A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation
Journal of Imaging · 09.06.2026 · 12 (6) · 255
DOI: 10.3390/jimaging12060255 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 09.06.2026. Verfasst von Zhuye Xu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of New Energy and Power Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gansu Provincial Science and Technology Department, Central Guiding Local Science and Technology Development Fund Project, Youth Doctor Support Project for Universities in Gansu Province.
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of New Energy and Power Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China.
ORCID-Profile: Ru Qiao
Förderung
- Gansu Provincial Science and Technology Department
- Central Guiding Local Science and Technology Development Fund Project
- Youth Doctor Support Project for Universities in Gansu Province
- Gansu Provincial United Scientific Research Fund General Project
Zitieren
APA
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
Vancouver
Xu Z, Qiao R. A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation. Journal of Imaging. 2026;12(6):255. doi:10.3390/jimaging12060255
BibTeX
@article{Xu2026,
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},
volume = {12},
number = {6},
pages = {255},
doi = {10.3390/jimaging12060255}
}
EUVIMED