Deep Learning for Regularization Prediction in Diffeomorphic Image Registration

TL;DR

This paper introduces a deep learning model that automatically predicts regularization parameters for diffeomorphic image registration, reducing manual tuning effort and improving efficiency in both 2D and 3D image datasets.

Contribution

The paper presents a novel CNN-based framework that predicts registration regularization parameters in a low-dimensional bandlimited space, enhancing efficiency and accuracy.

Findings

Accurately predicts regularization parameters for image registration

Reduces time and memory consumption in training

Effective on both synthetic and real brain images

Abstract

This paper presents a predictive model for estimating regularization parameters of diffeomorphic image registration. We introduce a novel framework that automatically determines the parameters controlling the smoothness of diffeomorphic transformations. Our method significantly reduces the effort of parameter tuning, which is time and labor-consuming. To achieve the goal, we develop a predictive model based on deep convolutional neural networks (CNN) that learns the mapping between pairwise images and the regularization parameter of image registration. In contrast to previous methods that estimate such parameters in a high-dimensional image space, our model is built in an efficient bandlimited space with much lower dimensions. We demonstrate the effectiveness of our model on both 2D synthetic data and 3D real brain images. Experimental results show that our model not only predicts appropriate regularization parameters for image registration, but also improving the network training in terms of time and memory efficiency.