Stochastic Inverse Consistent Registration

An essential goal in medical image registration is, the forward and reverse mapping matrices should be inverse to each other, i.e., inverse consistent. Conventional approaches enforce such consistency in deterministic fashions, either through incorporation of sub-objective cost function to impose consistent property during the registration process or by construction of consistent mapping on predetermined landmarks sets. Assuming that the initial forward and reverse matching matrices have been computed and used as the inputs to our system, this paper presents a stochastic framework which yields perfect consistent registration. During the optimization process to reach the perfect consistency, we model the errors of the registration matrices and the imperfectness of the consistent constraint as stochastic processes. An iterative generalized total least square (GTLS) strategy has been developed so that consistency is optimally imposed