BINDER: A Latent Variable Model for Probabilistic Medical Image Registration
Organizations: Copenhagen Research Centre for Biological and Precision Psychiatry, Mental Health Centre Copenhagen, Copenhagen University Hospital, Denmark, and the Pioneer Centre for Artificial Intelligence, University of Copenhagen, Denmark · Department of Neuroscience and Biomedical Engineering, Aalto University, Finland · Department of Experimental Psychology, Division of Psychology and Language Sciences, University College London · Departments of Neuroscience and Biomedical Engineering and of Computer Science at Aalto University, Finland
Abstract
We propose a new probabilistic model for general-purpose medical image registration that builds upon the mutual information registration criterion. It centers around a spatial interpolation technique that assumes latent voxel-wise correspondences between the images being registered. By exploiting these latent variables, we derive dedicated optimization and MCMC sampling techniques that only involve closed-form iterative updates. When applied to nonlinear registration, an efficient demons-like optimization algorithm is obtained that shows robust out-of-the-box performance across a variety of monomodal and multimodal registration tasks. We also demonstrate a corresponding sampler that can quantify, for the first time, uncertainty in multimodal registration scenarios with very high-dimensional 3D deformations. Our code, which we call BINDER (Bayesian INference for DEformable Registration), is freely available at https://github.com/ste93ste/BINDER.