A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration

HighlightsUnsupervised Deep Learning Image Registration (DLIR) is feasible for affine and deformable image registration.The method is unsupervised; no registration examples are necessary to train a ConvNet for image registration.Once a ConvNet is trained, image registration can be performed on unseen images in one‐shot.Registration, including image resampling, is near real‐time.Unsupervised DLIR yields image registration performance similar to a conventional approach. Graphical abstract Figure. No caption available. ABSTRACT Image registration, the process of aligning two or more images, is the core technique of many (semi‐)automatic medical image analysis tasks. Recent studies have shown that deep learning methods, notably convolutional neural networks (ConvNets), can be used for image registration. Thus far training of ConvNets for registration was supervised using predefined example registrations. However, obtaining example registrations is not trivial. To circumvent the need for predefined examples, and thereby to increase convenience of training ConvNets for image registration, we propose the Deep Learning Image Registration (DLIR) framework for unsupervised affine and deformable image registration. In the DLIR framework ConvNets are trained for image registration by exploiting image similarity analogous to conventional intensity‐based image registration. After a ConvNet has been trained with the DLIR framework, it can be used to register pairs of unseen images in one shot. We propose flexible ConvNets designs for affine image registration and for deformable image registration. By stacking multiple of these ConvNets into a larger architecture, we are able to perform coarse‐to‐fine image registration. We show for registration of cardiac cine MRI and registration of chest CT that performance of the DLIR framework is comparable to conventional image registration while being several orders of magnitude faster.