SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.01373 · 2019

Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 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 7 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/1908.01373.json · badge: /api/ran/1908.01373.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
shirgur/UMIS canonical (classifier label)
classifier basis: census
10 ran · 0 no recorded run
FunctionStatusWhere it lives
batch_pix_accuracy Ran
ran on a synthesized input
shirgur/UMIS/utils/metrices.py
code served (permissive licence) · get_code("ba849ba09bf7d085")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch
import numpy as np

torch.manual_seed(0)

# Create small binary prediction tensor (batch_size=2, spatial_dims=4x3)
# Values between 0 and 1 to test thresholding
predict = torch.rand(2, 4, 3)

# Create small target tensor with values that will become > 0 after +1
# Using values in range [-1, 1] so after +1 they're in [0, 2]
target = torch.randint(-1, 2, (2, 4, 3)).float()

# Threshold for thresholding operation
thr = 0.9

ARGS = {
    'predict': predict,
    'target': target,
    'thr': thr
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
conv3x3x3 Ran
ran; our contract draft was wrong, not the code
shirgur/UMIS/networks/resnet.py
code served (permissive licence) · get_code("c3b215555357b9d1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Conv3d. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function conv3x3x3 creates a 3D convolution layer
# Parameters:
# - in_planes: number of input channels
# - out_planes: number of output channels  
# - stride: stride for the convolution (default=1)

# We need to provide distinct values for in_planes and out_planes
in_planes = 3
out_planes = 5
stride = 2

ARGS = {
    'in_planes': in_planes,
    'out_planes': out_planes,
    'stride': stride
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv3d — a Conv3d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv3d 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
downsample_basic_block Ran
ran; our contract draft was wrong, not the code
shirgur/UMIS/networks/resnet.py
code served (permissive licence) · get_code("43c0211ff8dbca5f")
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 Tensor, ndim 5, dtype family float, shape (2, 8, 2, 2, 2) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn.functional as F
from torch.autograd import Variable

torch.manual_seed(0)

# Create a small 5D tensor (batch_size=2, channels=4, depth=3, height=3, width=3)
# This matches the expected input for a 3D convolution operation
x = torch.randn(2, 4, 3, 3, 3)

# planes should be greater than the number of input channels (4)
# so that zero padding can be added
planes = 8

# stride for the pooling operation
stride = 2

ARGS = {
    "x": x,
    "planes": planes,
    "stride": stride
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 5, dtype family float, shape (2, 8, 2, 2, 2) — shape (2, 8, 2, 2, 2) 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
euler_lagrange Ran
ran on a synthesized input
shirgur/UMIS/networks/loss_functions.py
code served (permissive licence) · get_code("72962239139e1d8a")
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 Tensor, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a small stand-in class for args
class Args:
    def __init__(self):
        self.lmd1 = 0.5
        self.lmd2 = 0.3
        self.lmd_area = 0.01

args = Args()

# Create tensors with distinct dimensions
# Shape: (batch=2, channels=3, depth=4, height=5, width=6)
batch_size = 2
channels = 3
depth = 4
height = 5
width = 6

data = torch.randn(batch_size, channels, depth, height, width)
seg = torch.sigmoid(torch.randn(batch_size, channels, depth, height, width))
area = torch.randn(batch_size, channels, depth, height, width)
c0 = torch.randn(batch_size, channels, depth, height, width)
c1 = torch.randn(batch_size, channels, depth, height, width)
rec = torch.randn(batch_size, channels, depth, height, width)
grad_seg = torch.randn(batch_size, channels, depth, height, width)
grad_rec = torch.randn(batch_size, channels, depth, height, width)

ARGS = {
    'data': data,
    'seg': seg,
    'area': area,
    'c0': c0,
    'c1': c1,
    'rec': rec,
    'grad_seg': grad_seg,
    'grad_rec': grad_rec,
    'args': args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
gaussian_threshold Ran
ran on a synthesized input
shirgur/UMIS/utils/metrices.py
code served (permissive licence) · get_code("1b98ff4071c3c6aa")
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 float, shape (4, 3) 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 import ndimage as ndi

# Create a small test image
image = np.random.rand(4, 3).astype('double')

ARGS = {
    'image': image,
    'block_size': 100,
    'offset': -0.06,
    'cval': 0
}
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 float, shape (4, 3) — shape (4, 3) 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
get_fine_tuning_parameters Ran
ran; our contract draft was wrong, not the code
shirgur/UMIS/networks/resnet.py
code served (permissive licence) · get_code("93801ecf3026ab06")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that has layer0, layer1, layer2, layer3, layer4, and fc
# The function iterates through named_parameters() and checks if module names
# like 'layer0', 'layer1', etc. are in the parameter names
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer0 = nn.Linear(4, 3)
        self.layer1 = nn.Linear(3, 3)
        self.layer2 = nn.Linear(3, 3)
        self.layer3 = nn.Linear(3, 3)
        self.layer4 = nn.Linear(3, 2)
        self.fc = nn.Linear(2, 1)
    
    def forward(self, x):
        x = self.layer0(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.fc(x)
        return x

model = SimpleModel()

