Rank Constrained Diffeomorphic Density Motion Estimation for Respiratory Correlated Computed Tomography

09/26/2019

∙

by Markus D. Foote, et al.

∙

THE UNIVERSITY OF UTAH

∙

Motion estimation of organs in a sequence of images is important in numerous medical imaging applications. The focus of this paper is the analysis of 4D Respiratory Correlated Computed Tomography (RCCT) Imaging. It is hypothesized that the quasi-periodic breathing induced motion of organs in the thorax can be represented by deformations spanning a very low dimension subspace of the full infinite dimensional space of diffeomorphic transformations. This paper presents a novel motion estimation algorithm that includes the constraint for low-rank motion between the different phases of the RCCT images. Low-rank deformation solutions are necessary for the efficient statistical analysis and improved treatment planning and delivery. Although the application focus of this paper is RCCT the algorithm is quite general and applicable to various motion estimation problems in medical imaging.

READ FULL TEXT

Rank Constrained Diffeomorphic Density Motion Estimation for Respiratory Correlated Computed Tomography

Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain Imaging

Low-rank Latent Matrix Factor-Analysis Modeling for Generalized Linear Regression with High-dimensional Imaging Biomarkers

Automated Segmentation of Computed Tomography Images with Submanifold Sparse Convolutional Networks

Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation

Accurate Benchmark Computations of the Polarizability Tensor for Characterising Small Conducting Inclusions

High dimensional VAR with low rank transition

Robust Cardiac Motion Estimation using Ultrafast Ultrasound Data: A Low-Rank-Topology-Preserving Approach

Rank Constrained Diffeomorphic Density Motion Estimation for Respiratory Correlated Computed Tomography

Related Research

Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain Imaging

Low-rank Latent Matrix Factor-Analysis Modeling for Generalized Linear Regression with High-dimensional Imaging Biomarkers

Automated Segmentation of Computed Tomography Images with Submanifold Sparse Convolutional Networks

Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation

Accurate Benchmark Computations of the Polarizability Tensor for Characterising Small Conducting Inclusions

High dimensional VAR with low rank transition

Robust Cardiac Motion Estimation using Ultrafast Ultrasound Data: A Low-Rank-Topology-Preserving Approach