SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1608.04667 · 2016

Medical image denoising using convolutional denoising autoencoders

arXiv · PDF · Open in the Atlas

Code that ran

6 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 6 have no contract verdict; 0 failures of our instrument; 2 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/1608.04667.json · badge: /api/ran/1608.04667.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
adam-mah/Medical-Image-Denoising community (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
FunctionStatusWhere it lives
Define_SearchWindow Ran
ran on a synthesized input
adam-mah/Medical-Image-Denoising/bm3d.py
code served (permissive licence) · get_code("9f06a392f759a780")
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 1, dtype family int, shape (2,) 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

# Analyze the function:
# - _noisyImg: needs .shape[0] attribute (array-like)
# - _BlockPoint: needs indexing [0] and [1] (tuple or list)
# - _WindowSize: numeric value
# - Blk_Size: numeric value

# Create a small noisy image (2D array, 16x16)
_noisyImg = numpy.random.rand(16, 16)

# Create a block point (x, y coordinates)
_BlockPoint = (8, 8)

# Window size and block size
_WindowSize = 8
Blk_Size = 4

ARGS = {
    "_noisyImg": _noisyImg,
    "_BlockPoint": _BlockPoint,
    "_WindowSize": _WindowSize,
    "Blk_Size": Blk_Size
}
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 1, dtype family int, shape (2,) — shape (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
Locate_blk Ran
ran on a synthesized input
adam-mah/Medical-Image-Denoising/bm3d.py
code served (permissive licence) · get_code("d8d514d6807e9171")
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 1, dtype family int, shape (2,) 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

# Analyze the function Locate_blk:
# Parameters:
# - i: block index in x direction (int)
# - j: block index in y direction (int)
# - blk_step: step size between blocks (int)
# - block_Size: size of each block (int)
# - width: image/canvas width (int)
# - height: image/canvas height (int)
#
# The function calculates the top-left corner point of a block,
# ensuring it doesn't exceed the canvas boundaries.

ARGS = {
    "i": 2,
    "j": 3,
    "blk_step": 10,
    "block_Size": 16,
    "width": 64,
    "height": 80
}
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 1, dtype family int, shape (2,) — shape (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
init Ran
ran on a synthesized input
adam-mah/Medical-Image-Denoising/bm3d.py
code served (permissive licence) · get_code("d86875c444f7728a")
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

# Construct valid arguments for the init function
# The function expects:
# - img: a numpy array with a shape attribute
# - _blk_size: an integer for the Kaiser window size
# - _Beta_Kaiser: a float for the Kaiser window beta parameter

# Create a small image array (2D for simplicity)
img = numpy.random.rand(4, 3).astype(float)

# Block size for Kaiser window
_blk_size = 5

# Beta parameter for Kaiser window
_Beta_Kaiser = 8.6

ARGS = {
    "img": img,
    "_blk_size": _blk_size,
    "_Beta_Kaiser": _Beta_Kaiser,
}
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
read_covid Ran
ran on a synthesized input
adam-mah/Medical-Image-Denoising/dataset_reader.py
code served (permissive licence) · get_code("dfcb59c1e0ad7e1f")
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 int, shape (3, 32, 32) 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 os
import cv2
import numpy
import tempfile
import shutil

# Create a temporary directory with test images
temp_dir = tempfile.mkdtemp()

# Create a few grayscale test images
img1 = numpy.random.randint(0, 256, (32, 32), dtype=numpy.uint8)
img2 = numpy.random.randint(0, 256, (32, 32), dtype=numpy.uint8)
img3 = numpy.random.randint(0, 256, (32, 32), dtype=numpy.uint8)

cv2.imwrite(os.path.join(temp_dir, 'covid_1.png'), img1)
cv2.imwrite(os.path.join(temp_dir, 'covid_2.png'), img2)
cv2.imwrite(os.path.join(temp_dir, 'covid_3.png'), img3)

ARGS = {
    'folder': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (3, 32, 32) — shape (3, 32, 32) 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
read_dental Ran
ran on a synthesized input
adam-mah/Medical-Image-Denoising/dataset_reader.py
code served (permissive licence) · get_code("db10410b6bbb4103")
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 int, shape (2, 32, 32) 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 os
import cv2
import numpy
import tempfile
import shutil

# Create a temporary directory with test images
temp_dir = tempfile.mkdtemp()

# Create a few simple grayscale images using numpy and cv2
for i in range(2):
    img = numpy.random.randint(0, 256, (32, 32), dtype=numpy.uint8)
    cv2.imwrite(os.path.join(temp_dir, f'dental_{i}.png'), img)

# Define ARGS with the temporary directory
ARGS = {
    'folder': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (2, 32, 32) — shape (2, 32, 32) 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
read_pgm Ran
ran on a synthesized input
adam-mah/Medical-Image-Denoising/dataset_reader.py
code served (permissive licence) · get_code("4c939267962ba77f")
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 (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 re
import numpy
import tempfile
import os

# Create a minimal valid PGM file
temp_dir = tempfile.gettempdir()
pgm_filename = os.path.join(temp_dir, "test_image.pgm")

# Create a small 3x4 PGM file with maxval 255
pgm_content = b"""P5
# This is a comment
3 4
255
""" + bytes([i % 256 for i in range(3 * 4)])

with open(pgm_filename, 'wb') as f:
    f.write(pgm_content)

ARGS = {
    'filename': pgm_filename,
    'byteorder': '>'
}
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 2, dtype family int, 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
bm3d_denoise Not yet run
unverified (harvested, no recorded run)
adam-mah/Medical-Image-Denoising/conv_denoiser.py
code served (permissive licence) · get_code("02ae55768470d494")
How it ran

no invocation recorded.

nlm_denoise Not yet run
unverified (harvested, no recorded run)
adam-mah/Medical-Image-Denoising/conv_denoiser.py
code served (permissive licence) · get_code("e6a079a363ea1bd1")
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

Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. More recently, having outperformed all conventional methods, deep learning based models have shown a great promise. These methods are however limited for requirement of large training sample size and high computational costs. In this paper we show that using small sample size, denoising autoencoders constructed using convolutional layers can be used for efficient denoising of medical images. Heterogeneous images can be combined to boost sample size for increased denoising performance. Simplest of networks can reconstruct images with corruption levels so high that noise and signal are not differentiable to human eye.

For agents

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

get_harvested_code_for_paper("1608.04667")
get_code_for_paper("1608.04667")
have("1608.04667")

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

curl https://syntology.ai/api/ran/1608.04667.json

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

[![Syntology run record](https://syntology.ai/api/ran/1608.04667.svg)](https://syntology.ai/paper/1608.04667)

Connect an agent — have() is free.