QUANTIFYING DEFORMATION USING INFORMATION THEORY: THE LOG-UNBIASED NONLINEAR REGISTRATION
Igor Yanovsky, Ming-Chang Chiang, Paul M. Thompson, Andrea D. Klunder, James T. Becker, Simon W. Davis, Arthur W. Toga, Alex Leow · 2007
In the past decade, information theory has been studied extensively in medical imaging. In particular, maximization of mutual information has been shown to yield good results in multi-modal image registration. In this paper, we apply information theory to quantifying the magnitude of deformations. We examine the statistical distributions of Jacobian maps in the logarithmic space, and develop a new framework for constructing image registration methods. The proposed framework yields both theoretically and intuitively correct deformation maps, and is compatible with large-deformation models. In the results section, we tested the proposed method using a pair of serial MRI images. We compared our results to those computed using the viscous fluid registration method, and demonstrated that the proposed method is advantageous when recovering voxel-wise local tissue change