Filters








388 Hits in 20.6 sec

Right ventricular strain analysis from three-dimensional echocardiography by using temporally diffeomorphic motion estimation

Zhijun Zhang, Meihua Zhu, Muhammad Ashraf, Craig S. Broberg, David J. Sahn, Xubo Song
2014 Medical Physics (Lancaster)  
The closeness of the segmental strain of their method to those from MRI shows the feasibility of their method in the study of RV function by using 3D echocardiography.  ...  Methods: The authors have proposed a temporally diffeomorphic motion estimation method in which a spatiotemporal transformation is estimated by optimization of a registration energy functional of the velocity  ...  It was a general method and it has four advantages over the existing methods on RV motion estimation from MRI and LV motion estimation from echocardiography.  ... 
doi:10.1118/1.4901253 pmid:25471981 pmcid:PMC4241709 fatcat:qugtz474rbafpdtmzasf5lkxgy

Learning-based Regularization for Cardiac Strain Analysis via Domain Adaptation

Allen Lu, Shawn S. Ahn, Kevinminh Ta, Nripesh Parajuli, John C. Stendahl, Zhao Liu, Nabil E. Boutagy, Geng-Shi Jeng, Lawrence H. Staib, Matthew OrDonnell, Albert J. Sinusas, James S. Duncan
2021 IEEE Transactions on Medical Imaging  
However, motion estimation is difficult due to the low-SNR that stems from the inherent image properties of 4DE, and intelligent regularization is critical for producing reliable motion estimates.  ...  Reliable motion estimation and strain analysis using 3D+time echocardiography (4DE) for localization and characterization of myocardial injury is valuable for early detection and targeted interventions  ...  Since the heart is a moving 3D object, learning from 4D data is required to avoid out-of-plane motion errors and allows the network to fully capture spatiotemporal motion patterns.  ... 
doi:10.1109/tmi.2021.3074033 pmid:33872145 pmcid:PMC8442959 fatcat:u3z3kphbonbcbl6sego6uifv7q

A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image [article]

Yuyu Guo, Lei Bi, Euijoon Ahn, Dagan Feng, Qian Wang, Jinman Kim
2020 arXiv   pre-print
SVIN introduces dual networks: first is the spatiotemporal motion network that leverages the 3D convolutional neural network (CNN) for unsupervised parametric volumetric registration to derive spatiotemporal  ...  motion field from two-image volumes; the second is the sequential volumetric interpolation network, which uses the derived motion field to interpolate image volumes, together with a new regression-based  ...  Comparison of spatiotemporal volumetric motion estimation results. The intensity image is warped from estimated spatiotemporal motion field.  ... 
arXiv:2002.12680v2 fatcat:zd2scrkoq5h6lbyflhgrer6yby

Deep Learning in Spatiotemporal Cardiac Imaging: A Review of Methodologies and Clinical Usability

Karen Andrea Lara Hernandez, Theresa Rienmüller, Daniela Baumgartner, Christian Baumgartner
2020 Computers in Biology and Medicine  
In summary, deep learning in spatiotemporal cardiac imaging is still strongly research-oriented and its implementation in clinical application still requires considerable efforts.  ...  This review aims to synthesize the most relevant deep learning methods and discuss their clinical usability in dynamic cardiac imaging using for example the complete spatiotemporal image information of  ...  [47] suggested a novel method to simultaneously estimate motion and segment cardiac structures from CMR cine sequences by using a Siamese style multi-scale network for unsupervised motion estimation  ... 
doi:10.1016/j.compbiomed.2020.104200 pmid:33421825 fatcat:ltxjpt6yhzgvdkifo4wo3ftveq

Temporally diffeomorphic cardiac motion estimation from three-dimensional echocardiography by minimization of intensity consistency error

Zhijun Zhang, Muhammad Ashraf, David J. Sahn, Xubo Song
2014 Medical Physics (Lancaster)  
However, motion estimation from 3D echocardiographic sequences is still a challenging problem due to low image quality and image corruption by noise and artifacts.  ...  Three dimensional (3D) echocardiography is among the most frequently used imaging modalities for motion estimation because it is convenient, real-time, low-cost, and nonionizing.  ...  to estimate cardiac motion from image sequences. 6, [25] [26] [27] [28] [29] [30] [31] Temporal smoothness is an important issue to consider for cardiac motion analysis because motion of heart wall  ... 
doi:10.1118/1.4867864 pmid:24784402 pmcid:PMC4000394 fatcat:jgmi5mzo35bwnkw4jy53gnl35q

