Graph-based energy-minimization segmentation and PCA applied to internal carotid extraction in neurological PET

An unseeded, graph-theoretic segmentation algorithm based on Mumford-Shah energy minimization is applied to segmentation of brain FDG dynamic positron emission tomography data after preprocessing by principal component analysis, for the automated extraction of regions of interest, and, in particular, extraction of the internal carotid arteries and venous sinuses for the noninvasive estimation of the input plasma time activity curve. Evaluation on clinical FDG brain PET studies show that the internal carotids and venous sinuses can be robustly segmented in typical dynamic PET data sets, allowing for the fully automatic estimation of the arterial input curve.