We have applied techniques from differential motion estimation to the problem of automatic elastic registration of medical images. This method models the mapping between images as a locally affine but globally smooth warp. The mapping also explicitly accounts for variations in image intensities. This approach is simple and highly effective across a broad range of medical images. We show the eff...

In this paper, different automatic registration schemes based on different optimization techniques in conjunction with different similarity measures are compared in terms of accuracy and efficiency. Results from every optimization procedure are quantitatively evaluated with respect to the manual registration, which is the standard registration method used in clinical practice. The comparison ha...

A multiscale image registration technique is presented for the registration of medical images that contain significant levels of noise. An overview of the medical image registration problem is presented, and various registration techniques are discussed. Experiments using mean squares, normalized correlation, and mutual information optimal linear registration are presented that determine the no...

This thesis investigates the employment of different entropic measures, including Rényi entropy, in the context of image registration. Specifically, we focus on the entropy estimation problem for image registration and provide theoretical and experimental comparisons of two important entropy estimators: the plug-in estimator and minimal entropic graphs. We further develop an image registration ...

To register two images means to align them so that common features overlap and differences — for example, a tumor that has grown— are readily apparent. Being able to easily spot differences between two images is obviously very important in applications. This paper is an introduction to image registration as applied to medical imaging. We first define image registration, breaking the problem dow...

We present a method to predict image deformations based on patch-wise image appearance. Specifically, we design a patch-based deep encoder-decoder network which learns the pixel/voxel-wise mapping between image appearance and registration parameters. Our approach can predict general deformation parameterizations, however, we focus on the large deformation diffeomorphic metric mapping (LDDMM) re...

Medical imaging sensors can be used to noninvasively probe tissue morphology and monitor material deformations associated with growth, disease, or normal physiology. Deformable image registration provides a framework for extracting and quantifying this information. Image registration is, however, an inherently ill-posed inverse problem. The research in this dissertation investigates techniques ...