Zakeri, A orcid.org/0000-0002-6011-2333, Hokmabadi, A orcid.org/0000-0002-1407-4540, Bi, N orcid.org/0000-0002-7505-3997 et al. (6 more authors) (2023) DragNet: Learning-based deformable registration for realistic cardiac MR sequence generation from a single frame. Medical Image Analysis, 83. 102678. ISSN 1361-8415
Abstract
Deformable image registration (DIR) can be used to track cardiac motion. Conventional DIR algorithms aim to establish a dense and non-linear correspondence between independent pairs of images. They are, nevertheless, computationally intensive and do not consider temporal dependencies to regulate the estimated motion in a cardiac cycle. In this paper, leveraging deep learning methods, we formulate a novel hierarchical probabilistic model, termed DragNet, for fast and reliable spatio-temporal registration in cine cardiac magnetic resonance (CMR) images and for generating synthetic heart motion sequences. DragNet is a variational inference framework, which takes an image from the sequence in combination with the hidden states of a recurrent neural network (RNN) as inputs to an inference network per time step. As part of this framework, we condition the prior probability of the latent variables on the hidden states of the RNN utilised to capture temporal dependencies. We further condition the posterior of the motion field on a latent variable from hierarchy and features from the moving image. Subsequently, the RNN updates the hidden state variables based on the feature maps of the fixed image and the latent variables. Different from traditional methods, DragNet performs registration on unseen sequences in a forward pass, which significantly expedites the registration process. Besides, DragNet enables generating a large number of realistic synthetic image sequences given only one frame, where the corresponding deformations are also retrieved. The probabilistic framework allows for computing spatio-temporal uncertainties in the estimated motion fields. Our results show that DragNet performance is comparable with state-of-the-art methods in terms of registration accuracy, with the advantage of offering analytical pixel-wise motion uncertainty estimation across a cardiac cycle and being a motion generator. We will make our code publicly available.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
Keywords: | Deformable temporal image registration; Sequential image data generation; Deep learning; Variational recurrent neural networks; Uncertainty estimation; UK Biobank |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Mechanical Engineering (Leeds) > Institute of Medical and Biological Engineering (iMBE) (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 14 Jul 2023 15:47 |
Last Modified: | 14 Jul 2023 15:47 |
Status: | Published |
Publisher: | Elsevier |
Identification Number: | 10.1016/j.media.2022.102678 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:201510 |