This study used independent component analysis (ICA) to decompose the surrogate image data by concatenating in space multiple subjects' anatomical images after spatial normalization and smoothing to make all images in the same space. The multiple-subject anatomical image data included three different subject/patient populations, namely the Parkinson's disease (PD) and essential tremor (ET) as well as age-matched normal control (NC) subjects. In so doing, we were to extract the independent components showing significant group differences caused by the morphometric changes due to the neurological diseases. Such an independent component-based morphometry (ICBM) applied to both the grouped gray-matter and white-matter image data could be used to successfully reveal the brain areas within the gray and white matters showing significant group differences. In gray matter, we found a majority of basal ganglia brain areas associated with NC > PD, which well represented the causes of PD reported in the literature. In addition, the ICBM also found the brain areas of right superior temporal gyrus, right angular gyrus (BA 39), right inferior temporal gyrus, and left middle temporal gyrus (BA 37) associated with NC > ET. On the other hand, a more complicated patterns were found in the white matter associated with PD > ET and ET > PD conditions.