Evaluating Graph Signal Processing for Neuroimaging Through Classification and Dimensionality Reduction
This work addresses the challenge of decoding brain activity in neuroimaging, but it is incremental as it applies existing GSP techniques to this domain with specific graph comparisons.
The study tackled the problem of analyzing neuroimaging data by applying Graph Signal Processing (GSP) for dimensionality reduction and classification on fMRI datasets, showing that mixed graphs combining geometric structure and functional connectivity performed best and outperformed classical methods like PCA and ICA.
Graph Signal Processing (GSP) is a promising framework to analyze multi-dimensional neuroimaging datasets, while taking into account both the spatial and functional dependencies between brain signals. In the present work, we apply dimensionality reduction techniques based on graph representations of the brain to decode brain activity from real and simulated fMRI datasets. We introduce seven graphs obtained from a) geometric structure and/or b) functional connectivity between brain areas at rest, and compare them when performing dimension reduction for classification. We show that mixed graphs using both a) and b) offer the best performance. We also show that graph sampling methods perform better than classical dimension reduction including Principal Component Analysis (PCA) and Independent Component Analysis (ICA).