MedGAN-SSM: Multimodal brain image synthesis network integration using SSM empowered GAN.
5 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.
The 7 matches · 1 of them tie a paragraph to a whole file without given lines: a weak match, whose lines are not tinted
- [1] § STAR★Methods › Quantification and statistical analysis › Evaluation metrics ↔ trainer.py, lines 69 to 136 · score 0.73 · Peak Signal, Absolute Error, Noise Ratio, metrics, SSIM, MAE · block
oscr:b:6C3V70WYMSP7Y-4· Report a mismatch - [2] § STAR★Methods › Quantification and statistical analysis › Evaluation metrics ↔ tester.py, the whole file · a weak match · score 0.63 · Peak Signal, Noise Ratio, Error, metrics, SSIM, MAE · block
oscr:b:FF5F0NSSJT03Q-7· Report a mismatch - [3] § STAR★Methods › Method details › State space construction and representation › Global information fusion ↔ models/generator.py, lines 4 to 20 · score 0.61 · state space construction, global contextual, GAP, linear, map, fusion · block
oscr:b:AN63NK9DJ218A-X· Report a mismatch - [4] § STAR★Methods › Method details › Multi-dimensional S6 module design ↔ models/generator.py, lines 49 to 69 · score 0.57 · S6 module, residual blocks, model · block
oscr:b:NZCQBWSZ1EYE8-9· Report a mismatch - [5] § STAR★Methods › Method details › Multi-dimensional S6 module design › Cross-dimensional feature fusion ↔ models/generator.py, lines 105 to 181 · score 0.55 · MRI slices, available modality, decoder, S6 · block
oscr:b:FNAXK73X78SYJ-I· Report a mismatch - [6] § STAR★Methods › Method details ↔ models/generator.py, lines 4 to 20 · score 0.53 · global context, state space, adaptive, maps, fusion, channel · block
oscr:b:AN63NK9DJ218A-X· Report a mismatch - [7] § Results › Comparison with SOTA methods ↔ trainer.py, lines 69 to 136 · score 0.50 · absolute error, target modality, predicted, metrics, SSIM, MAE · block
oscr:b:6C3V70WYMSP7Y-4· Report a mismatch
Paper
Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
Python · 181 lines · 6.3 KB · MIT · 4 matches
- import torch
- import torch.nn as nn
- class StateSpaceModule(nn.Module):
- """State Space Construction Module"""
- def __init__(self, in_channels, state_dim):
- super().__init__()
- self.conv = nn.Conv2d(in_channels, state_dim, 1)
- self.gap = nn.AdaptiveAvgPool2d(1)
- self.fc = nn.Linear(in_channels, state_dim)
- def forward(self, x):
- # Basic state mapping
- s = torch.relu(self.conv(x))
- # Global context fusion
- g = self.gap(x).squeeze(-1).squeeze(-1)
- g = torch.relu(self.fc(g))[:, :, None, None]
- return s + g # Modulated state Ŝ
- class DynamicGate(nn.Module):
- """Dynamic Gating Module"""
- def __init__(self, in_channels, ratio=16):
- super().__init__()
- # Spatial gating branch
- self.spatial = nn.Sequential(
- nn.Conv2d(in_channels, in_channels//ratio, 3, padding=1),
- nn.ReLU(),
- NonLocalBlock(in_channels//ratio),
- nn.Conv2d(in_channels//ratio, 1, 3, padding=1),
- nn.Sigmoid()
- )
- # Channel gating branch
- self.channel = nn.Sequential(
- nn.AdaptiveAvgPool2d(1),
- nn.Conv2d(in_channels, in_channels//ratio, 1),
- nn.ReLU(),
- nn.Conv2d(in_channels//ratio, in_channels, 1),
- nn.Sigmoid()
- )
- def forward(self, x):
- g_spatial = self.spatial(x)
- g_channel = self.channel(x)
- return g_spatial * 0.6 + g_channel * 0.4 # Weighted fusion
- class MultiScaleS6(nn.Module):
- """Multi-scale S6 Module"""
- def __init__(self, channels):
- super().__init__()
- # Local branch
- self.local = nn.Sequential(
- ResidualBlock(channels, dilation=1),
- ResidualBlock(channels, dilation=2),
- ResidualBlock(channels, dilation=4)
- )
- # Global branch
- self.global_branch = nn.Sequential(
- nn.Conv2d(channels, channels, 7, padding=3),
- NonLocalBlock(channels)
- )
- def forward(self, x, gate):
- local_feat = self.local(x)
- global_feat = self.global_branch(x)
- return x + gate*local_feat + (1-gate)*global_feat
- class ResidualBlock(nn.Module):
- """Residual Block"""
- def __init__(self, channels, dilation=1):
- super().__init__()
- self.conv = nn.Sequential(
- nn.Conv2d(channels, channels, 3, padding=dilation, dilation=dilation),
- nn.InstanceNorm2d(channels),
- nn.ReLU(),
