2019
DOI: 10.1016/j.media.2019.06.016
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: A new method is proposed to quantify the myocardial motion from both 2D C(ine)-MRI and T(agged)-MRI sequences. The tag pattern offers natural landmarks within the image that makes it possible to accurately quantify the motion within the myocardial wall. Therefore, several methods have been proposed for T-MRI. However, the lack of salient features within the cardiac wall in C-MRI hampers local motion estimation. Our method aims to ensure the local intensity and shape features invariance during motion through th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 13 publications
(6 citation statements)
references
References 30 publications
0
6
0
Order By: Relevance
“…Optical flow, which represents change of the pixels’ displacement vectors between image frames, is most widely used in motion tracking [ 33 ]. For example, optical flow has been used to detect human/animal movements [ 34 , 35 ] and medical organ lesions [ 36 , 37 ], robots or vehicle navigation [ 38 , 39 ], measure flow motion [ 40 ], airfoil deformation and surface strain [ 41 ]. With the assumption of instantaneous pixel value invariance over a short displacement, optical flow can be separated into two categories: local computation method on the basis of Lucas–Kanade (LK) method and global computation method based on Horn and Schunck (HS) formulation [ 42 ].…”
Section: Optical Flow Estimation Methodsmentioning
confidence: 99%
“…Optical flow, which represents change of the pixels’ displacement vectors between image frames, is most widely used in motion tracking [ 33 ]. For example, optical flow has been used to detect human/animal movements [ 34 , 35 ] and medical organ lesions [ 36 , 37 ], robots or vehicle navigation [ 38 , 39 ], measure flow motion [ 40 ], airfoil deformation and surface strain [ 41 ]. With the assumption of instantaneous pixel value invariance over a short displacement, optical flow can be separated into two categories: local computation method on the basis of Lucas–Kanade (LK) method and global computation method based on Horn and Schunck (HS) formulation [ 42 ].…”
Section: Optical Flow Estimation Methodsmentioning
confidence: 99%
“…The under-determined OF constraint equation is solved by variational principles in which some other regularization constraints are added in, including the image gradient, the phase or block matching. Although efforts have been made to seek more accurate regularization terms, OF approaches lack accuracy, especially for t-MRI motion tracking, due to the tag fading and large deformation problems [11,49]. More recently, convolutional neural networks (CNN) are trained to predict OF [16,19,20,24,26,41,31,47,53,51,48].…”
Section: Optical Flow Approachmentioning
confidence: 99%
“…There are also non-learning based methods that can be divided into two categories: optical flow-based and registration based. [22] shows the most recent gradient flow-based method. A Lagrangian displacement field based postprocessing is used to reduce the end-point error, which may not be time-efficient.…”
Section: Related Workmentioning
confidence: 99%
“…In [13,29], motion field smoothness is used as constraints, at the cost of compromised estimation of large motions. To evaluate the tracker's performance, DICE coefficients, surface distance and endpoint error are often used in recent researches [13,29,22]. Considering the clinical applications like myocardium strain which are computed along specific directions, these metrics are not well aligned with clinical interest.…”
Section: Introductionmentioning
confidence: 99%