Abstract
In this paper, we propose a new feature selection method to exploit the issue of High Dimension Low Sample Size (HDLSS) for the prediction of Mild Cognitive Impairment (MCI) conversion. Specially, by regarding the Magnetic Resonance Imaging (MRI) information of MCI subjects as the target data, this paper proposes to integrate auxiliary information with the target data
in a unified feature selection framework for distinguishing progressive MCI (pMCI) subjects from
stable MCI (sMCI) subjects, i.e., the MCI conversion classification for short in this paper, based on
their MRI information. The auxiliary information
includes the Positron Emission Tomography (PET)
information of the target data, the MRI information
of Alzheimer’s Disease (AD) subjects and Normal
Control (NC) subjects, and the ages of the target
data and the AD and NC subjects. As a result, the
proposed method jointly selects features from the
auxiliary data and the target data by taking into account the influence of outliers and aging of these
two kinds of data. Experimental results on the public data of Alzheimer’s Disease Neuroimaging Initiative (ADNI) verified the effectiveness of our proposed method, compared to three state-of-the-art
feature selection methods, in terms of four classification evaluation metrics