SFC-GAN: A Generative Adversarial Network for Brain Functional and Structural Connectome Translation

2025-01-13

AI Summary

In neuroscience, structural connectivity (SC) and functional connectivity (FC) are often acquired separately, and existing models typically support only unidirectional mapping or single-modality modeling, lacking robust bidirectional translation. This work proposes the first SC↔FC bidirectional translation framework for connectomics, built upon an enhanced CycleGAN architecture. We incorporate 2D convolutions to explicitly model the spatial structure of connectivity matrices and introduce a structure-preserving loss that enforces graph symmetry and topological integrity. Evaluated on multiple public datasets, our method significantly outperforms baselines in connection-wise similarity, graph-theoretic metrics (e.g., global efficiency, modularity), and downstream disease classification tasks. The synthesized connectomes exhibit high fidelity and functional interpretability. This framework provides a reliable cross-modal inference tool for single-modality brain connectome studies, enabling principled integration of structural and functional neuroimaging data.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Modern brain imaging technologies have enabled the detailed reconstruction of human brain connectomes, capturing structural connectivity (SC) from diffusion MRI and functional connectivity (FC) from functional MRI. Understanding the intricate relationships between SC and FC is vital for gaining deeper insights into the brain's functional and organizational mechanisms. However, obtaining both SC and FC modalities simultaneously remains challenging, hindering comprehensive analyses. Existing deep generative models typically focus on synthesizing a single modality or unidirectional translation between FC and SC, thereby missing the potential benefits of bi-directional translation, especially in scenarios where only one connectome is available. Therefore, we propose Structural-Functional Connectivity GAN (SFC-GAN), a novel framework for bidirectional translation between SC and FC. This approach leverages the CycleGAN architecture, incorporating convolutional layers to effectively capture the spatial structures of brain connectomes. To preserve the topological integrity of these connectomes, we employ a structure-preserving loss that guides the model in capturing both global and local connectome patterns while maintaining symmetry. Our framework demonstrates superior performance in translating between SC and FC, outperforming baseline models in similarity and graph property evaluations compared to ground truth data, each translated modality can be effectively utilized for downstream classification.

Problem

• Structural Connectivity
• Functional Connectivity
• Bidirectional Conversion

Innovation

• SFC-GAN
• bidirectional conversion
• structural integrity loss