Papers › UniverSeg: Universal Medical Image Segmentation

UniverSeg: Universal Medical Image Segmentation

12 Apr 2023ICCV 2023 1arXiv:2304.06131archive 2025-07-28

Victor Ion Butoi, Jose Javier Gonzalez Ortiz, Tianyu Ma, Mert R. Sabuncu, John Guttag, Adrian V. Dalca

While deep learning models have become the predominant method for medical image segmentation, they are typically not capable of generalizing to unseen segmentation tasks involving new anatomies, image modalities, or labels. Given a new segmentation task, researchers generally have to train or fine-tune models, which is time-consuming and poses a substantial barrier for clinical researchers, who often lack the resources and expertise to train neural networks. We present UniverSeg, a method for solving unseen medical segmentation tasks without additional training. Given a query image and example set of image-label pairs that define a new segmentation task, UniverSeg employs a new Cross-Block mechanism to produce accurate segmentation maps without the need for additional training. To achieve generalization to new tasks, we have gathered and standardized a collection of 53 open-access medical segmentation datasets with over 22,000 scans, which we refer to as MegaMedical. We used this collection to train UniverSeg on a diverse set of anatomies and imaging modalities. We demonstrate that UniverSeg substantially outperforms several related methods on unseen tasks, and thoroughly analyze and draw insights about important aspects of the proposed system. The UniverSeg source code and model weights are freely available at https://universeg.csail.mit.edu

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 16 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 6 ran (3 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 2 ran (2 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.

JJGO/UniverSeg officialmentioned on GitHubpytorchSyntology: 14 samples, 6 ran (3 instrument-failed) · 8 unverified report
deel-ai-papers/consema mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 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

16 samples harvested: 8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 8 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.

2ran · honoured contract
3ran · our draft was wrong
3ran
8unverified

Licence: 2 of the 16 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

JJGO/UniverSeg official repository 14 samples, 6 ran (3 instrument-failed) · 8 unverified
CrossConv2d universeg/model.py ran Apache-2.0 (permissive) · 9994802f43d8b159 · report fixture: returned CrossConv2d · level recorded 2026-09-22
Vmap universeg/model.py ran Apache-2.0 (permissive) · 7daac70e030811f7 · report fixture: returned Vmap · level recorded 2026-09-22
as_2tuple universeg/model.py ran · honoured contract Apache-2.0 (permissive) · 142578030862b078 · report fixture: returned tuple · level recorded 2026-09-22
get_nonlinearity universeg/model.py ran · our draft was wrong Apache-2.0 (permissive) · 1617355e53350393 · report fixture: returned ReLU · level recorded 2026-09-22
validate_arguments_init universeg/model.py ran · our draft was wrong Apache-2.0 (permissive) · e61d58ef89523382 · report fixture: returned type · level recorded 2026-09-22
vmap universeg/model.py ran · our draft was wrong Apache-2.0 (permissive) · 290578cdad9c6a53 · report fixture: returned Tensor · level recorded 2026-09-22
ConvOp universeg/model.py unverified Apache-2.0 (permissive) · adf8d27021bbab9c · report
CrossBlock universeg/model.py unverified Apache-2.0 (permissive) · 616bb64d3505047c · report
CrossOp universeg/model.py unverified Apache-2.0 (permissive) · 02274408c04c614d · report
UniverSeg universeg/model.py unverified Apache-2.0 (permissive) · d931621ba7ba79fc · report
initialize_bias universeg/model.py unverified Apache-2.0 (permissive) · 874ef3743327a7df · report
initialize_layer universeg/model.py unverified Apache-2.0 (permissive) · d3e23d20c761e266 · report
initialize_weight universeg/model.py unverified Apache-2.0 (permissive) · 99341f22e98fdf80 · report
reset_conv2d_parameters universeg/model.py unverified Apache-2.0 (permissive) · a55e933baa469a5c · report
deel-ai-papers/consema community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
UniversegInferenceWrap src/benchmarkerie/models.py ran licence not identified · pointer only · fc48c1f3df993437 · report fixture: returned UniversegInferenceWrap · level recorded 2026-09-22
dice_score in 10 papers src/benchmarkerie/models.py ran · honoured contract fingerprinted licence not identified · pointer only · da563328802c0ab5 · report fixture: signature y_pred:Tensor/2/int, y_true:Tensor/2/int · returned float · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for UniverSeg (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for UniverSeg (graph method: UniverSeg). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. UniversegInferenceWrap entry · level 1 · ran · fc48c1f3df993437
  2. dice_score metric · level 1 · ran · honoured contract · da563328802c0ab5

harvested Assembly for UniverSeg (graph method: UniverSeg). 14 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. UniverSeg entry · level 0 · unverified · d931621ba7ba79fc
  2. ConvOp model · level 0 · unverified · adf8d27021bbab9c
  3. CrossBlock model · level 0 · unverified · 616bb64d3505047c
  4. as_2tuple helper · level 1 · ran · honoured contract · 142578030862b078
  5. validate_arguments_init helper · level 1 · ran · our draft was wrong · e61d58ef89523382
  6. vmap helper · level 1 · ran · our draft was wrong · 290578cdad9c6a53
  7. get_nonlinearity helper · level 1 · ran · our draft was wrong · 1617355e53350393
  8. reset_conv2d_parameters helper · level 0 · unverified · a55e933baa469a5c
  9. CrossOp model · level 0 · unverified · 02274408c04c614d
  10. Vmap helper · level 1 · ran · 7daac70e030811f7
  11. initialize_layer helper · level 0 · unverified · d3e23d20c761e266
  12. CrossConv2d model · level 1 · ran · 9994802f43d8b159
  13. initialize_bias helper · level 0 · unverified · 874ef3743327a7df
  14. initialize_weight helper · level 0 · unverified · 99341f22e98fdf80

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="2304.06131") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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