Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
This addresses the need for efficient and reliable deformable registration in medical imaging, offering a principled solution that is incremental by building on existing methods.
The paper tackles the problem of fast and topology-preserving image and surface registration by introducing an unsupervised learning-based method that connects classical and learning-based approaches, achieving state-of-the-art accuracy with very fast runtimes on a 3D brain registration task.
Classical deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. However, these approaches use restricted deformation models, require supervised labels, or do not guarantee a diffeomorphic (topology-preserving) registration. Furthermore, learning-based registration tools have not been derived from a probabilistic framework that can offer uncertainty estimates. In this paper, we build a connection between classical and learning-based methods. We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs). We demonstrate our method on a 3D brain registration task for both images and anatomical surfaces, and provide extensive empirical analyses. Our principled approach results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees. Our implementation is available at http://voxelmorph.csail.mit.edu.