SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.02284 · 2022

Nuclei instance segmentation and classification in histopathology images with StarDist

arXiv · PDF · Open in the Atlas

Code that ran

6 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 2 failures of our instrument; 9 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2203.02284.json · badge: /api/ran/2203.02284.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
stardist/stardist canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
mpicbg-csbd/stardist community (classifier label)
classifier basis not recorded on the link
5 ran · 8 no recorded run
FunctionStatusWhere it lives
dist_to_coord Ran
ran on a synthesized input
mpicbg-csbd/stardist/stardist/geometry/geom2d.py
code served (permissive licence) · get_code("cf3a9d8cf1cd5b76")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family float, shape (2, 2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Construct arguments for dist_to_coord function
n_polys = 2
n_rays = 4

# dist: shape (n_polys, n_rays) - distances from center points
dist = np.random.rand(n_polys, n_rays).astype(np.float32) * 10

# points: shape (n_polys, 2) - center points in cartesian coordinates
points = np.array([[5.0, 3.0], [2.0, 7.0]], dtype=np.float32)

# scale_dist: tuple of length 2 - scaling factors for x and y
scale_dist = (1.5, 2.0)

ARGS = {
    "dist": dist,
    "points": points,
    "scale_dist": scale_dist,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 2, 4) — shape (2, 2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
fill_label_holes Ran
ran on a synthesized input
mpicbg-csbd/stardist/stardist/utils.py
code served (permissive licence) · get_code("c71674a5afd79e55")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (5, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from scipy.ndimage import distance_transform_edt, binary_fill_holes
from scipy.ndimage import find_objects

# Create a simple label image with some holes
# This will be a 2D array with labeled regions
lbl_img = np.array([
    [0, 1, 1, 1, 0],
    [1, 1, 0, 1, 1],
    [1, 0, 0, 0, 1],
    [1, 1, 0, 1, 1],
    [0, 1, 1, 1, 0]
], dtype=np.int32)

ARGS = {
    'lbl_img': lbl_img,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (5, 5) — shape (5, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_array_of_integers Ran
ran on a synthesized input
mpicbg-csbd/stardist/stardist/matching.py
code served (permissive licence) · get_code("d1f03663983cd95f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Test case 1: Valid numpy array of integers
y_valid_int = np.array([1, 2, 3, 4, 5], dtype=np.int32)

# Test case 2: Valid numpy array of integers (different dtype)
y_valid_int64 = np.array([10, 20, 30], dtype=np.int64)

# Test case 3: Numpy array of floats (should return False)
y_float = np.array([1.0, 2.0, 3.0], dtype=np.float32)

# Test case 4: Not a numpy array (should return False)
y_list = [1, 2, 3]

# Test case 5: Not a numpy array - Python int
y_int = 5

ARGS = {
    "y": y_valid_int
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
label_are_sequential Ran
ran on a synthesized input
mpicbg-csbd/stardist/stardist/matching.py
code served (permissive licence) · get_code("7bbadcb4ea3c41c3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

def label_are_sequential(y):
    """ returns true if y has only sequential labels from 1... """
    labels = np.unique(y)
    return set(labels) - {0} == set(range(1, 1 + labels.max()))

# Test case 1: Sequential labels from 1 to 3 (should return True)
y_sequential = np.array([0, 1, 2, 3, 1, 2, 0, 3])

ARGS = {
    "y": y_sequential
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
path_absolute Ran
ran; our contract draft was wrong, not the code
mpicbg-csbd/stardist/stardist/utils.py
code served (permissive licence) · get_code("be509cf705126aab")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os

def path_absolute(path_relative):
    """ Get absolute path to resource"""
    base_path = os.path.abspath(os.path.dirname(__file__))
    return os.path.join(base_path, path_relative)

ARGS = {
    "path_relative": "data/config.json"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
random_label_cmap Ran
ran; our contract draft was wrong, not the code
stardist/stardist/stardist/plot/plot.py
code served (permissive licence) · get_code("78a539521e49ce67")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned ListedColormap. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import matplotlib.colors

ARGS = {
    "n": 256,
    "h": (0.0, 1.0),
    "l": (0.4, 1.0),
    "s": (0.2, 0.8),
    "seed": 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ListedColormap — a ListedColormap output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ListedColormap output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
draw_polygons Not yet run
unverified (harvested, no recorded run)
stardist/stardist/stardist/plot/plot.py
code served (permissive licence) · get_code("ea01a227751d9661")
How it ran

no invocation recorded.

edt_prob Not yet run
unverified (harvested, no recorded run)
mpicbg-csbd/stardist/stardist/utils.py
code served (permissive licence) · get_code("f31dcb2dcd038f21")
How it ran

no invocation recorded.

non_maximum_suppression Not yet run
unverified (harvested, no recorded run)
mpicbg-csbd/stardist/stardist/nms.py
code served (permissive licence) · get_code("e2dcd6ed644b4198")
How it ran

no invocation recorded.

non_maximum_suppression_inds Not yet run
unverified (harvested, no recorded run)
mpicbg-csbd/stardist/stardist/nms.py
code served (permissive licence) · get_code("8237fa3b96720d36")
How it ran

no invocation recorded.

non_maximum_suppression_sparse Not yet run
unverified (harvested, no recorded run)
mpicbg-csbd/stardist/stardist/nms.py
code served (permissive licence) · get_code("d65ff3a37c542e41")
How it ran

no invocation recorded.

polygons_to_label_coord Not yet run
unverified (harvested, no recorded run)
mpicbg-csbd/stardist/stardist/geometry/geom2d.py
code served (permissive licence) · get_code("4cba6d519a0927db")
How it ran

no invocation recorded.

polyhedron_to_label Not yet run
unverified (harvested, no recorded run)
mpicbg-csbd/stardist/stardist/geometry/geom3d.py
code served (permissive licence) · get_code("30cf36f602ed77e1")
How it ran

no invocation recorded.

rays_from_json Not yet run
unverified (harvested, no recorded run)
mpicbg-csbd/stardist/stardist/rays3d.py
code served (permissive licence) · get_code("f7197778e73bf45b")
How it ran

no invocation recorded.

reorder_faces Not yet run
unverified (harvested, no recorded run)
mpicbg-csbd/stardist/stardist/rays3d.py
code served (permissive licence) · get_code("cdaf70ead486e3e7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
dist_to_coord 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
draw_polygons 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
edt_prob 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
is_array_of_integers 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
label_are_sequential 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
non_maximum_suppression 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
non_maximum_suppression_inds 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
non_maximum_suppression_sparse 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
path_absolute 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
polygons_to_label_coord 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
random_label_cmap 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
rays_from_json 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons
reorder_faces 1 other paper
1 dated earlier
1806.03535 (2018-06)
Cell Detection with Star-convex Polygons

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Instance segmentation and classification of nuclei is an important task in computational pathology. We show that StarDist, a deep learning nuclei segmentation method originally developed for fluorescence microscopy, can be extended and successfully applied to histopathology images. This is substantiated by conducting experiments on the Lizard dataset, and through entering the Colon Nuclei Identification and Counting (CoNIC) challenge 2022, where our approach achieved the first spot on the leaderboard for the segmentation and classification task for both the preliminary and final test phase.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.02284")
get_code_for_paper("2203.02284")
have("2203.02284")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.02284.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.02284.svg)](https://syntology.ai/paper/2203.02284)

Connect an agent — have() is free.