Novel deep learning approaches for functional FMRI data analysis

Abstract

Functional MRI (fMRI) has revolutionized our ability to analyze brain activity by providing insights into high-dimensional, time-series data. Despite advancements, existing methods often fall short in their ability to effectively capture contextual representations across varying time scales and interpret the resulting data. Addressing these challenges, this thesis introduces three innovative ap-proaches: BolT, GraphCorr, and DreaMR, each designed to enhance the analysis and interpretability of fMRI data. BolT represents a significant advancement in modeling fMRI time series by utilizing a blood-oxygen-level-dependent trans-former architecture. This model incorporates a novel fused window attention mechanism, which enables the extraction of both local and global representations by processing temporally-overlapped windows and employing cross-window regularization. BolT’s approach improves upon existing methods, offering enhanced sensitivity and aligning with key neuroscientific findings through extensive experimentation. GraphCorr addresses limitations in static functional connectivity (FC) features used in classification models by introducing a graph neural network-based plug-in. This method captures dynamic latent FC features while preserving dimensional efficiency, employing a node embedder and lag filter module to re-fine temporal information. The integration of these features through a message passing algorithm significantly enhances the performance of baseline classification models, as demonstrated through comprehensive testing on public datasets. Finally, DreaMR tackles the interpretability of deep fMRI classifiers through a novel diffusion-driven counterfactual approach. By using fractional multi-phase-distilled diffusion, DreaMR generates high-fidelity counterfactual samples and employs a transformer architecture to account for long-range spatiotemporal contexts. This method surpasses traditional counterfactual techniques in both fidelity and efficiency, offering a more precise and actionable explanation of classifier decisions. Together, these contributions advance the field of fMRI analysis by improving model performance and interpretability, thereby facilitating more effective and insightful neuroimaging research.