GradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency

learning regular spatial
regular spatial transformations
present an approach
approach to learning
learning regular
Author

Lin Tian, Hastings Greer, Francois-Xavier Vialard, Roland Kwitt, Raul San Jose Estepar, Richard Jarrett Rushmore, Nikolaos Makris, Sylvain Bouix, Marc Niethammer

Published

April 30, 2023

Abstract:

We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration. Contrary to optimization-based registration techniques and many modern learning-based methods, we do not directly penalize transformation irregularities but instead promote transformation regularity via an inverse consistency penalty. We use a neural network to predict a map between a source and a target image as well as the map when swapping the source and target images. Different from existing approaches, we compose these two resulting maps and regularize deviations of the Jacobian of this composition from the identity matrix. This regularizer - GradICON - results in much better convergence when training registration models compared to promoting inverse consistency of the composition of maps directly while retaining the desirable implicit regularization effects of the latter. We achieve state-of-the-art registration performance on a variety of real-world medical image datasets using a single set of hyperparameters and a single non-dataset-specific training protocol. Code is available at https://github.com/uncbiag/ICON.