Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces

8 Mar 2019  ·  Adrian V. Dalca, Guha Balakrishnan, John Guttag, Mert R. Sabuncu ·

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Diffeomorphic Medical Image Registration OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP VoxelMorph-diff Dice (Average) 0.754 # 2
GPU sec 0.47 # 3
CPU (sec) 84.2 # 3
Neg Jacob Det 0.2 # 2
Dice (SE) 0.139 # 3

Methods


No methods listed for this paper. Add relevant methods here