In this section
@article{Zhou:2026:10.1016/j.inffus.2025.104085,
author = {Zhou, T and Li, M and Ruan, S and Luo, T and Jiang, B and Zhu, J and Ma, P and Yang, D and Yang, G},
doi = {10.1016/j.inffus.2025.104085},
journal = {Information Fusion},
title = {A reliable framework for brain tumor segmentation via multi-modal fusion and uncertainty modeling},
url = {http://dx.doi.org/10.1016/j.inffus.2025.104085},
volume = {129},
year = {2026}
}
TY - JOUR
AB - Accurate brain tumor segmentation from MRI scans is critical for effective diagnosis and treatment planning. Recent advances in deep learning have significantly improved brain tumor segmentation performance. However, these models still face challenges in clinical adoption due to their inherent uncertainties and potential for errors. In this paper, we propose a novel MR brain tumor segmentation approach that integrates multi-modal data fusion and uncertainty quantification to improve the accuracy and reliability of brain tumor segmentation. Recognizing that each MR modality contributes unique insights into the tumor’s characteristics, we propose a novel modality-aware guidance by explicitly categorizing the modalities into ”teacher” (FLAIR and T1c) and ”student” (T2 and T1) groups. Since the teacher modalities are the most informative modalities for identifying brain tumors, we propose a multi-modal teacher-student fusion strategy. This strategy leverages the teacher modalities to guide the student modalities in both spatial and channel feature representation aspects. To address prediction reliability, we employ Monte Carlo dropout during training to generate multiple uncertainty estimates. Additionally, we develop a novel uncertainty-aware loss function that optimizes segmentation accuracy while quantifying the uncertainty in predictions. Experimental results conducted on three BraTS datasets demonstrate the effectiveness of the proposed components and the superior performance compared to the state-of-the-art methods, highlighting their potential for clinical application.
AU - Zhou,T
AU - Li,M
AU - Ruan,S
AU - Luo,T
AU - Jiang,B
AU - Zhu,J
AU - Ma,P
AU - Yang,D
AU - Yang,G
DO - 10.1016/j.inffus.2025.104085
PY - 2026///
SN - 1566-2535
TI - A reliable framework for brain tumor segmentation via multi-modal fusion and uncertainty modeling
T2 - Information Fusion
UR - http://dx.doi.org/10.1016/j.inffus.2025.104085
VL - 129
ER -