Quantification of Full Left Ventricular Metrics via Deep Regression Learning With Contour-Guidance
Authors:
Open Access
- 26 March 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 47918-47928
Abstract
Quantifying full left ventricular (LV) metrics including cavity area, myocardium area, cavity dimensions and wall thicknesses from cardiac magnetic resonance (MR) images and then assessing regional and global cardiac function plays a crucial role in clinical practice. However, due to highly variable cardiac structures across different subjects, it is challenging to obtain accurate estimation of LV metrics. In this paper, we propose a novel deep learning framework, called Cascaded Segmentation and Regression Network (CSRNet), to improve the quantification results. The CSRNet consists of two components: segmentation component and regression component. The segmentation component yields myocardial contours of left ventricle from the input cardiac MR images, and then the regression component learns hierarchical representations from the segmented images and estimates the desired LV metrics. By introducing the myocardial contours, the regression component can pay more attention to the left ventricle, which contributes to more accurate quantification results, although the cardiac structures are variable. Extensive experiments on a dataset of 145 subjects demonstrate that our framework outperforms the state-of-the-art methods.Keywords
Funding Information
- National Natural Science Foundation of China (61702037)
- Natural Science Foundation of Beijing Municipality (L172027)
- Key Program from NSF of Hebei Province (F2016202144)
- Natural Science Foundation of Tianjin Municipality (16JCYBJC15600)
- Department of Education of Hebei Province (QN2016217)
This publication has 25 references indexed in Scilit:
- A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRIMedical Image Analysis, 2016
- Multi-scale deep networks and regression forests for direct bi-ventricular volume estimationMedical Image Analysis, 2016
- Quantification of LV function and mass by cardiovascular magnetic resonance: multi-center variability and consensus contoursJournal of Cardiovascular Magnetic Resonance, 2015
- Direct Estimation of Cardiac Biventricular Volumes With an Adapted Bayesian FormulationIEEE Transactions on Biomedical Engineering, 2014
- Direct Estimation of Cardiac Bi-ventricular Volumes with Regression Forests2014
- Left ventricle segmentation from cardiac MRI combining level set methods with deep belief networks2013
- Segmentation of the left ventricle in cardiac cine MRI using a shape-constrained snake modelComputer Vision and Image Understanding, 2013
- Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measureMedical Image Analysis, 2012
- Efficient and generalizable statistical models of shape and appearance for analysis of cardiac MRIMedical Image Analysis, 2008
- Snakes, shapes, and gradient vector flowIEEE Transactions on Image Processing, 1998