In the presence of diseases such as ischemic heart disease (IHD), cardiac dyssynchrony deteriorates cardiac function and often cannot be treated effectively. However, while imaging methods such as cardiovascular magnetic resonance (CMR) can provide high quality images of the moving heart, conventional clinical quantitative analysis of cardiac function is largely limited to global function analysis of the left ventricle (LV), with only qualitative and subjective characterization of regional function. An obstacle to better quantification of regional function is the complex 3D structure and motion of the heart wall, which has typically necessitated time-consuming user-guided processing of the images to carry out the associated 3D-motion analysis. Recent advances in machine-learning (ML) approaches for image analysis are promising as new means to speed up the processing of cardiac images, as well as to analyze the underlying regional motion patterns. However, current Deep ML (DML) approaches to image analysis largely function as ?black boxes?, without clear indications of which features contribute most to the analysis results, thus limiting their clinical utility. In the initial funded period of this research project, we have been developing integrated approaches to the segmentation, 3D reconstruction, and analysis of CMR data, with application to the evaluation of cardiac dyssynchrony. Today, treatment of dyssynchrony in HF with cardiac resynchronization therapy (CRT) leads to improvement in only ~2/3 patients selected with conventional criteria (usually by electrocardiogram [ECG]). Our initial results show encouraging results of correlation between MRI evaluation of dyssynchrony and cardiac resynchronization therapy (CRT) outcomes. In the new proposed research, we will further develop these methods, with the goal of automating the cardiac analysis methods. This will include the introduction of new ML-based methods, which will incorporate information on the specific cardiac motion factors that lead to classification of different disease states in dyssynchrony. Our Hypothesis is that by using these new ML-based methods for cardiac motion analysis, we will discover and evaluate significant quantitative correlations between different cardiac dyssynchrony motion patterns and CRT outcomes. Also, late-gadolinium enhancement (LGE) provides images for infarction visualization. Incorporation of tissue characterization into the motion-pattern analysis could lead to increased understanding of how infarcted areas affect regional motion in concert with dyssynchrony. The unearthing of these findings will allow us to validate them in future clinical studies. The project will also disseminate our novel, coupled DML and model-based methodology for quantifying and classifying cardiac motion in diseases affecting regional wall motion. Other research groups can then apply our tools to specifically study dyssynchrony, as well as other cardiac diseases affecting LV motion.

Public Health Relevance

A significant proportion of patients with heart failure and cardiac dyssynchrony fail to positively respond to cardiac resynchronization therapy (CRT), as the current clinical selection criteria do not take into account regional cardiac function. We will develop improved methods for 4D-analysis and -visualization of both global and regional cardiac function from cardiovascular magnetic resonance (CMR) data, including novel deep learning methods that will provide additional information on the salient features that contribute most to characterization of cardiac dyssynchrony. These new methods will be applied to the analysis of CMR data from both a stratified sample of normal subjects and patients with cardiac dyssynchrony (with and without infarction), with correlation with therapeutic results following CRT, potentially leading to improved clinical guidelines and clinical outcomes, as well as increased understanding of cardiac physiology and pathophysiology.

Agency
National Institute of Health (NIH)
Institute
National Heart, Lung, and Blood Institute (NHLBI)
Type
Research Project (R01)
Project #
2R01HL127661-05
Application #
10052934
Study Section
Biomedical Computing and Health Informatics Study Section (BCHI)
Program Officer
Desvigne-Nickens, Patrice
Project Start
2015-07-01
Project End
2024-04-30
Budget Start
2020-08-15
Budget End
2021-04-30
Support Year
5
Fiscal Year
2020
Total Cost
Indirect Cost
Name
Rutgers University
Department
Biostatistics & Other Math Sci
Type
Schools of Arts and Sciences
DUNS #
001912864
City
Piscataway
State
NJ
Country
United States
Zip Code
08854
Bernardis, Elena; Zhang, Yong; Konukoglu, Ender et al. (2018) eCurves: A Temporal Shape Encoding. IEEE Trans Biomed Eng 65:733-744
Niethammer, Marc; Pohl, Kilian M; Janoos, Firdaus et al. (2017) ACTIVE MEAN FIELDS FOR PROBABILISTIC IMAGE SEGMENTATION: CONNECTIONS WITH CHAN-VESE AND RUDIN-OSHER-FATEMI MODELS. SIAM J Imaging Sci 10:1069-1103
Zhang, Yong; Kwon, Dongjin; Pohl, Kilian M (2017) Computing group cardinality constraint solutions for logistic regression problems. Med Image Anal 35:58-69
Yang, Dong; Wu, Pengxiang; Tan, Chaowei et al. (2017) 3D Motion Modeling and Reconstruction of Left Ventricle Wall in Cardiac MRI. Funct Imaging Model Heart 10263:481-492
Chen, Ting; Reyhan, Meral; Yue, Ning et al. (2015) Tagged MRI based cardiac motion modeling and toxicity evaluation in breast cancer radiotherapy. Front Oncol 5:9
Fang, Ruogu; Chen, Tsuhan; Metaxas, Dimitris et al. (2015) Sparsity techniques in medical imaging. Comput Med Imaging Graph 46 Pt 1:1
Zhang, Yong; Pohl, Kilian M (2015) Solving Logistic Regression with Group Cardinality Constraints for Time Series Analysis. Med Image Comput Comput Assist Interv 9351:459-466
Wang, Xiaoxu; Chen, Ting; Zhang, Shaoting et al. (2015) Meshless deformable models for 3D cardiac motion and strain analysis from tagged MRI. Magn Reson Imaging 33:146-60
Yu, Yang; Zhang, Shaoting; Li, Kang et al. (2014) Deformable models with sparsity constraints for cardiac motion analysis. Med Image Anal 18:927-37
Uzunba?, Mustafa Gökhan; Chen, Chao; Zhang, Shaoting et al. (2013) Collaborative multi organ segmentation by integrating deformable and graphical models. Med Image Comput Comput Assist Interv 16:157-64

Showing the most recent 10 out of 11 publications