Predicting Disease Status Using Imaging Data from Various Modalities

• Activity Number: 360
• Type: Contributed
• Date/Time: Tuesday, August 11, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Imaging
• Author(s): Wenqiong Xue* and DuBois Bowman and Jian Kang and Daniel Drake
• Companies: Boehringer Ingelheim and Columbia University and Emory University and Columbia University
• Keywords: Spatial model ; Functional Neuroimaging ; Structural Neuroimaging ; Prediction ; Parkison's disease

Abstract

Relating disease status to imaging data increases the clinical significance of neuroimaging studies. Many neurological and psychiatric disorders involve complex, systems-level alterations that manifest in functional and structural properties of the brain and possibly other clinical and biologic measures. We propose a Bayesian hierarchical model to predict the disease status using both functional and structural brain imaging scans. We consider a two-stage whole brain parcellation, partitioning the brain into more than 200 subregions, and our model accounts for spatial correlations between distinct brain regions. Our approach uses posterior predictive probabilities to perform prediction, and evaluate our method by examining the prediction accuracy rates based on cross validations. We apply our model to multimodal brain imaging data from a study of Parkinson's disease (PD) to classify subjects as either PD patients or healthy controls. We achieve extremely high accuracy, in general, and our model identifies key regions contributing to accurate prediction.