified · 5bb7ac2f77d822c6
  12. build_sam_vit_h helper · level 0 · unverified · 6437df869de8de01
  13. build_sam_vit_l helper · level 0 · unverified · eaf0e28351ecdc2c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2306.11925") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Brain Tumor ClassificationContrastive LearningDiabetic Retinopathy GradingGraph MatchingObject Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections