OSCR

A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation.

Overview

Authors: Zhuye Xu1, Ru Qiao1
ORCID iDs: Ru Qiao
  1. School of New Energy and Power Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
Institutions: Lanzhou Jiaotong University (China)
Journal: Journal of imaging, volume 12, issue 6, article 255
Dates: received 17 April 2026; accepted 1 June 2026; published online 9 June 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/jimaging12060255 · PMID 42346918 · PMCID PMC13301621 · OpenAlex W7164018628
Open access: gold, a free copy (OpenAlex)
Status: code on request (how the code is found and verified)
Categories: structural MRI / diffusion (modality), other condition (population), methods / tools (subfield)
Methods: Connectivity, Machine learning
Keywords: brain tumor, feature recombination, image segmentation, multimodal
Topic: Advanced Neural Network Applications (Computer Vision and Pattern Recognition, Computer Science), according to OpenAlex
Funding: Gansu Provincial Science and Technology Department (23JRRA1486); Central Guiding Local Science and Technology Development Fund Project (24ZYQA055); Youth Doctor Support Project for Universities in Gansu Province (2024QB-039)
Citations: not cited yet (Europe PMC); 27 references in the paper

Abstract

Brain tumor segmentation from 3D MRI presents significant challenges due to small lesion sizes, ambiguous boundaries, arbitrary spatial distributions, and heterogeneous morphological properties. To tackle these issues, this paper presents a fully automatic 3D brain tumor segmentation network that integrates morphological and anatomical information under a multi-task learning framework for whole tumor, tumor core, and enhanced tumor segmentation. We propose a multimodal feature fusion module to adaptively weight features from four MRI modalities (T1, T1ce, T2, FLAIR), enabling discriminative information integration and helping reduce modality intensity discrepancy and data imbalance. Furthermore, a ConvReXt downsampling module is introduced to preserve fine-grained semantic details by reducing information loss caused by conventional pooling. A dense parallel global attention module is also developed to capture both local details and long-range dependencies, addressing the limited receptive field of standard convolutions. Extensive experiments on the BraTS2020 dataset show that the proposed model obtains average Dice coefficients of 92.54%, 89.21%, and 86.54% for whole tumors, tumor cores, and enhanced tumors. The proposed model achieves competitive performance compared with state-of-the-art methods including nnFormer, validating that it can effectively fuse multimodal and multi-scale features and improve brain tumor segmentation accuracy.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper says that its authors' code is available on request: it was not published with the paper, so there is nothing to verify.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none (its code is available on request), so it has no map.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The BraTS 2020 dataset used in this study is publicly available at https://www.med.upenn.edu/cbica/brats2020/ (accessed on 15 July 2025). The code supporting the findings of this study is available from the corresponding author upon reasonable request.

Reproduced under the paper's license (CC BY), 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, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 2 authors, 4 keywords, 3 funders, 14 references.

Cite

This paper

Xu, Z., & Qiao, R. (2026). A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation. Journal of imaging, 12(6), 255. https://doi.org/10.3390/jimaging12060255

BibTeX

@article{xu2026multimodal,
author = {Xu, Zhuye and Qiao, Ru},
title = {{A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation}},
journal = {Journal of imaging},
year = {2026},
month = jun,
volume = {12},
number = {6},
pages = {255},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2313-433X},
doi = {10.3390/jimaging12060255},
url = {https://doi.org/10.3390/jimaging12060255},
pmid = {42346918},
pmcid = {PMC13301621}
}

RIS

TY - JOUR
AU - Xu, Zhuye
AU - Qiao, Ru
TI - A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation
T2 - Journal of imaging
J2 - J Imaging
PY - 2026
DA - 2026/06/09
VL - 12
IS - 6
SP - 255
SN - 2313-433X
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/jimaging12060255
UR - https://doi.org/10.3390/jimaging12060255
LA - en
ER -

CSL-JSON

{
"id": "10.3390/jimaging12060255",
"type": "article-journal",
"title": "A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation",
"container-title": "Journal of imaging",
"author": [
{
"family": "Xu",
"given": "Zhuye"
},
{
"family": "Qiao",
"given": "Ru"
}
],
"container-title-short": "J Imaging",
"volume": "12",
"issue": "6",
"page": "255",
"DOI": "10.3390/jimaging12060255",
"PMID": "42346918",
"PMCID": "PMC13301621",
"ISSN": "2313-433X",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/jimaging12060255",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
9
]
]
}
}

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:10.3389/fmed.2025.1660445
Application research on YOLOv5 model based on Lightweight Atrous Attention Module in brain tumor MRI image segmentation.
Journal: Frontiers in medicine
In common: structural MRI / diffusion, other condition, 2 references
[2] doi:10.3390/brainsci16010037
A Multi-Task EfficientNetV2S Approach with Hierarchical Hybrid Attention for MRI Enhancing Brain Tumor Segmentation and Classification.
Journal: Brain sciences
In common: structural MRI / diffusion, other condition, 2 references
[3] doi:10.1002/acm2.70560 [code]
Hybrid CNN-GCN framework for brain tumor MRI classification: A graph-based approach to smart healthcare diagnostics.
Journal: Journal of applied clinical medical physics
In common: structural MRI / diffusion, other condition, 2 references
[4] doi:10.3390/children12091127 [code]
The Expanding Frontier: The Role of Artificial Intelligence in Pediatric Neuroradiology.
Journal: Children (Basel, Switzerland)
In common: structural MRI / diffusion, 2 references
[5] doi:10.2174/0115734056342623241119061744
Enhancing Medical Image Classification through Transfer Learning and CLAHE Optimization.
Journal: Current medical imaging
In common: other condition, 2 references
[6] doi:10.3389/fnins.2024.1510175
Application of MRI image segmentation algorithm for brain tumors based on improved YOLO.
Journal: Frontiers in neuroscience
In common: methods / tools, structural MRI / diffusion, other condition, 1 reference
[7] doi:10.1371/journal.pone.0351953 [code]
GL-Net: A knowledge-guided Gaussian-gated and layered refinement network for 3D MRI segmentation of brain gliomas.
Journal: PloS one
In common: methods / tools, structural MRI / diffusion, other condition, 1 reference
[8] doi:10.1371/journal.pone.0292768
PRCnet: An efficient model for automatic detection of brain tumor in MRI images.
Journal: PloS one
In common: methods / tools, structural MRI / diffusion, other condition, 1 reference
[9] doi:10.1038/s41598-025-92776-1
Automated multi-class MRI brain tumor classification and segmentation using deformable attention and saliency mapping.
Journal: Scientific reports
In common: methods / tools, structural MRI / diffusion, other condition, 1 reference
[10] doi:10.1371/journal.pone.0284418
Brain tumor detection and segmentation: Interactive framework with a visual interface and feedback facility for dynamically improved accuracy and trust.
Journal: PloS one
In common: methods / tools, structural MRI / diffusion, other condition, 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.

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.

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.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.