HyperMorph: Amortized Hyperparameter Learning for Image Registration

by   Andrew Hoopes, et al.

We present HyperMorph, a learning-based strategy for deformable image registration that removes the need to tune important registration hyperparameters during training. Classical registration methods solve an optimization problem to find a set of spatial correspondences between two images, while learning-based methods leverage a training dataset to learn a function that generates these correspondences. The quality of the results for both types of techniques depends greatly on the choice of hyperparameters. Unfortunately, hyperparameter tuning is time-consuming and typically involves training many separate models with various hyperparameter values, potentially leading to suboptimal results. To address this inefficiency, we introduce amortized hyperparameter learning for image registration, a novel strategy to learn the effects of hyperparameters on deformation fields. The proposed framework learns a hypernetwork that takes in an input hyperparameter and modulates a registration network to produce the optimal deformation field for that hyperparameter value. In effect, this strategy trains a single, rich model that enables rapid, fine-grained discovery of hyperparameter values from a continuous interval at test-time. We demonstrate that this approach can be used to optimize multiple hyperparameters considerably faster than existing search strategies, leading to a reduced computational and human burden and increased flexibility. We also show that this has several important benefits, including increased robustness to initialization and the ability to rapidly identify optimal hyperparameter values specific to a registration task, dataset, or even a single anatomical region - all without retraining the HyperMorph model. Our code is publicly available at http://voxelmorph.mit.edu.


page 1

page 2

page 3

page 4


Learning the Effect of Registration Hyperparameters with HyperMorph

We introduce HyperMorph, a framework that facilitates efficient hyperpar...

Conditional Deformable Image Registration with Convolutional Neural Network

Recent deep learning-based methods have shown promising results and runt...

GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration

Deep learning-based deformable registration methods have been widely inv...

Conditional Deformable Image Registration with Spatially-Variant and Adaptive Regularization

Deep learning-based image registration approaches have shown competitive...

CortexMorph: fast cortical thickness estimation via diffeomorphic registration using VoxelMorph

The thickness of the cortical band is linked to various neurological and...

FLO: Fast and Lightweight Hyperparameter Optimization for AutoML

Integrating ML models in software is of growing interest. Building accur...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset