Learning-Based Regularization for Cardiac Strain Analysis Via Domain Adaptation

Overview

Journal IEEE Trans Med Imaging

Date 2021 Apr 19

PMID 33872145

Citations 8

Authors

Allen Lu

Shawn S Ahn

Kevinminh Ta

Nripesh Parajuli

John C Stendahl

Zhao Liu

Nabil E Boutagy

Geng-Shi Jeng

Lawrence H Staib

Matthew ODonnell

Albert J Sinusas

James S Duncan

Affiliations

Soon will be listed here.

Abstract

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. 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. In this work, we incorporated the notion of domain adaptation into a supervised neural network regularization framework. We first propose a semi-supervised Multi-Layered Perceptron (MLP) network with biomechanical constraints for learning a latent representation that is shown to have more physiologically plausible displacements. We extended this framework to include a supervised loss term on synthetic data and showed the effects of biomechanical constraints on the network's ability for domain adaptation. We validated the semi-supervised regularization method on in vivo data with implanted sonomicrometers. Finally, we showed the ability of our semi-supervised learning regularization approach to identify infarct regions using estimated regional strain maps with good agreement to manually traced infarct regions from postmortem excised hearts.

Citing Articles

A preoperative planning procedure of septal myectomy for hypertrophic obstructive cardiomyopathy using image-based computational fluid dynamics simulations and shape optimization.

Ding Z, Liu Q, Luo H, Yang M, Zhang Y, Wang S Sci Rep. 2024; 14(1):24617.

PMID: 39426997 PMC: 11490630. DOI: 10.1038/s41598-024-74091-3.

Coordinate-Independent 3-D Ultrasound Principal Stretch and Direction Imaging.

Jeng G, Chen P, Hsieh M, Liu Z, Langdon J, Ahn S IEEE Trans Biomed Eng. 2024; 71(11):3312-3323.

PMID: 38941195 PMC: 11637688. DOI: 10.1109/TBME.2024.3420220.

Multi-Task Learning for Motion Analysis and Segmentation in 3D Echocardiography.

Ta K, Ahn S, Thorn S, Stendahl J, Zhang X, Langdon J IEEE Trans Med Imaging. 2024; 43(5):2010-2020.

PMID: 38231820 PMC: 11514714. DOI: 10.1109/TMI.2024.3355383.

Co-attention spatial transformer network for unsupervised motion tracking and cardiac strain analysis in 3D echocardiography.

Ahn S, Ta K, Thorn S, Onofrey J, Melvinsdottir I, Lee S Med Image Anal. 2022; 84:102711.

PMID: 36525845 PMC: 9812938. DOI: 10.1016/j.media.2022.102711.

Novel Cardiac Computed Tomography Methods for the Assessment of Anthracycline Induced Cardiotoxicity.

Feher A, Baldassarre L, Sinusas A Front Cardiovasc Med. 2022; 9:875150.

PMID: 35571206 PMC: 9094702. DOI: 10.3389/fcvm.2022.875150.

References

Kaluzynski K, Chen X, Emelianov S, Skovoroda A, ODonnell M . Strain rate imaging using two-dimensional speckle tracking. IEEE Trans Ultrason Ferroelectr Freq Control. 2001; 48(4):1111-23. DOI: 10.1109/58.935730. View

Frangi A, Niessen W, Viergever M . Three-dimensional modeling for functional analysis of cardiac images: a review. IEEE Trans Med Imaging. 2001; 20(1):2-25. DOI: 10.1109/42.906421. View

Chen X, Xie H, Erkamp R, Kim K, Jia C, Rubin J . 3-D correlation-based speckle tracking. Ultrason Imaging. 2005; 27(1):21-36. DOI: 10.1177/016173460502700102. View

Ledesma-Carbayo M, Kybic J, Desco M, Santos A, Suhling M, Hunziker P . Spatio-temporal nonrigid registration for ultrasound cardiac motion estimation. IEEE Trans Med Imaging. 2005; 24(9):1113-26. DOI: 10.1109/TMI.2005.852050. View

Lamata P, Sinclair M, Kerfoot E, Lee A, Crozier A, Blazevic B . An automatic service for the personalization of ventricular cardiac meshes. J R Soc Interface. 2013; 11(91):20131023. PMC: 3869175. DOI: 10.1098/rsif.2013.1023. View

De Craene M, Piella G, Camara O, Duchateau N, Silva E, Doltra A . Temporal diffeomorphic free-form deformation: application to motion and strain estimation from 3D echocardiography. Med Image Anal. 2011; 16(2):427-50. DOI: 10.1016/j.media.2011.10.006. View

