Classification Based on Neuroimaging Data by Tensor Boosting

Recent advances in medical imaging technologies generate a high volume of imaging data. Classification of cognitive outcome and disease status based on brain images is one of the most important tasks in neuroimaging studies. However it poses great challenge to the current classification methods due to the extremely high dimensionality and low signal to noise ratio in brain image data. In this article we propose a tensor boosting algorithm for classification based on neuroimaging data. The method is off-the-shelf, computationally simple and amenable to various modalities of neuroimaging data. The method is applied to an EEG data set from an alcoholism study and an MRI data set from an ADHD Global Competition and shows significantly improved classification performance.