Simultaneous Segmentation, Kinetic Parameter Estimation, and Uncertainty Visualization of Dynamic PET Images

Abstract. We develop a segmentation technique for dynamic PET incorporating the physiological parameters for different regions via kinetic modeling. We demonstrate the usefulness of our technique on fifteen [11 C]Raclopride simulated PET images. We show qualitatively and quantitatively that the physiologically based algorithm outperforms two classical segmentation techniques. Further, we derive a formula to compute and visualize the uncertainty encountered during the segmentation.

• Type: Conference
• Year: 2007
• Where: MICCAI
• Authors: Ahmed Saad, Benjamin Smith 0002, Ghassan Hamarneh, Torsten Möller
• Keywords: Classical Segmentation Techniques, C]raclopride Simulated Pet, Medical Imaging, MICCAI 2007, Segmentation Technique