Graph-Regularized Manifold-Aware Conditional Wasserstein GAN for Brain Functional Connectivity Generation
This work addresses the challenge of generating realistic brain network data for medical applications like disorder classification, though it appears incremental as it builds on existing GAN frameworks with domain-specific adaptations.
The paper tackles the problem of generating brain functional connectivity (FC) data, which has inherent geometric structure as semi-positive definite matrices on a Riemannian manifold, by proposing a graph-regularized manifold-aware conditional Wasserstein GAN (GR-SPD-GAN). The method outperforms state-of-the-art GANs in generating realistic FC samples and, when used for data augmentation in major depressive disorder identification, achieved the largest improvement in classification accuracy among competing approaches.
Common measures of brain functional connectivity (FC) including covariance and correlation matrices are semi-positive definite (SPD) matrices residing on a cone-shape Riemannian manifold. Despite its remarkable success for Euclidean-valued data generation, use of standard generative adversarial networks (GANs) to generate manifold-valued FC data neglects its inherent SPD structure and hence the inter-relatedness of edges in real FC. We propose a novel graph-regularized manifold-aware conditional Wasserstein GAN (GR-SPD-GAN) for FC data generation on the SPD manifold that can preserve the global FC structure. Specifically, we optimize a generalized Wasserstein distance between the real and generated SPD data under an adversarial training, conditioned on the class labels. The resulting generator can synthesize new SPD-valued FC matrices associated with different classes of brain networks, e.g., brain disorder or healthy control. Furthermore, we introduce additional population graph-based regularization terms on both the SPD manifold and its tangent space to encourage the generator to respect the inter-subject similarity of FC patterns in the real data. This also helps in avoiding mode collapse and produces more stable GAN training. Evaluated on resting-state functional magnetic resonance imaging (fMRI) data of major depressive disorder (MDD), qualitative and quantitative results show that the proposed GR-SPD-GAN clearly outperforms several state-of-the-art GANs in generating more realistic fMRI-based FC samples. When applied to FC data augmentation for MDD identification, classification models trained on augmented data generated by our approach achieved the largest margin of improvement in classification accuracy among the competing GANs over baselines without data augmentation.