Papers › PanNuke Dataset Extension, Insights and Baselines

PanNuke Dataset Extension, Insights and Baselines

24 Mar 2020arXiv:2003.10778archive 2025-07-28

Jevgenij Gamper, Navid Alemi Koohbanani, Ksenija Benes, Simon Graham, Mostafa Jahanifar, Syed Ali Khurram, Ayesha Azam, Katherine Hewitt, Nasir Rajpoot

The emerging area of computational pathology (CPath) is ripe ground for the application of deep learning (DL) methods to healthcare due to the sheer volume of raw pixel data in whole-slide images (WSIs) of cancerous tissue slides. However, it is imperative for the DL algorithms relying on nuclei-level details to be able to cope with data from `the clinical wild', which tends to be quite challenging. We study, and extend recently released PanNuke dataset consisting of ~200,000 nuclei categorized into 5 clinically important classes for the challenging tasks of segmenting and classifying nuclei in WSIs. Previous pan-cancer datasets consisted of only up to 9 different tissues and up to 21,000 unlabeled nuclei and just over 24,000 labeled nuclei with segmentation masks. PanNuke consists of 19 different tissue types that have been semi-automatically annotated and quality controlled by clinical pathologists, leading to a dataset with statistics similar to the clinical wild and with minimal selection bias. We study the performance of segmentation and classification models when applied to the proposed dataset and demonstrate the application of models trained on PanNuke to whole-slide images. We provide comprehensive statistics about the dataset and outline recommendations and research directions to address the limitations of existing DL tools when applied to real-world CPath applications.

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

The archive's official repository (TIA-Lab/PanNuke-metrics) was not harvested; the 39 samples below come from 3 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 40 code samples: 39 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 40: 35 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 1 violated, 31 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 39 samples from 3 repositories, 34 ran (32 with no instrument failure; 2 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

TIA-Lab/PanNuke-metrics officialmentioned in paperSyntology: not harvested report
aaparna/UNet-Image-Segmentation mentioned on GitHubSyntology: not harvested report
alexjfoote/reetoolbox mentioned on GitHubpytorchApache-2.0Syntology: 11 samples, 10 ran (0 instrument-failed) · 1 unverified report
kaiseem/pointnu-net mentioned on GitHubpytorchMITSyntology: 15 samples, 13 ran (2 instrument-failed) · 2 unverified report
lhaof/cgt mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Cell Graph Transformer for Nuclei Classification (arXiv:2402.12946; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
okunator/Dippa mentioned on GitHubpytorchMITSyntology: 13 samples, 11 ran (0 instrument-failed) · 2 unverified report
vqdang/hover_net mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

40 samples harvested: 35 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 1 violated, 31 with no contract checked; 3 where Syntology's instrument failed) · 5 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 · violated contract
1ran · our draft was wrong
2ran; the contract check could not run
31ran
5unverified

Licence: 1 of the 40 samples is 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 3 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. 1 sample is listed last, in a group without a repository. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

