Non-Rigid Image Registration Using Self-Supervised Fully Convolutional Networks without Training Data

TL;DR

This paper introduces a self-supervised, fully convolutional network-based method for non-rigid image registration that does not require training data with known transformations, achieving superior results on 3D brain MRI images.

Contribution

It presents a novel self-supervised deep learning approach for non-rigid image registration that directly estimates transformations without relying on pre-labeled training data.

Findings

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

Employs multi-resolution framework for improved accuracy

Learns spatial transformations through self-supervision without training data

Abstract

A novel non-rigid image registration algorithm is built upon fully convolutional networks (FCNs) to optimize and learn spatial transformations between pairs of images to be registered in a self-supervised learning framework. 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. The image registration is implemented in a multi-resolution image registration framework to jointly optimize and learn spatial transformations and FCNs at different spatial resolutions with deep self-supervision through typical feedforward and backpropagation computation. 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.