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

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 [11C]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.