DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images (2021-03-04T00:00:00.000000Z)

TL;DR

This paper proposes a novel deep learning-based fully unsupervised method for in vivo motion tracking on t-MRI images and shows that this method is superior to conventional motion tracking methods in terms of landmark tracking accuracy and inference efficiency.

Abstract

Cardiac tagging magnetic resonance imaging (t-MRI) is the gold standard for regional myocardium deformation and cardiac strain estimation. However, this technique has not been widely used in clinical diagnosis, as a result of the difficulty of motion tracking encountered with t-MRI images. In this paper, we propose a novel deep learning-based fully unsupervised method for in vivo motion tracking on t-MRI images. We first estimate the motion field (INF) between any two consecutive t-MRI frames by a bi-directional generative diffeomorphic registration neural network. Using this result, we then estimate the Lagrangian motion field between the reference frame and any other frame through a differentiable composition layer. By utilizing temporal information to perform reasonable estimations on spatiotemporal motion fields, this novel method provides a useful solution for motion tracking and image registration in dynamic medical imaging. Our method has been validated on a representative clinical t-MRI dataset; the experimental results show that our method is superior to conventional motion tracking methods in terms of landmark tracking accuracy and inference efficiency. Project page is at: https://github.com/DeepTag/cardiac_tagging_motion_estimation.

Authors

Dimitris N. Metaxas

3 papers

Mikael Kanski

1 papers

D. Yang

1 papers

TL;DR

Abstract

Authors

References58 items

Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networks

FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation

Recursive Cascaded Networks for Unsupervised Medical Image Registration

Implementation and Validation of a Three-dimensional Cardiac Motion Estimation Network.

A gradient-based optical-flow cardiac motion estimation method for cine and tagged MR images

Region-specific Diffeomorphic Metric Mapping

Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence

Metric Learning for Image Registration

SelFlow: Self-Supervised Learning of Optical Flow

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation

Networks for Joint Affine and Non-Parametric Image Registration

Myocardial strain imaging: review of general principles, validation, and sources of discrepancies

Learning a Probabilistic Model for Diffeomorphic Registration

Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow

Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration

Deformable Image Registration Using a Cue-Aware Deep Regression Network

GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose

An Unsupervised Learning Model for Deformable Medical Image Registration

UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss

Robust Non-rigid Registration Through Agent-Based Action Learning

Deformable Image Registration Based on Similarity-Steered CNN Regression

SVF-Net: Learning Deformable Image Registration Using Shape Matching

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Accurate harmonic phase tracking of tagged MRI using locally-uniform myocardium displacement constraint.

FlowNet: Learning Optical Flow with Convolutional Networks

Auto-Encoding Variational Bayes

LCC-Demons: A robust and accurate symmetric diffeomorphic registration algorithm

Cardiac Motion and Deformation Estimation from Tagged MRI Sequences Using a Temporal Coherent Image Registration Framework

A Comprehensive Cardiac Motion Estimation Framework Using Both Untagged and 3-D Tagged MR Images Based on Nonrigid Registration

Incompressible Deformation Estimation Algorithm (IDEA) From Tagged MR Images

An Incompressible Log-Domain Demons Algorithm for Tracking Heart Tissue

Identifying Regional Cardiac Abnormalities From Myocardial Strains Using Nontracking-Based Strain Estimation and Spatio-Temporal Tensor Analysis

A reproducible evaluation of ANTs similarity metric performance in brain image registration

Motion estimation of tagged cardiac magnetic resonance images using variational techniques

Shortest Path Refinement for Motion Estimation From Tagged MR Images

Meshless deformable models for LV motion analysis

Unsupervised estimation of myocardial displacement from tagged MR sequences using nonrigid registration

A fast diffeomorphic image registration algorithm

A Log-Euclidean Framework for Statistics on Diffeomorphisms

A non-rigid registration approach for quantifying myocardial contraction in tagged MRI using generalized information measures

Analysis of 3-D myocardial motion in tagged MR images using nonrigid image registration

High Accuracy Optical Flow Estimation Based on a Theory for Warping

Imaging heart motion using harmonic phase MRI

Cardiac motion tracking using CINE harmonic phase (HARP) magnetic resonance imaging

Dense estimation and object-based segmentation of the optical flow with robust techniques

MR imaging of motion with spatial modulation of magnetization.

Determining Optical Flow

Supplementary Materials for UnOS: Uniﬁed Unsupervised Optical-ﬂow and Stereo-depth Estimation by Watching Videos

Alzheimer’s Disease Neuroimaging Initiative (ADNI, et al. Lcc-demons: a robust and accurate symmetric diffeomorphic registration

Automated 3D Motion Tracking Using Gabor Filter Bank, Robust Point Matching, and Deformable Models

Structure-and motion-adaptive regularization for high accuracy optic ﬂow

Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names