Independent component analysis based assessment of linked gray and white matter in the initial stages of Alzheimer's disease using structural MRI phase images

Alzheimer's disease (AD) is a common form of dementia that is affecting the elderly population worldwide. We present here a novel approach based on independent component analysis (ICA) method to get useful features that are representative of the interrelationship among the structural magnetic resonance imaging (sMRI) brain voxels. ICA effectively considers the information inherent in the sMRI scans and provides information about the independent sources of brain that are affected during the course of progression of AD. Phase images summarize the complex relationship between gray and white matter in the brain. The results presented depicts interesting differences among the healthy elderly controls and elder patients belonging to early categories of AD with clinical dementia rating (CDR) of 0.5 and 1 for parahippocampus and other areas. The effects of socioeconomic factors on ICA features also shows the usefulness of sources that are preserved by ICA features. These interesting findings show the usefulness of ICA for feature extraction and analysis in AD research. In addition, the use of phase images for feature extraction have a clear advantage over other approaches that consider the relationship among gray and white matter intermittently.