Hierarchical Brain Structure Modeling for Predicting Genotype of Glioma

TL;DR

This paper introduces Hi-SMGNN, a hierarchical neural network framework that combines structural and morphological brain connectomes to improve the prediction of IDH mutation status in glioma patients, addressing limitations of existing methods.

Contribution

The paper presents a novel hierarchical framework that models multiscale brain connectomes with multimodal interaction and personalized modular partitioning, enhancing prediction accuracy and interpretability.

Findings

Outperforms baseline and state-of-the-art models

Demonstrates improved robustness and effectiveness

Validates on UCSF-PDGM dataset

Abstract

Isocitrate DeHydrogenase (IDH) mutation status is a crucial biomarker for glioma prognosis. However, current prediction methods 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.