Papers › nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation

nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation

15 Apr 2024arXiv:2404.09556archive 2025-07-28

Fabian Isensee, Tassilo Wald, Constantin Ulrich, Michael Baumgartner, Saikat Roy, Klaus Maier-Hein, Paul F. Jaeger

The release of nnU-Net marked a paradigm shift in 3D medical image segmentation, demonstrating that a properly configured U-Net architecture could still achieve state-of-the-art results. Despite this, the pursuit of novel architectures, and the respective claims of superior performance over the U-Net baseline, continued. In this study, we demonstrate that many of these recent claims fail to hold up when scrutinized for common validation shortcomings, such as the use of inadequate baselines, insufficient datasets, and neglected computational resources. By meticulously avoiding these pitfalls, we conduct a thorough and comprehensive benchmarking of current segmentation methods including CNN-based, Transformer-based, and Mamba-based approaches. In contrast to current beliefs, we find that the recipe for state-of-the-art performance is 1) employing CNN-based U-Net models, including ResNet and ConvNeXt variants, 2) using the nnU-Net framework, and 3) scaling models to modern hardware resources. These results indicate an ongoing innovation bias towards novel architectures in the field and underscore the need for more stringent validation standards in the quest for scientific progress.

PaperPDFCodeCode Syntology ran

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 7 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 4 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 between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

MIC-DKFZ/nnunet officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
DeepMicroscopy/nnUNet mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
tawald/nnunet mentioned on GitHubpytorchApache-2.0Syntology: not harvested 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

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
5ran

Licence: 2 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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.

MIC-DKFZ/nnunet official repository 3 samples, 3 ran (1 instrument-failed) · 0 unverified
comp_blosc2_params nnunetv2/training/dataloading/nnunet_dataset.py ran Apache-2.0 (permissive) · f8636c471203bf8b · report fixture: signature image_size:tuple/1/int, patch_size:tuple/1/int, bytes_per_pixel:int/0/int, max_block_nbytes:int/0/int, max_chunk_nbytes:int/0/int, max_chunk_to_patch_ratio_per_axis:float/0/float, grow_singleton_patch_axes:bool/0/bool · returned tuple · level recorded 2026-09-24
copy_files in 11 papers nnunetv2/dataset_conversion/Dataset027_ACDC.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 517ad51ee69e8a2d · report fixture: signature src_data_folder:PosixPath/0/?, train_dir:PosixPath/0/?, labels_dir:PosixPath/0/?, test_dir:PosixPath/0/? · returned int · level recorded 2026-09-25
merge in 85 papers nnunetv2/batch_running/generate_lsf_runs_customDecathlon.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 86ec2ccc2984b8bf · report fixture: signature dict1:dict/0/?, dict2:dict/0/? · returned dict · level recorded 2026-09-25
DeepMicroscopy/nnUNet community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
calculate_confusion_matrix in 5 papers nnunetv2/evaluation.py ran Apache-2.0 (permissive) · 58d38fedb5114f60 · report fixture: signature pred_mask:ndarray/1/int, true_mask:ndarray/1/int, num_classes:int/0/int · returned ndarray · level recorded 2026-09-24
convert_labels_back_to_BraTS in 11 papers nnunetv2/dataset_conversion/Dataset042_BraTS18.py ran · violated contract fingerprinted Apache-2.0 (permissive) · a2c8b38ba9393780 · report fixture: signature seg:ndarray/3/int · returned ndarray · level recorded 2026-09-25
mean_iou nnunetv2/evaluation.py ran Apache-2.0 (permissive) · 9235f33692fd804d · report fixture: signature true_masks_dir:str/0/str, pred_masks_dir:str/0/str, scanner:str/0/str, num_classes:int/0/int · returned float64 · level recorded 2026-09-24
mean_iou_from_confusion_matrix nnunetv2/evaluation.py ran Apache-2.0 (permissive) · 1ce6a0bc9d7ba540 · report fixture: signature confusion_matrix:ndarray/2/float, num_classes:int/0/int · returned float32 · level recorded 2026-09-24

Tasks

BenchmarkingImage SegmentationMambaMedical Image SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Average PoolingConcatenated Skip ConnectionConvNeXtConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUU-Net

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