Direct Estimation of Regional Wall Thicknesses via Residual Recurrent Neural Network

Abstract

Accurate estimation of regional wall thicknesses (RWT) of left ventricular (LV) myocardium from cardiac MR sequences is of significant importance for identification and diagnosis of cardiac disease. Existing RWT estimation still relies on segmentation of LV myocardium, which requires strong prior information and user interaction. No work has been devoted into direct estimation of RWT from cardiac MR images due to the diverse shapes and structures for various subjects and cardiac diseases, as well as the complex regional deformation of LV myocardium during the systole and diastole phases of the cardiac cycle. In this paper, we present a newly proposed Residual Recurrent Neural Network (ResRNN) that fully leverages the spatial and temporal dynamics of LV myocardium to achieve accurate frame-wise RWT estimation. Our ResRNN comprises two paths: 1) a feed forward convolution neural network (CNN) for effective and robust CNN embedding learning of various cardiac images and preliminary estimation of RWT from each frame itself independently, and 2) a recurrent neural network (RNN) for further improving the estimation by modeling spatial and temporal dynamics of LV myocardium. For the RNN path, we design for cardiac sequences a Circle-RNN to eliminate the effect of null hidden input for the first time-step. Our ResRNN is capable of obtaining accurate estimation of cardiac RWT with Mean Absolute Error of 1.44mm (less than 1-pixel error) when validated on cardiac MR sequences of 145 subjects, evidencing its great potential in clinical cardiac function assessment.

Automated selection of myocardial inversion time with a convolutional neural network: Spatial temporal ensemble myocardium inversion network (STEMI‐NET)

“…33 Xue et al introduced a spatialtemporal circle LSTM model to calculate left-ventricle myocardial thickness in the short axis scan. 34 A few limitations of this feasibility study should be noted. In the training and validation of this model, we restricted training to short-axis inversion-recovery scout acquisitions.…”

“…In addition, Zhang et al combined recurrent neural network with convolutional LSTM for left‐ventricle myocardium segmentation . Xue et al introduced a spatial–temporal circle LSTM model to calculate left‐ventricle myocardial thickness in the short axis scan …”

Dynamic Displacement Forecasting of Dashuitian Landslide in China Using Variational Mode Decomposition and Stack Long Short-Term Memory Network

“…Recently, due to the advantages of deep learning in automatic feature extraction and high recognition rate or prediction accuracy, it has been successfully applied to speech recognition [17], action recognition [18], remaining useful life prognosis [19], traffic flow prediction [20], and other fields. As a commonly used deep learning model, the recurrent neural network (RNN) is an effective method for modeling dynamic sequences [21][22][23][24][25][26][27][28]. However, a RNN struggles to model long sequences because of gradient disappearance.…”

A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR images

“…For the application of cardiac cine MRI, Poudel et al [5] introduced an RNN at the lowest resolution level of a U-Net CNN to model the spatial continuity between adjacent LV locations. Xue et al [11] proposed a spatial-temporal circle LSTM model to estimate the LV myocardium thicknesses at the six regions of the mid-slice in the short axis scan. Both works succeeded by introducing RNNs to process abstracted features extracted by the corresponding CNN models.…”

“…Inspired by these RNN-based approaches, especially the work in [11], we propose a multi-level convolutional LSTM (ConvLSTM) approach for the automatic segmentation of LV myocardium. To develop the ConvLSTM model, a ResNet-56 CNN model [12] is trained first, and the LVrelated image features at the low-and high-resolution levels are extracted separately, each for training one LSTM model.…”