alexjfoote/reetoolbox community (archive-listed) 11 samples, 10 ran (0 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
reetoolbox/metrics.py ran Apache-2.0 (permissive) · 504d09c7575c571d · report fixture: signature results:dict/0/? · returned float · level recorded 2026-09-24
adversarial_accuracy reetoolbox/metrics.py ran Apache-2.0 (permissive) · f2adf71dc1102ec8 · report fixture: signature results:dict/0/? · returned float · level recorded 2026-09-24
apply_transforms reetoolbox/trainer.py ran Apache-2.0 (permissive) · e45684da05f7df4a · report fixture: signature model:callable/0/?, inputs:Tensor/2/float, labels:Tensor/1/int, adv_optimisers:list/1/SimpleAdvOptimizer, k:int/0/int, reset_weights:bool/0/bool · returned Tensor · level recorded 2026-09-24
get_dataloader in 111 papers reetoolbox/utils.py ran Apache-2.0 (permissive) · 8fa7bbbf062a1aad · report fixture: signature dataset:MinimalDataset/0/?, n:int/0/int, batch_size:int/0/int, num_workers:int/0/int, shuffle:bool/0/bool · returned DataLoader · level recorded 2026-09-24
label_patch reetoolbox/utils.py ran Apache-2.0 (permissive) · 9b00b93154e766c2 · report fixture: signature patch:Tensor/2/float, count:list/1/int · returned tuple · level recorded 2026-09-24
load_resnet reetoolbox/utils.py ran Apache-2.0 (permissive) · e7a3997691bd97d3 · report fixture: signature model_path:str/0/str, n_classes:int/0/int, hidden_size:int/0/int, pretrained:bool/0/bool, device:str/0/str · returned ResNet · level recorded 2026-09-24
rmse in 44 papers reetoolbox/metrics.py ran fingerprinted Apache-2.0 (permissive) · 30f91c811cbc554f · report fixture: signature a:Tensor/2/float · returned Tensor · level recorded 2026-09-24
run_val reetoolbox/trainer.py ran Apache-2.0 (permissive) · db1bae643c60dd31 · report fixture: signature model:callable/0/?, loader:list/1/tuple, criterion:callable/0/?, device:str/0/str · returned tuple · level recorded 2026-09-24
training_bout reetoolbox/trainer.py ran Apache-2.0 (permissive) · d6bd6ff6fe6aad52 · report fixture: signature model:callable/0/?, train_loader:list/1/tuple, val_loader:list/1/tuple, optimizer:SGD/0/?, criterion:callable/0/?, adversarial:bool/0/bool, attacks:list/1/empty, epochs:int/0/int, m:int/0/int, last_n:int/0/int, k:int/0/int, device:str/0/str · returned tuple · level recorded 2026-09-24
untargeted_loss reetoolbox/optimisers.py ran Apache-2.0 (permissive) · 432e211219845a2b · report fixture: signature outputs:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-24
targeted_loss reetoolbox/optimisers.py unverified Apache-2.0 (permissive) · 21780435c6ca1913 · report
kaiseem/pointnu-net community (archive-listed) 15 samples, 13 ran (2 instrument-failed) · 2 unverified
binary_focal_loss losses/focal_loss.py ran MIT (permissive) · 241b293cb3a3c43d · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, alpha:float/0/float, gamma:float/0/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-24
check_sha1 models/download.py ran MIT (permissive) · 484859bf41155745 · report fixture: signature filename:str/0/str, sha1_hash:str/0/str · returned bool · level recorded 2026-09-24
compute_edts_forPenalizedLoss losses/dice_loss.py ran MIT (permissive) · b53ea61df431b694 · report fixture: signature GT:ndarray/4/bool · returned ndarray · level recorded 2026-09-24
get_model_file in 15 papers models/model_store.py ran MIT (permissive) · 4bf53b623193a6f7 · report fixture: signature name:str/0/str, root:str/0/str · returned str · level recorded 2026-09-24
get_resnet_file models/model_store.py ran MIT (permissive) · 420ae9a3239bb203 · report fixture: returned str · level recorded 2026-09-24
iou in 97 papers
census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 3 of 5, arg 1: rank 2, kind int, dtype int64 · arg 2: rank 2, kind int, dtype int64
losses/lovasz_losses.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d94639b28b2134ff · report fixture: signature preds:ndarray/2/int, labels:ndarray/2/int, C:int/0/int, EMPTY:float/0/float, ignore:NoneType/0/?, per_image:bool/0/bool · returned ndarray · level recorded 2026-09-22
iou_binary in 27 papers losses/lovasz_losses.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 1211530cd527bd0b · report fixture: signature preds:ndarray/3/int, labels:ndarray/3/int, EMPTY:float/0/float, ignore:int/0/int, per_image:bool/0/bool · returned float · level recorded 2026-09-22
