Direct Multitype Cardiac Indices Estimation via Joint Representation and Regression Learning

Abstract

Cardiac indices estimation is of great importance during identification and diagnosis of cardiac disease in clinical routine. However, estimation of multitype cardiac indices with consistently reliable and high accuracy is still a great challenge due to the high variability of cardiac structures and the complexity of temporal dynamics in cardiac MR sequences. While efforts have been devoted into cardiac volumes estimation through feature engineering followed by a independent regression model, these methods suffer from the vulnerable feature representation and incompatible regression model. In this paper, we propose a semi-automated method for multitype cardiac indices estimation. After the manual labeling of two landmarks for ROI cropping, an integrated deep neural network Indices-Net is designed to jointly learn the representation and regression models. It comprises two tightly-coupled networks, such as a deep convolution autoencoder for cardiac image representation, and a multiple output convolution neural network for indices regression. Joint learning of the two networks effectively enhances the expressiveness of image representation with respect to cardiac indices, and the compatibility between image representation and indices regression, thus leading to accurate and reliable estimations for all the cardiac indices. When applied with five-fold cross validation on MR images of 145 subjects, Indices-Net achieves consistently low estimation error for LV wall thicknesses (1.44 ± 0.71 mm) and areas of cavity and myocardium (204 ± 133 mm). It outperforms, with significant error reductions, segmentation method (55.1% and 17.4%), and two-phase direct volume-only methods (12.7% and 14.6%) for wall thicknesses and areas, respectively. These advantages endow the proposed method a great potential in clinical cardiac function assessment.

Large-scale biometry with interpretable neural network regression on UK Biobank body MRI

“…Techniques involving neural networks for image-based regression have been previously proposed for the analysis of brain MRI for detection of premature ageing 2 , early symptoms of Alzheimers disease 3 and mental disorders 4 . In heart MRI, related approaches were able to perform measurements of volumes and wall thicknesses of the heart 5 . Similarly, analyses of retinal fundus photographs showed that neural networks were able to leverage image features for the prediction of properties including age, gender, smoking status and blood pressure 6 .…”

PV-LVNet: Direct left ventricle multitype indices estimation from 2D echocardiograms of paired apical views with deep neural networks

“…2) the end-to-end direct estimation, i,e, Indices-Net (Xue et al, 2017a); 3) the indirect estimation with segmentation U-net (Ronneberger et al, 2015). As shown in Table 1 Figure 11: The inter-frames gradient well regularizes the network to enhance sequential data fitting.…”

“…Our method is fed with entire echo image and does not require post-processing, benefited from its robust processing ability. But the other direct methods need to be performed on the the pre-handcrafted region to work (Zhen et al, 2014b(Zhen et al, , 2015a(Zhen et al, , 2016Xue et al, 2017a). The segmentation method U-net is post processed as general with maximum connected region extraction to improve its segmentation results for indices estimation.…”

Multi-estimator Full Left Ventricle Quantification Through Ensemble Learning

“…This category of methods is advantages as the results (usually as segmentation masks) are easier to interpret which can provide more insight into the analytic procedure. The latter category of direct estimation-based methods [5,6,7,8] perform estimation of the cardiac parameters directly from the image and/or image features, without relying on explicit segmentation procedure. It is advantages as the training error can be directly back-propagated to the feature selection and regression process, thus normally resulting in higher accuracy.…”