Rigid multimodal/multispectral image registration based on the expectation-maximization algorithm

In this paper, we present a novel methodology for multimodal/ multispectral rigid image registration. The proposed approach is formulated by using the Expectation-Maximization (EM) technique in order to estimate a geometric transformation that aligns the multiparametric images to register. In this approach, the images alignment relies on hidden stochastic random variables which allow to compare the multiparametric intensity values between images of different modalities. The methodology is basically composed by an EM-technique approach, where at each step, a new estimation of the joint conditional multispectral intensity distribution and the rigid transformation are computed. The proposed algorithm was tested with different kinds of medical images; our results show that the proposed methodology is a good alternative for rigid multimodal/multispectral registration. © Springer International Publishing Switzerland 2014.

Image registration; Image segmentation; Mathematical transformations; Maximum principle; Stochastic systems; Expectation Maximization; Expectation-maximization algorithms; Geometric transformations; Intensity distribution; Intensity values; Multi-spectral; Novel methodology; Rigid transformations; Medical imaging

VIVO