Non-rigid image registration using fully convolutional networks with deep self-supervision

TL;DR

This paper introduces a deep learning-based non-rigid image registration method using fully convolutional networks that directly estimates spatial transformations between image pairs, achieving superior performance on 3D brain MRI data.

Contribution

It presents a novel registration approach that learns spatial transformations directly from image pairs with deep self-supervision, avoiding reliance on pre-known transformations.

Findings

Outperforms state-of-the-art registration algorithms on 3D brain MRI data

Enables direct registration of new images without additional optimization

Uses multi-resolution framework with deep self-supervision for improved accuracy

Abstract

We propose a novel non-rigid image registration algorithm that is built upon fully convolutional networks (FCNs) to optimize and learn spatial transformations between pairs of images to be registered. Different from most existing deep learning based image registration methods that learn spatial transformations from training data with known corresponding spatial transformations, our method directly estimates spatial transformations between pairs of images by maximizing an image-wise similarity metric between fixed and deformed moving images, similar to conventional image registration algorithms. At the same time, our method also learns FCNs for encoding the spatial transformations at the same spatial resolution of images to be registered, rather than learning coarse-grained spatial transformation information. The image registration is implemented in a multi-resolution image registration framework to jointly optimize and learn spatial transformations and FCNs at different resolutions with deep self-supervision through typical feedforward and backpropagation computation. Since our method simultaneously optimizes and learns spatial transformations for the image registration, our method can be directly used to register a pair of images, and the registration of a set of images is also a training procedure for FCNs so that the trained FCNs can be directly adopted to register new images by feedforward computation of the learned FCNs without any optimization. The proposed method has been evaluated for registering 3D structural brain magnetic resonance (MR) images and obtained better performance than state-of-the-art image registration algorithms.