Learning a Model-Driven Variational Network for Deformable Image Registration

by   Xi Jia, et al.

Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this whilst retaining the fast inference speed of deep learning, we propose VR-Net, a novel cascaded variational network for unsupervised deformable image registration. Using the variable splitting optimization scheme, we first convert the image registration problem, established in a generic variational framework, into two sub-problems, one with a point-wise, closed-form solution while the other one is a denoising problem. We then propose two neural layers (i.e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net to formulate the denoising problem (i.e. generalized denoising layer). Finally, we cascade the warping layer, intensity consistency layer, and generalized denoising layer to form the VR-Net. Extensive experiments on three (two 2D and one 3D) cardiac magnetic resonance imaging datasets show that VR-Net outperforms state-of-the-art deep learning methods on registration accuracy, while maintains the fast inference speed of deep learning and the data-efficiency of variational model.



There are no comments yet.


page 1

page 3

page 6

page 10


Enhancing Label-Driven Deep Deformable Image Registration with Local Distance Metrics for State-of-the-Art Cardiac Motion Tracking

While deep learning has achieved significant advances in accuracy for me...

Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration

Deterministic approaches using iterative optimisation have been historic...

CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning

Image registration is a fundamental building block for various applicati...

F3RNet: Full-Resolution Residual Registration Network for Multimodal Image Registration

Multimodal deformable image registration is essential for many image-gui...

VS-Net: Variable splitting network for accelerated parallel MRI reconstruction

In this work, we propose a deep learning approach for parallel magnetic ...

Most Likely Separation of Intensity and Warping Effects in Image Registration

This paper introduces a class of mixed-effects models for joint modeling...

Iterative Residual Network for Deep Joint Image Demosaicking and Denoising

Modern digital cameras rely on sequential execution of separate image pr...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.