Rapid calculation of functional maps of glucose metabolic rate and individual model rate parameters from serial 2-FDG images

The authors have developed a method for the rapid pixel-by-pixel estimation of glucose metabolic rate from a dynamic sequence of PCT images acquired over 40 minutes following venous bolus injection of 2-deoxy-2-fluoro-D-glucose (2-FDG). The calculations are based on the conventional four parameter model. The dephosphorylation rate (k/sub 4/) cannot be reliably estimated from only 40 minutes of data; however, neglecting dephosphorylation can nonetheless introduce significant biases into the parameter estimation processes. In the authors' method, the rate is constrained to fall within a small range about a presumed value. Computer simulation studies show that this constraint greatly reduces the systematic biases in the other three fitted parameters and in the metabolic rate that arise from the assumption of no dephosphorylation. The parameter estimation scheme used is formally identical to one originally developed for dynamic methods of cerebral blood flow estimation. Estimation of metabolic rate and the individual model rate parameters k/sub 1/, k/sub 2/, and k/sub 3/, can be carried out for each pixel sequence of a 100 x 100 pixel image in less than two minutes on our PDP 11/60 minicomputer with floating point processor. While the maps of k/sub 2/ amd k/sub 3/ are quite noisy, accurate estimates of average values can be attained for regions of a few cm/sup 2/. The maps of metabolic rate offer many advantages in addition to that of direct visualization. These include improved statistical precision and the avoidance of averaging failure in the fitting of heterogeneous regions