- nn.Conv2d(channels, channels, 3, padding=dilation, dilation=dilation),
- nn.InstanceNorm2d(channels))
- def forward(self, x):
- return x + self.conv(x)
- class NonLocalBlock(nn.Module):
- """Non-local Attention Module"""
- def __init__(self, channels):
- super().__init__()
- self.theta = nn.Conv2d(channels, channels//8, 1)
- self.phi = nn.Conv2d(channels, channels//8, 1)
- self.g = nn.Conv2d(channels, channels//8, 1)
- self.out = nn.Conv2d(channels//8, channels, 1)
- def forward(self, x):
- batch_size = x.size(0)
- theta = self.theta(x).view(batch_size, -1, x.size(2)*x.size(3))
- phi = self.phi(x).view(batch_size, -1, x.size(2)*x.size(3)).permute(0,2,1)
- g = self.g(x).view(batch_size, -1, x.size(2)*x.size(3))
- attn = torch.softmax(torch.bmm(theta, phi), dim=-1)
- out = torch.bmm(attn, g)
- out = out.view(batch_size, -1, x.size(2), x.size(3))
- return self.out(out) + x
- class Generator(nn.Module):
- """
- 2D Image Generator - Processing Multi-modal MRI Slices
- Input: 2D multi-modal MRI slices (variable channels, depending on available modalities)
- Output: Single modality 2D MRI slice
- """
- def __init__(self, in_channels=None, out_channels=1):
- super().__init__()
- if in_channels is None:
- in_channels = 3
- # Encoder
- self.encoder1 = nn.Sequential(
- nn.Conv2d(in_channels, 64, 4, stride=2, padding=1),
- nn.LeakyReLU(0.2),
- StateSpaceModule(64, 64)
- )
- self.encoder2 = nn.Sequential(
- nn.Conv2d(64, 128, 4, stride=2, padding=1),
- nn.InstanceNorm2d(128),
- nn.LeakyReLU(0.2)
- )
- self.encoder3 = nn.Sequential(
- nn.Conv2d(128, 256, 4, stride=2, padding=1),
- nn.InstanceNorm2d(256),
- nn.LeakyReLU(0.2)
- )
- self.encoder4 = nn.Sequential(
- nn.Conv2d(256, 512, 4, stride=2, padding=1),
- nn.InstanceNorm2d(512),
- nn.LeakyReLU(0.2)
- )
- # Core processing modules
- self.process = nn.Sequential(
- MultiScaleS6(512),
- DynamicGate(512),
- MultiScaleS6(512)
- )
- # Decoder
- self.decoder1 = nn.Sequential(
- nn.ConvTranspose2d(512, 256, 4, stride=2, padding=1),
- nn.InstanceNorm2d(256),
- nn.ReLU()
- )
- self.decoder2 = nn.Sequential(
- nn.ConvTranspose2d(512, 128, 4, stride=2, padding=1), # 512 = 256 + 256 (skip connection)
- nn.InstanceNorm2d(128),
- nn.ReLU()
- )
- self.decoder3 = nn.Sequential(
- nn.ConvTranspose2d(256, 64, 4, stride=2, padding=1), # 256 = 128 + 128 (skip connection)
- nn.InstanceNorm2d(64),
- nn.ReLU()
- )
- self.decoder4 = nn.Sequential(
- nn.ConvTranspose2d(128, out_channels, 4, stride=2, padding=1), # 128 = 64 + 64 (skip connection)
- nn.Tanh()
- )
- def forward(self, x):
- enc1 = self.encoder1(x)
- enc2 = self.encoder2(enc1)
- enc3 = self.encoder3(enc2)
- enc4 = self.encoder4(enc3)
- gate = self.process[1](enc4)
- proc = self.process[0](enc4, gate)
- proc = self.process[2](proc, gate)
- dec1 = self.decoder1(proc)
- dec2 = self.decoder2(torch.cat([dec1, enc3], dim=1)) # Skip connection
- dec3 = self.decoder3(torch.cat([dec2, enc2], dim=1)) # Skip connection
- dec4 = self.decoder4(torch.cat([dec3, enc1], dim=1)) # Skip connection
- return dec4
generator.py at commit 624db77, under MIT · at the source
Overview
- School of Integrated Circuit, Wuxi Vocational College of Science and Technology, Wuxi 214028, China
- School of Software, Dalian University of Technology, Dalian 116024, China
- Department of Emergency Internal Medicine, Heilongjiang Hospital of Beijing Children’s Hospital Affiliated to Capital Medical University, Harbin 150010, China
Abstract
Multimodal medical image synthesis is essential for addressing data scarcity and incomplete modality acquisition in clinical imaging. This study presents MedGAN-SSM, a framework that enhances multimodal brain MRI synthesis by integrating generative adversarial networks (GANs) with state space modeling (SSM). MedGAN-SSM uses a state space module to capture global semantic information via cross-layer transmission. A dynamic attention gate adjusts spatial and channel features, allowing the model to target relevant areas, while a multi-dimensional S6 module merges local and global features across scales to enhance synthesis quality and anatomical consistency. Experiments on the BraTS2020 and IXI datasets show that MedGAN-SSM outperforms existing methods in PSNR, SSIM, and MAE, demonstrating robustness in missing-modality scenarios while generating high-fidelity images that enhance segmentation performance. Overall, MedGAN-SSM reliably synthesizes high-quality multimodal brain MRI, preserving anatomical details while aiding automated analyses and clinical workflows in incomplete imaging conditions.
