A method for optimizing MR imaging pulse sequence parameters in a stat
istical framework is presented. Parameters are defined to be optimal w
hen the resulting scalar images yield optimal image segmentations usin
g Bayesian pixel classification. Thus, Bayes risk is used as the objec
tive function to minimize. Approximations are made to give a tractable
solution in a four-step procedure. A sample calculation is carried ou
t to determine the optimal TR and flip angle for scalar SPGR imaging o
f the brain. Overall, this paper gives a new approach to optimize MRI
pulse sequences for the specific objective of improved image segmentat
ion.