# Test with ft_begin_index = 0 (should return all parameters)
ft_begin_index_0 = 0

# Test with ft_begin_index = 2 (should fine-tune layer2, layer3, layer4, fc)
ft_begin_index_2 = 2

ARGS = {
    "model": model,
    "ft_begin_index": ft_begin_index_2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
level_set Ran
ran on a synthesized input
shirgur/UMIS/networks/loss_functions.py
code served (permissive licence) · get_code("cb7bf54b4dbcc934")
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 Tensor, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# data: shape (batch=2, channels=3, height=4, width=5) - will be reduced over dims 1-4
data = torch.randn(2, 3, 4, 5)

# seg: binary segmentation mask, same spatial shape as data
seg = torch.randint(0, 2, (2, 3, 4, 5), dtype=torch.float32)

# area: scalar or small tensor for area regularization
area = torch.randn(2, 1)

# c0 and c1: scalar tensors (mean intensity values for two regions)
c0 = torch.randn(1, requires_grad=True)
c1 = torch.randn(1, requires_grad=True)

# args: config object with lmd_area attribute
class Args:
    def __init__(self):
        self.lmd_area = 0.1

args = Args()

ARGS = {
    "data": data,
    "seg": seg,
    "area": area,
    "c0": c0,
    "c1": c1,
    "args": args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
norm_ip Ran
ran on a synthesized input
shirgur/UMIS/networks/utils.py
code served (permissive licence) · get_code("e154ed276ec9e9db")
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 Tensor, ndim 2, dtype family float, shape (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 torch

torch.manual_seed(0)

# Create a small tensor for the image
img = torch.randn(2, 4)

# Define min and max values for normalization
min_val = 0.0
max_val = 1.0

ARGS = {
    "img": img,
    "min": min_val,
    "max": max_val,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (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
norm_range Ran
ran on a synthesized input
shirgur/UMIS/networks/utils.py
code served (permissive licence) · get_code("8464029e4b200afe")
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 Tensor, ndim 2, dtype family float, shape (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 torch

torch.manual_seed(0)

# Create a small tensor for testing
t = torch.randn(2, 4)

# Define ARGS with all parameters of norm_range
ARGS = {
    "t": t,
    "range": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (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
otsu_threshold Ran
ran on a synthesized input
shirgur/UMIS/utils/metrices.py
code served (permissive licence) · get_code("b275506a27ffc844")
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 float32, 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

# Create a small test image
image = np.random.randint(0, 256, size=(10, 10), dtype=np.uint8).astype(np.float32)

ARGS = {
    "image": image,
    "nbins": 256
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float32, 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

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 7 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
conv3x3x3 19 other papers
2 dated earlier, 17 later
1711.08580 (2017-11)
3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes
1711.09577 (2017-11)
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
1911.00232 (2019-11)
Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding
and 16 more not named here
downsample_basic_block 15 other papers
2 dated earlier, 13 later
1705.07750 (2017-05)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
1711.09577 (2017-11)
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
1909.04656 (2019-09)
Video Representation Learning by Dense Predictive Coding
and 12 more not named here
get_fine_tuning_parameters 5 other papers
1 dated earlier, 4 later
1711.09577 (2017-11)
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
1912.05534 (2019-12)
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
1912.09930 (2019-12)
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks
and 2 more not named here

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 2026-11-21.

Repositories linked to this paper

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

Abstract

The task of blood vessel segmentation in microscopy images is crucial for many diagnostic and research applications. However, vessels can look vastly different, depending on the transient imaging conditions, and collecting data for supervised training is laborious. We present a novel deep learning method for unsupervised segmentation of blood vessels. The method is inspired by the field of active contours and we introduce a new loss term, which is based on the morphological Active Contours Without Edges (ACWE) optimization method. The role of the morphological operators is played by novel pooling layers that are incorporated to the network's architecture. We demonstrate the challenges that are faced by previous supervised learning solutions, when the imaging conditions shift. Our unsupervised method is able to outperform such previous methods in both the labeled dataset, and when applied to similar but different datasets. Our code, as well as efficient PyTorch reimplementations of the baseline methods VesselNN and DeepVess is available on GitHub - https://github.com/shirgur/UMIS.

For agents

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

get_harvested_code_for_paper("1908.01373")
get_code_for_paper("1908.01373")
have("1908.01373")

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

curl https://syntology.ai/api/ran/1908.01373.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.01373.svg)](https://syntology.ai/paper/1908.01373)

Connect an agent — have() is free.