Parkinson's disease (PD) is a common neurodegenerative disorder, which progresses slowly and affects the quality of life dramatically. In this paper, we use the T1 MRI and DTI data from the PPMI study to analyze the effect of each modality through investigating the brain regions, and determine which modality can be a better marker at diagnosing the disease. For this purpose, we propose a joint feature selection and max-margin classification framework, in which we select features that best benefit the classification scheme. Our results show that the brain structural connectivity studies using DTI leads to better results.
This abstract and the presentation materials are available to members only; a login is required.