Parametric FDG PET Quantification, Segmentation and Classification of Primary Brain Tumors in Human GBM

Distinguishing tumor progression (TP) vs treatment related necrosis (TN) is critical for clinical management decisions in patients with glioblastoma (GBM). FDG PET is an imaging technique that can provide pathophysiologic and diagnostic data in this clinical setting. We are investigating novel methods using a model corrected blood input function accounting for partial volume averaging and peak fitting cost function to compute parametric maps that reveal more kinetic information. In our study, we use a 4-parameter 3-compartmentmodel on dynamic FDG PET data. To highlight the usefulness of these novel mappings, we created a preliminary prediction algorithm using logistic regression that uses averaged tumor information from these maps. Our preliminary results of tumor segmentation and classification using logistic regression on high resolution parametric PET data are promising in the differentiation of TN from TP in GBM patients based on relevant connections between certain kinetic parameters and the binary prediction outputs.