SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_28536 · AAAI · 2024

A Robust Mutual-Reinforcing Framework for 3D Multi-Modal Medical Image Fusion Based on Visual-Semantic Consistency

Hao Zhang, Tao Lu, Jiayi Ma, Xuhui Zuo, Huabing Zhou

Open in the Atlas

Code that ran

6 of 6 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, 1 violated it and 1 has no contract verdict; 4 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/aaai_28536.json · badge: /api/ran/aaai_28536.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
HaoZhang1018/RMR-Fusion canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
get_image_paths Ran
ran; our contract draft was wrong, not the code
HaoZhang1018/RMR-Fusion/utils.py
code served (permissive licence) · get_code("d914d771dc7818f3")
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 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 os
import tempfile
from pathlib import Path

# Create a temporary directory structure with some image files
temp_dir = tempfile.mkdtemp()
subdir1 = os.path.join(temp_dir, "subdir1")
subdir2 = os.path.join(temp_dir, "subdir2")
os.makedirs(subdir1, exist_ok=True)
os.makedirs(subdir2, exist_ok=True)

# Create dummy image files with valid extensions
Path(os.path.join(subdir1, "image1.jpg")).touch()
Path(os.path.join(subdir1, "image2.png")).touch()
Path(os.path.join(subdir1, "image3.bmp")).touch()
Path(os.path.join(subdir2, "image4.jpeg")).touch()
Path(os.path.join(subdir2, "image5.tif")).touch()

# Also create a non-image file to ensure filtering works
Path(os.path.join(subdir1, "readme.txt")).touch()

# Test with string path
dataroot_str = subdir1

# Test with list of paths
dataroot_list = [subdir1, subdir2]

# Use the list version for ARGS since it exercises more of the function
ARGS = {
    "dataroot": dataroot_list
}
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 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
get_window_size Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
HaoZhang1018/RMR-Fusion/models/dualSwinAE.py
code served (permissive licence) · get_code("34484ba7deb03520")
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 tuple, ndim 2, dtype family int; 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

torch.manual_seed(0)

# Analyze the function:
# - x_size: needs to be a sequence (list/tuple) of integers representing input dimensions
# - window_size: needs to be a sequence of integers representing window dimensions
# - shift_size: optional sequence of integers representing shift amounts, or None

# The function iterates through indices of x_size and compares with window_size
# It creates lists from window_size and optionally shift_size
# Returns tuple(s) based on whether shift_size is provided

ARGS = {
    "x_size": (8, 12, 16),  # input spatial dimensions (distinct sizes)
    "window_size": (4, 4, 4),  # window dimensions
    "shift_size": (2, 2, 2),  # shift dimensions
}
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 tuple, ndim 2, dtype family int — a tuple 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
is_image_file Ran
ran, violated the contract we drafted
HaoZhang1018/RMR-Fusion/utils.py
code served (permissive licence) · get_code("86889dc6e9a74a48")
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 torch

torch.manual_seed(0)

ARGS = {
    "filename": "test_image.jpg"
}
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 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
tf_fspecial_gauss_3d_torch Ran
ran on a synthesized input
HaoZhang1018/RMR-Fusion/loss.py
code served (permissive licence) · get_code("02d404b6518a16ec")
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 5, dtype family float, shape (1, 1, 5, 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
import torch

torch.manual_seed(0)

ARGS = {
    "size": 5,
    "sigma": 1.0
}
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 Tensor, ndim 5, dtype family float, shape (1, 1, 5, 5, 5) — shape (1, 1, 5, 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
window_partition Ran
ran; our contract draft was wrong, not the code
HaoZhang1018/RMR-Fusion/models/dualSwinAE.py
pointer only (licence: MIT); the stored copy get_code serves, from HeadLiuYun/NeuroDiff, is pointer only (licence: NONE) · get_code("8cd5fa7e1d693a92")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from HeadLiuYun/NeuroDiff, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

window_reverse Ran
ran; our contract draft was wrong, not the code
HaoZhang1018/RMR-Fusion/models/dualSwinAE.py
pointer only (licence: MIT); the stored copy get_code serves, from HeadLiuYun/NeuroDiff, is pointer only (licence: NONE) · get_code("1545b891ff0bbdd7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from HeadLiuYun/NeuroDiff, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 4 later) and 1 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
is_image_file 62 other papers
48 dated earlier, 2 later, 12 same year, order not determinable
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1703.07511 (2017-03)
Deep Photo Style Transfer
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
and 59 more not named here
get_window_size 26 other papers
13 dated earlier, 4 later, 9 same year, order not determinable · 7 only as an assembly brick
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.13230 (2021-06)
Video Swin Transformer
2111.14821 (2021-11)
End-to-End Referring Video Object Segmentation with Multimodal Transformers
and 23 more not named here
window_partition 7 other papers
3 dated earlier, 1 later, 3 same year, order not determinable
2204.00631 (2022-04)
UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation
2211.02701 (2022-11)
MONAI: An open-source framework for deep learning in healthcare
2305.19467 (2023-05)
Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Model
and 4 more not named here
window_reverse 3 other papers
2 dated earlier, 1 later
2211.02701 (2022-11)
MONAI: An open-source framework for deep learning in healthcare
2305.19467 (2023-05)
Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Model
2601.15779 (2026-01)
Diffusion Model-Based Data Augmentation for Enhanced Neuron Segmentation
get_image_paths 2 other papers
2 dated earlier
2203.13278 (2022-03)
Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
2309.03020 (2023-09)
SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution

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

This work proposes a robust 3D medical image fusion framework to establish a mutual-reinforcing mechanism between visual fusion and lesion segmentation, achieving their double improvement. Specifically, we explore the consistency between vision and semantics by sharing feature fusion modules. Through the coupled optimization of the visual fusion loss and the lesion segmentation loss, visual-related and semantic-related features will be pulled into the same domain, effectively promoting accuracy improvement in a mutual-reinforcing manner. Further, we establish the robustness guarantees by constructing a two-level refinement constraint in the process of feature extraction and reconstruction. Benefiting from full consideration for common degradations in medical images, our framework can not only provide clear visual fusion results for doctor's observation, but also enhance the defense ability of lesion segmentation against these negatives. Extensive evaluations of visual fusion and lesion segmentation scenarios demonstrate the advantages of our method in terms of accuracy and robustness. Moreover, our proposed framework is generic, which can be wellcompatible with existing lesion segmentation algorithms and improve their performance. The code is publicly available at https://github.com/HaoZhang1018/RMR-Fusion.

For agents

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

get_harvested_code_for_paper("aaai_28536")
get_code_for_paper("aaai_28536")
have("aaai_28536")

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

curl https://syntology.ai/api/ran/aaai_28536.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_28536.svg)](https://syntology.ai/paper/aaai_28536)

Connect an agent — have() is free.