Non-Rigid Image Registration Using Self-Supervised Fully Convolutional Networks without Training Data
This addresses the problem of image registration in medical imaging without requiring labeled training data, representing a novel approach but with incremental improvements in performance.
The paper tackles non-rigid image registration by proposing a self-supervised fully convolutional network that learns spatial transformations without training data, achieving better performance than state-of-the-art methods on 3D brain MR images.
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.