Conditional Deformable Image Registration with Convolutional Neural Network

TL;DR

This paper introduces a conditional deep learning approach for deformable image registration that allows for flexible regularization control during inference, reducing the need for multiple model trainings.

Contribution

It proposes a novel self-supervised learning paradigm that captures optimal registration solutions across various hyperparameters within a single model.

Findings

Enables precise control of deformation smoothness during inference.

Maintains high registration accuracy and runtime efficiency.

Reduces the need for training multiple models for different hyperparameters.

Abstract

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 are 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.