lovasz_grad in 42 papers losses/lovasz_losses.py ran · violated contract fingerprinted MIT (permissive) · e85b5d21dc5b8382 · report fixture: signature gt_sorted:Tensor/1/int · returned Tensor · level recorded 2026-09-22
make_one_hot in 15 papers losses/dice_loss.py ran MIT (permissive) · f93cd0d2bb2e4795 · report fixture: signature input:Tensor/4/int, num_classes:int/0/int · returned Tensor · level recorded 2026-09-24
reduce_loss in 75 papers losses/generalise_focal_loss.py ran MIT (permissive) · 93358ba7aa223343 · report fixture: signature loss:Tensor/2/float, reduction:str/0/str · returned Tensor · level recorded 2026-09-25
short_hash in 15 papers models/model_store.py ran MIT (permissive) · 77bc65d2018e9d9e · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-24
stack_prediction infer_pannuke.py ran MIT (permissive) · 274a4c2795ca8dd4 · report fixture: signature seg_masks:list/1/ndarray, cate_labels:list/1/int · returned ndarray · level recorded 2026-09-24
weight_reduce_loss in 61 papers losses/generalise_focal_loss.py ran MIT (permissive) · 8553862254d49840 · report fixture: signature loss:Tensor/2/float, weight:Tensor/2/float, reduction:str/0/str, avg_factor:NoneType/0/? · returned Tensor · level recorded 2026-09-25
download in 53 papers models/download.py unverified MIT (permissive) · 8faa1b60508d7b44 · report
quality_focal_loss losses/generalise_focal_loss.py unverified MIT (permissive) · e5457e2f64864dd0 · report
okunator/Dippa community (archive-listed) 13 samples, 11 ran (0 instrument-failed) · 2 unverified
AJI src/metrics/metrics.py ran fingerprinted MIT (permissive) · 70dfe5fac9f92989 · report fixture: signature true:ndarray/2/int, pred:ndarray/2/int · returned float64 · level recorded 2026-09-24
AJI_plus src/metrics/metrics.py ran MIT (permissive) · 0ec0f8e9ea494c64 · report fixture: signature true:ndarray/2/int, pred:ndarray/2/int · returned float64 · level recorded 2026-09-24
DICE2 src/metrics/metrics.py ran fingerprinted MIT (permissive) · 1942c4a97287927f · report fixture: signature true:ndarray/2/int, pred:ndarray/2/int · returned float64 · level recorded 2026-09-24
binarize in 22 papers src/utils/mask_utils.py ran fingerprinted MIT (permissive) · df537567c64fea4a · report fixture: signature inst_map:ndarray/2/int · returned ndarray · level recorded 2026-09-24
draw_stuff_contours src/utils/viz_utils.py ran MIT (permissive) · 42361797de298480 · report fixture: signature inst_map:ndarray/2/int, image:ndarray/3/int, type_map:ndarray/2/int, classes:dict/0/?, fill_contours:bool/0/bool, thickness:int/0/int · returned ndarray · level recorded 2026-09-24
fix_duplicates src/utils/mask_utils.py ran fingerprinted MIT (permissive) · b8109b79acc64068 · report fixture: signature inst_map:ndarray/2/int · returned ndarray · level recorded 2026-09-24
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
src/utils/img_utils.py ran MIT (permissive) · 247e39ae4944e031 · report fixture: signature img:ndarray/3/float, channels:str/0/str, standardize:bool/0/bool · returned ndarray · level recorded 2026-09-24
percentile_normalize src/utils/img_utils.py ran MIT (permissive) · dc269540663f3fb7 · report fixture: signature img:ndarray/3/float, channels:str/0/str · returned ndarray · level recorded 2026-09-24
percentile_normalize_and_clamp src/utils/img_utils.py ran MIT (permissive) · 12218d17d813eb74 · report fixture: signature im:ndarray/3/float, a_min:int/0/int, a_max:int/0/int · returned ndarray · level recorded 2026-09-24
poly2mask src/utils/save_utils.py ran MIT (permissive) · ac05aad67c119188 · report fixture: signature contour:ndarray/2/float, shape:tuple/1/int, x_off:int/0/int, y_off:int/0/int · returned ndarray · level recorded 2026-09-24
remove_small_objects src/utils/mask_utils.py ran MIT (permissive) · 15b380d239dc63a4 · report fixture: signature ar:ndarray/2/bool, min_size:int/0/int, connectivity:int/0/int, in_place:bool/0/bool, out:NoneType/0/? · returned ndarray · level recorded 2026-09-24
draw_thing_contours src/utils/viz_utils.py unverified MIT (permissive) · 5c30f53f7cde0bda · report
viz_patches src/patching/viz_patches.py unverified MIT (permissive) · 86befdff7aeeaec4 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
numericalSort repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · d39d1cd46009e948 · report fixture: signature value:str/0/str · returned list · level recorded 2026-09-22

Tasks

Selection biaswhole slide images

Datasets

Introduced by this paper, per the archive.

PanNuke

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