Assessment of Left Ventricular Function in Cardiac MSCT Imaging by a 4D Hierarchical Surface-Volume Matching Process

Mireille Garreau, Antoine Simon, Dominique Boulmier, Jean-Louis Coatrieux, Hervé Le Breton
2006 International Journal of Biomedical Imaging  
Multislice computed tomography (MSCT) scanners offer new perspectives for cardiac kinetics evaluation with 4D dynamic sequences of high contrast and spatiotemporal resolutions.  ...  A new method is proposed for cardiac motion extraction in multislice CT.  ...  A 4D HIERARCHICAL MOTION ESTIMATION METHOD From a time sequence of 3D MSCT cardiac images, our approach allows the spatiotemporal detection of the left heart cavities and the quantification of their deformations  ... 
doi:10.1155/ijbi/2006/37607 pmid:23165027 pmcid:PMC2324033 fatcat:tuzdp3alerb4jj2avzcnrdnm3i

Learning-based Regularization for Cardiac Strain Analysis with Ability for Domain Adaptation [article]

Allen Lu, Nripesh Parajuli, Maria Zontak, John Stendahl, Kevinminh Ta, Zhao Liu, Nabil Boutagy, Geng-Shi Jeng, Imran Alkhalil, Lawrence H. Staib, Matthew O'Donnell, Albert J. Sinusas, James S. Duncan
2018 arXiv   pre-print
However, motion estimation is difficult due to the low-SNR that stems from the inherent image properties of 4DE, and intelligent regularization is critical for producing reliable motion estimates.  ...  Reliable motion estimation and strain analysis using 3D+time echocardiography (4DE) for localization and characterization of myocardial injury is valuable for early detection and targeted interventions  ...  To regularize spatiotemporal cardiac motion, Ledesma-Carbayo et al. registered the entire 2D+time echo image sequence (i.e.  ... 
arXiv:1807.04807v1 fatcat:xnruoyjxbncstattgwbbpj76oy

Machine Learning Approaches for Myocardial Motion and Deformation Analysis

Nicolas Duchateau, Andrew P. King, Mathieu De Craene
2020 Frontiers in Cardiovascular Medicine  
With the advent of approaches relying on data rather than pre-conceived models, machine learning could either improve the robustness of motion quantification or reveal patterns of motion and deformation  ...  We review machine learning strategies for extracting motion-related descriptors and analyzing such features among populations, keeping in mind constraints specific to the cardiac application.  ...  (19) used dictionary learning as a sparse basis for cardiac motion fields to feed the regularization.  ... 
doi:10.3389/fcvm.2019.00190 pmid:31998756 pmcid:PMC6962100 fatcat:o565yqcqq5an7nhdvvutyy2yua

Spatiotemporal Segmentation and Modeling of the Mitral Valve in Real-Time 3D Echocardiographic Images [chapter]

Alison M. Pouch, Ahmed H. Aly, Eric K. Lai, Natalie Yushkevich, Rutger H. Stoffers, Joseph H. Gorman, Albert T. Cheung, Joseph H. Gorman, Robert C. Gorman, Paul A. Yushkevich
2017 Lecture Notes in Computer Science  
The algorithm is evaluated on rt-3DE data series from 10 patients: five with normal mitral valve morphology and five with severe IMR.  ...  As a step towards filling this knowledge gap, we present a novel framework for 4D segmentation and geometric modeling of the mitral valve in real-time 3D echocardiography (rt-3DE).  ...  Spatiotemporal Segmentation and Modeling of the Mitral Valve 753  ... 
doi:10.1007/978-3-319-66182-7_85 pmid:29285527 pmcid:PMC5743331 fatcat:meyjxndp5nanlfc4wufs2hqcmi

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
Landmark-free 3D US to MRI Registration 541 Left Ventricle Segmentation via Optical-Flow-Net from Short-axis Cine MRI: Preserving the Temporal Coherence of Cardiac Motion 545 Cell Instance Tracking with  ...  Estimation and Segmentation for Cardiac MR Image Sequences 681 3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes 682 Real Time RNN Based 3D Ultrasound Scan Adequacy  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Image-Based Estimation of Myocardial Acceleration Using TDFFD: A Phantom Study [chapter]

