TY - GEN
T1 - Hierarchical Brain Structure Modeling for Predicting Genotype of Glioma
AU - Tang, Haotian
AU - Chen, Jianwei
AU - Tang, Xinrui
AU - Wu, Yunjia
AU - Miao, Zhengyang
AU - Li, Chao
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - Isocitrate DeHydrogenase (IDH) mutation status is a crucial biomarker for glioma prognosis. However, current prediction are limited by the low availability and noise of functional MRI. Structural and morphological connectomes offer a non-invasive alternative, yet existing approaches often ignore the brain’s hierarchical organisation and multiscale interactions. To address this, we propose Hi-SMGNN, a hierarchical framework that integrates structural and morphological connectomes from regional to modular levels. It features a multimodal interaction module with a Siamese network and cross-modal attention, a multiscale feature fusion mechanism for reducing redundancy, and a personalised modular partitioning strategy to enhance individual specificity and interpretability. Experiments on the UCSF-PDGM dataset demonstrate that Hi-SMGNN outperforms baseline and state-of-the-art models, showing improved robustness and effectiveness in IDH mutation prediction.
AB - Isocitrate DeHydrogenase (IDH) mutation status is a crucial biomarker for glioma prognosis. However, current prediction are limited by the low availability and noise of functional MRI. Structural and morphological connectomes offer a non-invasive alternative, yet existing approaches often ignore the brain’s hierarchical organisation and multiscale interactions. To address this, we propose Hi-SMGNN, a hierarchical framework that integrates structural and morphological connectomes from regional to modular levels. It features a multimodal interaction module with a Siamese network and cross-modal attention, a multiscale feature fusion mechanism for reducing redundancy, and a personalised modular partitioning strategy to enhance individual specificity and interpretability. Experiments on the UCSF-PDGM dataset demonstrate that Hi-SMGNN outperforms baseline and state-of-the-art models, showing improved robustness and effectiveness in IDH mutation prediction.
KW - graph learning
KW - Isocitrate Dehydrogenase
KW - Morphological connectome
KW - Multimodal
KW - Structure connectome
UR - https://www.scopus.com/pages/publications/105018804542
U2 - 10.1007/978-3-032-06624-4_17
DO - 10.1007/978-3-032-06624-4_17
M3 - Conference contribution
AN - SCOPUS:105018804542
SN - 9783032066237
VL - 16178
T3 - Lecture Notes in Computer Science
SP - 160
EP - 169
BT - Computational Mathematics Modeling in Cancer Analysis - 4th International Workshop, CMMCA 2025, Held in Conjunction with MICCAI 2025, Proceedings
A2 - Li, Chao
A2 - Qin, Wenjian
A2 - Wu, Jia
A2 - Zaki, Nazar
PB - Springer Science and Business Media Deutschland GmbH
CY - Switzerland
T2 - 4th International Workshop on Computational Mathematics Modeling in Cancer Analysis, CMMCA 2025, Held in Conjunction with the 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
Y2 - 27 September 2025 through 27 September 2025
ER -