Akaishi M, Schneider R, Seelaus P, Klein L, Agarwal J, Helfant R . A non-linear elastic model of contraction of ischaemic segments. Cardiovasc Res. 1988; 22(12):889-99. DOI: 10.1093/cvr/22.12.889. View

Stendahl J, Parajuli N, Lu A, Boutagy N, Guerrera N, Alkhalil I . Regional myocardial strain analysis via 2D speckle tracking echocardiography: validation with sonomicrometry and correlation with regional blood flow in the presence of graded coronary stenoses and dobutamine stress. Cardiovasc Ultrasound. 2020; 18(1):2. PMC: 6964036. DOI: 10.1186/s12947-019-0183-x. View

Jeng G, Zontak M, Parajuli N, Lu A, Ta K, Sinusas A . Efficient Two-Pass 3-D Speckle Tracking for Ultrasound Imaging. IEEE Access. 2019; 6:17415-17428. PMC: 6365000. DOI: 10.1109/ACCESS.2018.2815522. View

10.

Alessandrini M, De Craene M, Bernard O, Giffard-Roisin S, Allain P, Waechter-Stehle I . A Pipeline for the Generation of Realistic 3D Synthetic Echocardiographic Sequences: Methodology and Open-Access Database. IEEE Trans Med Imaging. 2015; 34(7):1436-1451. DOI: 10.1109/TMI.2015.2396632. View

11.

Heyde B, Jasaityte R, Barbosa D, Robesyn V, Bouchez S, Wouters P . Elastic image registration versus speckle tracking for 2-D myocardial motion estimation: a direct comparison in vivo. IEEE Trans Med Imaging. 2012; 32(2):449-59. DOI: 10.1109/TMI.2012.2230114. View

12.

Waldman L, Fung Y, Covell J . Transmural myocardial deformation in the canine left ventricle. Normal in vivo three-dimensional finite strains. Circ Res. 1985; 57(1):152-63. DOI: 10.1161/01.res.57.1.152. View

13.

Rueckert D, Sonoda L, Hayes C, Hill D, Leach M, Hawkes D . Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans Med Imaging. 1999; 18(8):712-21. DOI: 10.1109/42.796284. View

14.

Papademetris X, Sinusas A, Dione D, Constable R, Duncan J . Estimation of 3-D left ventricular deformation from medical images using biomechanical models. IEEE Trans Med Imaging. 2002; 21(7):786-800. DOI: 10.1109/TMI.2002.801163. View

15.

Compas C, Wong E, Huang X, Sampath S, Lin B, Pal P . Radial basis functions for combining shape and speckle tracking in 4D echocardiography. IEEE Trans Med Imaging. 2014; 33(6):1275-89. PMC: 4283552. DOI: 10.1109/TMI.2014.2308894. View

16.

Shi P, Sinusas A, Constable R, Ritman E, Duncan J . Point-tracked quantitative analysis of left ventricular surface motion from 3-D image sequences. IEEE Trans Med Imaging. 2000; 19(1):36-50. DOI: 10.1109/42.832958. View

17.

Lubinski M, Emelianov S, ODonnell M . Speckle tracking methods for ultrasonic elasticity imaging using short-time correlation. IEEE Trans Ultrason Ferroelectr Freq Control. 2008; 46(1):82-96. DOI: 10.1109/58.741427. View

18.

Heyde B, Alessandrini M, Hermans J, Barbosa D, Claus P, Dhooge J . Anatomical Image Registration Using Volume Conservation to Assess Cardiac Deformation From 3D Ultrasound Recordings. IEEE Trans Med Imaging. 2015; 35(2):501-11. DOI: 10.1109/TMI.2015.2479556. View

19.

Parajuli N, Compas C, Lin B, Sampath S, ODonnell M, Sinusas A . Sparsity and Biomechanics Inspired Integration of Shape and Speckle Tracking for Cardiac Deformation Analysis. Funct Imaging Model Heart. 2016; 9126:57-64. PMC: 5146991. DOI: 10.1007/978-3-319-20309-6_7. View

20.

Huang X, Dione D, Compas C, Papademetris X, Lin B, Bregasi A . Contour tracking in echocardiographic sequences via sparse representation and dictionary learning. Med Image Anal. 2013; 18(2):253-71. PMC: 3946038. DOI: 10.1016/j.media.2013.10.012. View