Ali Pashaei, Gemma Piella, Nicolas Duchateau, Luigi Gabrielli, Oscar Camara
2014 Lecture Notes in Computer Science  
The method is tested on 3D+t echocardiographic sequences from a realistic physical heart phantom, in which ground truth displacement is known in some regions.  ...  In this paper, we propose to estimate myocardial acceleration using a temporal di↵eomorphic free-form deformation (TDFFD) algorithm.  ...  This is one limit of our study, that one may consider less relevant in the future with the availability of higher frame rates for 3D echocardiography.  ... 
doi:10.1007/978-3-642-54268-8_31 fatcat:zu3ocgdn2nczxmcrlia2vg5rui

Three-Dimensional Echocardiography: Current Status and Real-Life Applications

Victor Chien-Chia Wu, Masaaki Takeuchi
2017 Acta Cardiologica Sinica  
or multislice mode, all of which are not possible with traditional 2D echocardiography (2DE).  ...  The growing availability of 3D echocardiography (3DE) over the last decade has allowed its applications to expand from establishing reference values for chamber size and elucidating ventricular mechanics  ...  echocardiography and cardiac magnetic resonance 3DE vs.  ... 
pmid:28344414 pmcid:PMC5364152 fatcat:dpolk33u5bedhhnk56rpjga4wq

Simulating time to event prediction with spatiotemporal echocardiography deep learning [article]

Rohan Shad, Nicolas Quach, Robyn Fong, Patpilai Kasinpila, Cayley Bowles, Kate M. Callon, Michelle C. Li, Jeffrey Teuteberg, John P. Cunningham, Curtis P. Langlotz, William Hiesinger
2021 arXiv   pre-print
By training on just the simulated survival outcomes, we show that spatiotemporal convolutional neural networks yield accurate survival estimates.  ...  In this paper, to explore the feasibility of these methods when applied to deep learning with echocardiography videos, we utilize the Stanford EchoNet-Dynamic dataset with over 10,000 echocardiograms,  ...  We would like to acknowledge Håvard Kvamme for assisting with refactoring the survival loss functions to pytorch.  ... 
arXiv:2103.02583v1 fatcat:ds4iu6akavenjdbo55fgrvtsnq

Temporal diffeomorphic free-form deformation: Application to motion and strain estimation from 3D echocardiography

Mathieu De Craene, Gemma Piella, Oscar Camara, Nicolas Duchateau, Etelvino Silva, Adelina Doltra, Jan D'hooge, Josep Brugada, Marta Sitges, Alejandro F. Frangi
2012 Medical Image Analysis  
Temporal diffeomorphic free-form deformation: Application to motion and strain estimation from 3D echocardiography. Medical Image Analysis, Elsevier, 2012, 16 (2), pp.  ...  Subsequently, TDFFD was applied to a database of cardiac 3D US images of the left ventricle acquired from 9 healthy volunteers and 13 patients treated by Cardiac Resynchronization Therapy (CRT).  ...  with the objective of recovering myocardial motion from a 3D US image sequence.  ... 
doi:10.1016/j.media.2011.10.006 pmid:22137545 fatcat:4tfs6t6n4jhzng3u3xahd2twka

Flow Network Tracking for Spatiotemporal and Periodic Point Matching: Applied to Cardiac Motion Analysis [article]

Nripesh Parajuli, Allen Lu, Kevinminh Ta, John C. Stendahl, Nabil Boutagy, Imran Alkhalil, Melissa Eberle, Geng-Shi Jeng, Maria Zontak, Matthew ODonnell, Albert J. Sinusas, James S. Duncan
2018 arXiv   pre-print
However, accurate estimation of the displacement of myocardial tissue and hence LV strain has been challenging due to a variety of issues, including those related to deriving tracking tokens from images  ...  The constraints also encourage motion to be cyclic, which is an important characteristic of LV motion.  ...  Song and Leahy (1991) applied this to model cardiac motion in 3D CT images. These methods can be time-consuming due to a large search space and also lack a regularization term.  ... 
arXiv:1807.02951v1 fatcat:t4o4jv37qzeftm6efpeolmy3xi
« Previous Showing results 1 — 15 out of 388 results