Multimodal Sheaf-based Network for Glioblastoma Molecular Subtype Prediction

2025-08-13

AI Summary

To address key challenges in glioblastoma molecular subtype prediction—including difficulty in sharing structural information across multimodal (MRI and histopathology) data, loss of discriminative features in heterogeneous graphs, and insufficient reconstruction mechanisms under missing modalities—this paper proposes the first sheaf-theoretic multimodal fusion framework. Our method employs sheaf neural networks to explicitly model cross-modal structural consistency, integrates graph neural networks with a learnable structural reconstruction module, and preserves discriminative topological patterns within heterogeneous graphs. Crucially, it enables robust inference from single-modality inputs. Extensive experiments on multiple benchmark datasets demonstrate significant improvements over state-of-the-art methods, particularly under modality-missing scenarios, where it maintains high accuracy and generalizability. The code is publicly available. This work establishes a novel, interpretable, structure-aware paradigm for non-invasive “virtual biopsy.”

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Glioblastoma is a highly invasive brain tumor with rapid progression rates. Recent studies have shown that glioblastoma molecular subtype classification serves as a significant biomarker for effective targeted therapy selection. However, this classification currently requires invasive tissue extraction for comprehensive histopathological analysis. Existing multimodal approaches combining MRI and histopathology images are limited and lack robust mechanisms for preserving shared structural information across modalities. In particular, graph-based models often fail to retain discriminative features within heterogeneous graphs, and structural reconstruction mechanisms for handling missing or incomplete modality data are largely underexplored. To address these limitations, we propose a novel sheaf-based framework for structure-aware and consistent fusion of MRI and histopathology data. Our model outperforms baseline methods and demonstrates robustness in incomplete or missing data scenarios, contributing to the development of virtual biopsy tools for rapid diagnostics. Our source code is available at https://github.com/basiralab/MMSN/.

Problem

• Predicts glioblastoma molecular subtypes non-invasively
• Improves multimodal MRI-histopathology data fusion
• Handles missing or incomplete modality data robustly

Innovation

• Sheaf-based framework for multimodal fusion
• Structure-aware MRI and histopathology integration
• Robust handling of incomplete modality data