ICA-Based Segmentation of the Brain on Perfusion Data.

摘要

An Independent Component Analysis (ICA) based segmentation technique is presented allowing the quantitative assessment of cerebral blood volume (CBV), cerebral blood flow (CBF) and mean transit time (MTT) from dynamic susceptibility contrast magnetic resonance (MR) images of the brain. Tissue types such as gray matter (GM), white matter (WM), and pathology appear as different ICA components as a result of their distinct temporal response to the first passage of contrast agent through the brain. The average CBV, CBF, and MTT values calculated for each component/tissue type could help evaluate the evolution of pathology and provide the opportunity for intersubject comparisons.