Reproduced under the paper's license (CC BY-NC), from the paper cited above.
Repository
Its files are read in the Code ↔ Paper reader above, with 7 matches between paragraphs and lines of code.
Charles-wmz/MedGAN-SSM
624db770579c5807bdc10f6e83d1789b1a3504cb, 7 December 2025Availability: 1 check, the latest on 30 September 2026: the link answers
- 30 September 2026: the link answers
16 files
- DataProcessing.py, Python, 141 lines
- dataset.py, Python, 125 lines
- main.py, Python, 108 lines
- models/
__init__.py , Python, 4 lines - models/
discriminator.py , Python, 17 lines - models/
generator.py , Python, 181 lines, 4 matches - tester.py, Python, 139 lines, 1 match
- trainer.py, Python, 224 lines, 2 matches
- utils/
DataProcessing.py , Python, 141 lines - utils/
Slices_80.py , Python, 61 lines - utils/
align_mri_modalities.py , Python, 199 lines - utils/
modality_missing.py , Python, 79 lines - utils/
organize_data.py , Python, 58 lines - visualize.py, Python, 439 lines
- LICENSE, License, 21 lines
- README.md, Text, 128 lines
The paper's code and data availability statement is in the Data section.
Tracing map
Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.
What the map holds:
- 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 14 scripts, each with its path and the digest of its content;
- 7 matches between paragraphs of the paper and lines of the code (method lexical-v1);
- neither the text of the paper nor the code itself.
Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.
Data
No dataset and no data link were found in the paper.
Data and code availability
• The code for the proposed method is publicly available at https://
Reproduced under the paper's license (CC BY-NC), from the paper cited above.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 1, 30 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 6 authors, 2 keywords, 2 funders, 37 references.
Cite
This paper
Song, T., Wang, M., Ren, Z., Li, W., Zhang, J., & Li, K. (2026). MedGAN-SSM: Multimodal brain image synthesis network integration using SSM empowered GAN. iScience, 29(6), 115924. https://
BibTeX
@article{song2026medgan,
author = {Song, Tianming and Wang, Mingzhi and Ren, Zhe and Li, Wensi and Zhang, Jian and Li, Kexin},
title = {{MedGAN-SSM: Multimodal brain image synthesis network integration using SSM empowered GAN}},
journal = {iScience},
year = {2026},
month = apr,
volume = {29},
number = {6},
pages = {115924},
publisher = {Elsevier},
issn = {2589-0042},
doi = {10.1016/
url = {https://
pmid = {42181291},
pmcid = {PMC13196568}
}
RIS
TY - JOUR
AU - Song, Tianming
AU - Wang, Mingzhi
AU - Ren, Zhe
AU - Li, Wensi
AU - Zhang, Jian
AU - Li, Kexin
TI - MedGAN-SSM: Multimodal brain image synthesis network integration using SSM empowered GAN
T2 - iScience
J2 - iScience
PY - 2026
DA - 2026/
VL - 29
IS - 6
SP - 115924
SN - 2589-0042
PB - Elsevier
DO - 10.1016/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1016/
"type": "article-journal",
"title": "MedGAN-SSM: Multimodal brain image synthesis network integration using SSM empowered GAN",
"container-title": "iScience",
"author": [
{
"family": "Song",
"given": "Tianming"
},
{
"family": "Wang",
"given": "Mingzhi"
},
{
"family": "Ren",
"given": "Zhe"
},
{
"family": "Li",
"given": "Wensi"
},
{
"family": "Zhang",
"given": "Jian"
},
{
"family": "Li",
"given": "Kexin"
}
],
"container-title-short":
"volume": "29",
"issue": "6",
"page": "115924",
"DOI": "10.1016/
"PMID": "42181291",
"PMCID": "PMC13196568",
"ISSN": "2589-0042",
"publisher": "Elsevier",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
30
]
]
}
}
The tracing map gets a citation of its own once an author has validated it and it has a DOI.
