DeepAI AI Chat
Log In Sign Up

Conditional Deformable Image Registration with Convolutional Neural Network

by   Tony C. W. Mok, et al.

Recent deep learning-based methods have shown promising results and runtime advantages in deformable image registration. However, analyzing the effects of hyperparameters and searching for optimal regularization parameters prove to be too prohibitive in deep learning-based methods. This is because it involves training a substantial number of separate models with distinct hyperparameter values. In this paper, we propose a conditional image registration method and a new self-supervised learning paradigm for deep deformable image registration. By learning the conditional features that correlated with the regularization hyperparameter, we demonstrate that optimal solutions with arbitrary hyperparameters can be captured by a single deep convolutional neural network. In addition, the smoothness of the resulting deformation field can be manipulated with arbitrary strength of smoothness regularization during inference. Extensive experiments on a large-scale brain MRI dataset show that our proposed method enables the precise control of the smoothness of the deformation field without sacrificing the runtime advantage or registration accuracy.


Conditional Deformable Image Registration with Spatially-Variant and Adaptive Regularization

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

Deformable Image Registration with Deep Network Priors: a Study on Longitudinal PET Images

Longitudinal image registration is challenging and has not yet benefited...

Unsupervised diffeomorphic cardiac image registration using parameterization of the deformation field

This study proposes an end-to-end unsupervised diffeomorphic deformable ...

Learning the Effect of Registration Hyperparameters with HyperMorph

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

HyperMorph: Amortized Hyperparameter Learning for Image Registration

We present HyperMorph, a learning-based strategy for deformable image re...

Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration

Deterministic approaches using iterative optimisation have been historic...

Train smarter, not harder: learning deep abdominal CT registration on scarce data

Purpose: This study aims to explore training strategies to improve convo...