Medical image registration in computational intelligence framework: a review

The purpose of this paper is to provide a review of computational intelligence techniques and their application to medical image registration. Each computational intelligence technique is summarised and its utility to medical image registration is analysed. Genetic computation provides an efficient search methodology. Neural networks can learn complex nonlinear input-output relationships. Fuzzy sets use symbols to summarise the domain knowledge allowing them to handle inconsistent or noisy data and to produce understandable results. Rough sets offer tools to handle different types of uncertainty in data. Some challenges to medical image registration and the application of computational intelligence technologies are indicated.