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1002/acm2.13530 [code]
- Deep learning-based convolutional neural network for intramodality brain MRI synthesis.Journal: Journal of applied clinical medical physicsIn common: SimpleITK, scikit-image, NiBabel, 2 other tools, 2 references
- [2] doi:10.1038/s41598-025-16257-1 [code]
- High-resolution conditional MR image synthesis through the PACGAN framework.Journal: Scientific reportsIn common: scikit-image, NiBabel, PyTorch, 2 other tools, 2 references
- [3] doi:10.1038/s41698-025-01269-x [code]
- AI-powered segmentation and prognosis with missing MRI in pediatric brain tumors.Journal: NPJ precision oncologyIn common: SimpleITK, scikit-image, NiBabel, 3 other tools, 1 reference
- [4] doi:10.1007/978-3-031-43999-5_43 [code]
- Unified Brain MR-Ultrasound Synthesis using Multi-Modal Hierarchical Representations.Journal: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted InterventionIn common: NiBabel, PyTorch, NumPy, 3 references
- [5] doi:10.1038/s41467-026-69578-8 [code]
- Contrast-free identification of glioma blood-brain barrier status via generative diffusion AI and non-contrast MRI.Journal: Nature communicationsIn common: SimpleITK, scikit-image, NiBabel, 2 other tools, 1 reference
- [6] doi:10.21037/atm-21-4056 [code]
- Detecting brain lesions in suspected acute ischemic stroke with CT-based synthetic MRI using generative adversarial networks.Journal: Annals of translational medicineIn common: SimpleITK, scikit-image, PyTorch, 2 other tools, 1 reference
- [7] doi:10.1016/j.crmeth.2025.101138 [code]
- All-in-one medical image-to-image translation.Journal: Cell reports methodsIn common: SimpleITK, scikit-image, PyTorch, 2 other tools, 1 reference
- [8] doi:10.1186/s12880-024-01242-3 [code]
- Contrast-enhanced to non-contrast-enhanced image translation to exploit a clinical data warehouse of T1-weighted brain MRI.Journal: BMC medical imagingIn common: NiBabel, PyTorch, Matplotlib, 1 other tool, 2 references
- [9] doi:10.3390/diagnostics16060875 [code]
- An Adaptive Attention 3D U-Net for High-Fidelity MRI-to-CT Synthesis: Bridging the Anatomical Gap with CBAM.Journal: Diagnostics (Basel, Switzerland)In common: scikit-image, NiBabel, PyTorch, 2 other tools, 1 reference
- [10] doi:10.1038/s42003-025-07936-w [code]
- Diffusion MRI GAN synthesizing fibre orientation distribution data using generative adversarial networks.Journal: Communications biologyIn common: scikit-image, NiBabel, PyTorch, 2 other tools, 1 reference
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 14 scripts, and 7 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:8edd90e0bc9cd4cf…
Add the badge to the code's README
If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.
Markdown
<!-- oscr-badge:start -->
[](https://openscicode.org/badge/doi/10.1016/j.isci.2026.115924)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.1016/j.isci.2026.115924.svg
:target: https://openscicode.org/badge/doi/10.1016/j.isci.2026.115924
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1016/j.isci.2026.115924"><img src="https://openscicode.org/badge/doi/10.1016/j.isci.2026.115924.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".
If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Report a mismatch between the code and the paper · Report a code error (signed in)
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Report a reproduction failure (signed in)
Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
