SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.09063 · 2019

A large annotated medical image dataset for the development and evaluation of segmentation algorithms

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 0 failures of our instrument; 1 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/1902.09063.json · badge: /api/ran/1902.09063.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
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant community (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
Dice3d Ran
ran on a synthesized input
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant/section2/src/utils/volume_stats.py
code served (permissive licence) · get_code("d13080d32de76975")
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 float, 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 two 3D binary masks of the same shape
# First volume: a 4x5x6 array with some non-zero values
a = np.zeros((4, 5, 6), dtype=np.float32)
a[1:3, 2:4, 1:5] = 1  # Set some region to 1 (foreground)

# Second volume: a 4x5x6 array with overlapping non-zero values
b = np.zeros((4, 5, 6), dtype=np.float32)
b[1:3, 2:4, 2:5] = 1  # Set overlapping region to 1 (foreground)

ARGS = {
    'a': a,
    'b': b
}
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 float, 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
Jaccard3d Ran
ran on a synthesized input
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant/section2/src/utils/volume_stats.py
code served (permissive licence) · get_code("7f4f606901654251")
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 float, 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

np.random.seed(0)

# Create two 3D binary masks with some overlap
# First volume: 4x5x6 shape
a = np.random.randint(0, 2, size=(4, 5, 6))

# Second volume: same shape as a
b = np.random.randint(0, 2, size=(4, 5, 6))

ARGS = {
    'a': a,
    'b': b
}
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 float, 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
Spec3d Ran
ran on a synthesized input
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant/section2/src/utils/volume_stats.py
code served (permissive licence) · get_code("75fcd7f0223c34d5")
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 float, 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 two 3D binary masks of the same shape
# First dimension: depth, Second: height, Third: width
np.random.seed(0)

# Create prediction volume (a)
a = np.random.randint(0, 2, size=(5, 6, 7))

# Create ground truth volume (b)
b = np.random.randint(0, 2, size=(5, 6, 7))

ARGS = {
    'a': a,
    'b': b
}
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 float, 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
get_predicted_volumes Ran
ran on a synthesized input
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant/section3/src/inference_dcm.py
code served (permissive licence) · get_code("b35f51071ddc1ca2")
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 dict. 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

# Create a small predicted array with labels 0 (background), 1 (anterior), 2 (posterior)
# Shape: 10x10x10 3D volume with some voxels labeled as anterior (1) and posterior (2)
pred = np.zeros((10, 10, 10), dtype=np.int32)
pred[2:5, 2:5, 2:5] = 1  # anterior region
pred[6:9, 6:9, 6:9] = 2  # posterior region

ARGS = {
    'pred': pred
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
load_dicom_volume_as_numpy_from_list Ran
ran on a synthesized input
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant/section3/src/inference_dcm.py
code served (permissive licence) · get_code("8bb9742ae1118fd0")
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 tuple. 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
from unittest.mock import Mock

# Create mock PyDicom objects
def create_mock_dicom(instance_number, shape=(64, 64)):
    """Create a mock PyDicom object with necessary attributes"""
    mock_dcm = Mock()
    mock_dcm.InstanceNumber = instance_number
    mock_dcm.pixel_array = np.random.randint(0, 256, shape, dtype=np.uint8)
    mock_dcm.PixelData = b"fake_pixel_data"
    return mock_dcm

# Create a list of mock DICOM objects with different instance numbers
dcmlist = [
    create_mock_dicom(instance_number=3, shape=(64, 64)),
    create_mock_dicom(instance_number=1, shape=(64, 64)),
    create_mock_dicom(instance_number=2, shape=(64, 64)),
]

ARGS = {
    "dcmlist": dcmlist
}
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 tuple — a tuple output has no array shape of its own; none is 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
med_reshape Ran
ran on a synthesized input
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant/section2/src/utils/utils.py
code served (permissive licence) · get_code("1442b5f845073c45")
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 (4, 5, 6) 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 3D array as input image
image = np.random.rand(2, 3, 4).astype(np.float32)

# Define new shape (must be >= original shape dimensions)
new_shape = (4, 5, 6)

ARGS = {
    "image": image,
    "new_shape": new_shape,
}
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 (4, 5, 6) — shape (4, 5, 6) 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
mpl_image_grid Ran
ran on a synthesized input
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant/section2/src/utils/utils.py
code served (permissive licence) · get_code("3915b21d17fcf609")
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 Figure. 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 matplotlib.pyplot as plt

torch.manual_seed(0)

# Create a small batch of images
# The function expects NxWxH or NxCxWxH format
# Looking at the code, it checks images.shape[1] for channel count
# So format is N x C x W x H

# Test case 1: RGB images (3 channels)
# N=2 images, C=3 channels, W=4, H=5
images_rgb = torch.rand(2, 3, 4, 5)

ARGS = {
    "images": images_rgb
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
create_report Not yet run
unverified (harvested, no recorded run)
korotulea/Quantifying-Hippocampus-Volume-for-Alzheimers-Progression-AI-Assistant/section3/src/inference_dcm.py
code served (permissive licence) · get_code("992fafba04852523")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human initialization. The success of semantic segmentation algorithms is contingent on the availability of high-quality imaging data with corresponding labels provided by experts. We sought to create a large collection of annotated medical image datasets of various clinically relevant anatomies available under open source license to facilitate the development of semantic segmentation algorithms. Such a resource would allow: 1) objective assessment of general-purpose segmentation methods through comprehensive benchmarking and 2) open and free access to medical image data for any researcher interested in the problem domain. Through a multi-institutional effort, we generated a large, curated dataset representative of several highly variable segmentation tasks that was used in a crowd-sourced challenge - the Medical Segmentation Decathlon held during the 2018 Medical Image Computing and Computer Aided Interventions Conference in Granada, Spain. Here, we describe these ten labeled image datasets so that these data may be effectively reused by the research community.

For agents

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

get_harvested_code_for_paper("1902.09063")
get_code_for_paper("1902.09063")
have("1902.09063")

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

curl https://syntology.ai/api/ran/1902.09063.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.09063.svg)](https://syntology.ai/paper/1902.09063)

Connect an agent — have() is free.