A Foundation Model for Lesion Segmentation on Brain MRI With Mixture of Modality Experts
IEEE Transactions on Medical Imaging · 2025-06 · 44 (6) · 2594-2604
DOI: 10.1109/tmi.2025.3540809 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-06. Verfasst von Xinru Zhang und 9 weiteren Autor:innen. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: Beijing Municipal Natural Science Foundation, Xiaomi Young Scholars Program, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Brain lesion segmentation is crucial for neurological disease research and diagnosis. As different types of lesions exhibit distinct characteristics on different imaging modalities, segmentation methods are typically developed in a task-specific manner, where each segmentation model is tailored to a specific lesion type and modality. However, the use of task-specific models requires predetermination of the lesion type and imaging modality, which complicates their deployment in real-world scenarios. In this work, we propose a universal foundation model for brain lesion segmentation on magnetic resonance imaging (MRI), which can automatically segment different types of brain lesions given input of various MRI modalities. We develop a novel Mixture of Modality Experts (MoME) framework with multiple expert networks attending to different imaging modalities. A hierarchical gating network is proposed to combine the expert predictions and foster expertise collaboration. Moreover, to avoid the degeneration of each expert network, we introduce a curriculum learning strategy during training to preserve the specialisation of each expert. In addition to MoME, to handle the combination of multiple input modalities, we propose MoME+, which uses a soft dispatch network for input modality routing. We evaluated the proposed method on nine brain lesion datasets, encompassing five imaging modalities and eight lesion types. The results show that our model outperforms state-of-the-art universal models for brain lesion segmentation and achieves promising generalisation performance onto unseen datasets.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Beijing Municipal Natural Science Foundation
- Xiaomi Young Scholars Program
- Fundamental Research Funds for the Central Universities
- Engineering and Physical Sciences Research Council
Zitieren
APA
Zhang, X., Ou, N., Doga Basaran, B., Visentin, M., Qiao, M., Gu, R., Matthews, P. M., Liu, Y., Ye, C., & Bai, W. (2025). A Foundation Model for Lesion Segmentation on Brain MRI With Mixture of Modality Experts. IEEE Transactions on Medical Imaging, 44(6), 2594-2604. https://doi.org/10.1109/tmi.2025.3540809
Vancouver
Zhang X, Ou N, Doga Basaran B, Visentin M, Qiao M, Gu R, et al. A Foundation Model for Lesion Segmentation on Brain MRI With Mixture of Modality Experts. IEEE Transactions on Medical Imaging. 2025;44(6):2594-2604. doi:10.1109/tmi.2025.3540809
BibTeX
@article{Zhang2025,
author = {Zhang, Xinru and Ou, Ni and Doga Basaran, Berke and Visentin, Marco and Qiao, Mengyun and Gu, Renyang and Matthews, Paul M and Liu, Yaou and Ye, Chuyang and Bai, Wenjia},
title = {A Foundation Model for Lesion Segmentation on Brain MRI With Mixture of Modality Experts},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
volume = {44},
number = {6},
pages = {2594--2604},
doi = {10.1109/tmi.2025.3540809}
}
EUVIMED