VoxelMorph: A Learning Framework for Deformable Medical Image Registration

We present VoxelMorph, a fast, unsupervised, learning-based algorithm for deformable pairwise medical image registration. Traditional registration methods optimize an objective function independently for each pair of images, which is time-consuming for large datasets. We define registration as a parametric function, implemented as a convolutional neural network (CNN). We optimize its global parameters given a set of images from a collection of interest. Given a new pair of scans, VoxelMorph rapidly computes a deformation field by directly evaluating the function. Our model is flexible, enabling the use of any differentiable objective function to optimize these parameters. In this work, we propose and extensively evaluate a standard image matching objective function as well as an objective function that can use auxiliary data such as anatomical segmentations available only at training time. We demonstrate that the unsupervised model's accuracy is comparable to state-of-the-art methods, while operating orders of magnitude faster. We also show that VoxelMorph trained with auxiliary data significantly improves registration accuracy at test time. Our method promises to significantly speed up medical image analysis and processing pipelines, while facilitating novel directions in learning-based registration and its applications. Our code is freely available at voxelmorph.csail.mit.edu.