ORCID Profile
0000-0002-2396-6970
Current Organisation
University of Nottingham
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: The Optical Society
Date: 16-05-2019
DOI: 10.1364/OME.9.002617
Publisher: OSA
Date: 2015
Publisher: The Optical Society
Date: 27-06-2014
DOI: 10.1364/OME.4.001444
Publisher: Springer Science and Business Media LLC
Date: 14-09-2014
Publisher: The Optical Society
Date: 31-07-2014
DOI: 10.1364/OE.22.019169
Publisher: SPIE
Date: 07-03-2016
DOI: 10.1117/12.2211584
Publisher: Elsevier BV
Date: 2023
DOI: 10.1016/J.MEDIA.2022.102678
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.
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Zhuoqi Tang.