Parkinson's Disease Detection from fMRI-Derived Brainstem Regional Functional Connectivity Networks

摘要

Parkinson's disease is the second most prevalent neurode-generative disorder after Alzheimer's disease. The brainstem, despite its early and crucial involvement in Parkinson's disease, is largely unexplored in the domain of functional medical imaging. Here we propose a data-driven, connectivity-pattern based framework to extract functional sub-regions within the brainstem and devise a machine learning based tool that can discriminate Parkinson's disease from healthy participants. We first propose a novel framework to generate a group model of brainstem functional sub-regions by optimizing a community quality function, and generate a brainstem regional network. We then extract graph theoretic features from this brainstem regional network and, after employing an SVM classifier, achieve a sensitivity of disease detection of 94% - comparable to approaches that normally require whole-brain analysis. To the best of our knowledge, this is the first study that employs brainstem functional sub-regions for Parkinson's disease detection.