Direct Estimation of Regional Wall Thicknesses via Residual Recurrent Neural Network

@inproceedings{Xue2017DirectEO,
  title={Direct Estimation of Regional Wall Thicknesses via Residual Recurrent Neural Network},
  author={Wufeng Xue and Ilanit Ben Nachum and Sachin Pandey and James Warrington and Stephanie Leung and S. Li},
  booktitle={IPMI},
  year={2017}
}
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… 
Left Ventricle Full Quantification via Hierarchical Quantification Network
TLDR
A novel multi-task quantification network (HQNet) to simultaneously quantify the four different parameters of cardiac left ventricle function and results indicate that the approach proposed has a promising performance to estimate all four parameters.
Quantification of Full Left Ventricular Metrics via Deep Regression Learning With Contour-Guidance
TLDR
A novel deep learning framework, called cascaded segmentation and regression network (CSRNet), to improve the quantification results, by introducing the myocardial contours of the left ventricle from the input cardiac MR images.
Automated Full Quantification of Left Ventricle with Deep Neural Networks
TLDR
A newly designed multitask learning network which combines the segmentation task and the cardiac indices quantification task, which comprises a segmentation network based on the U-net for image representation, and then a simple convolutional neural network for feature extraction of cardiac indices.
Cardiac Phase Detection in Echocardiograms With Densely Gated Recurrent Neural Networks and Global Extrema Loss
TLDR
Several deep learning-based architectures are proposed that minimize a novel global extrema structured loss function to localize the ED and ES frames and explore two CNN architectures: DenseNet and ResNet and four RNN architectures: long short-term memory, bi-directional LSTM, gated recurrent unit (GRU), and Bi-GRU, and compare the performance of these models.
Left-Ventricle Quantification Using Residual U-Net
TLDR
Assessing the methodology of calculating measurements from left ventricle segmentations automatically generated using deep learning on the STACOM18 LVQuan challenge dataset, it is found that it significantly outperforms the previously published state-of-the-art on a 5-fold validation all tasks considered.
A multi-level convolutional LSTM model for the segmentation of left ventricle myocardium in infarcted porcine cine MR images
TLDR
An approach based on recurrent neural network (RNN), specifically a multi-level convolutional long short-term memory (ConvLSTM) model, is proposed to take the motion of the heart into consideration and demonstrated its superior robustness against image inhomogeneity by incorporating information from adjacent frames.
Spatio-Temporal Multi-Task Learning for Cardiac MRI Left Ventricle Quantification
TLDR
A spatio-temporal multi-task learning approach to obtain a complete set of measurements quantifying cardiac LV morphology, regional-wall thickness (RWT), and additionally detecting the cardiac phase cycle (systole and diastole) for a given 3D Cine-magnetic resonance (MR) image sequence is proposed.
A Dense RNN for Sequential Four-Chamber View Left Ventricle Wall Segmentation and Cardiac State Estimation
TLDR
This is the first time that deals with both cardiac time-sequential LV segmentation problems and, robustly, estimates cardiac state and the method ensures an Intersection over Union (IoU) of 92.13%, which outperforms other classical deep learning algorithms.
Residual Convolutional Neural Network for Cardiac Image Segmentation and Heart Disease Diagnosis
TLDR
A new DL segmentation structure is proposed, which consists of a residual convolution neural network for compressing the intra-slice information, and a bidirectional-convolutional long short term memory (Bi-CLSTM) for leveraging the inter-slice contexts.
Left Ventricle Quantification Challenge: A Comprehensive Comparison and Evaluation of Segmentation and Regression for Mid-Ventricular Short-Axis Cardiac MR Data
TLDR
An unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018.
...
...

References

SHOWING 1-10 OF 23 REFERENCES
Multi-scale deep networks and regression forests for direct bi-ventricular volume estimation
Direct Estimation of Cardiac Bi-ventricular Volumes with Regression Forests
TLDR
With the proposed method, the most daily-used estimation of cardiac function, e.g., ejection fraction, can be conducted in a much more efficient, accurate and convenient way.
Recognizing End-Diastole and End-Systole Frames via Deep Temporal Regression Network
TLDR
A novel deep learning architecture is proposed, named as temporal regression network (TempReg-Net), to accurately identify specific frames from MRI sequences, by integrating the Convolutional Neural Network (CNN) with the Recurrent Neural network (RNN).
Recurrent Fully Convolutional Neural Networks for Multi-slice MRI Cardiac Segmentation
TLDR
A recurrent fully-convolutional network (RFCN) that learns image representations from the full stack of 2D slices and has the ability to leverage inter-slice spatial dependences through internal memory units is proposed.
Global Assessment of Cardiac Function Using Image Statistics in MRI
TLDR
This study proposes to estimate the cardiac ejection fraction in real-time directly from image statistics using machine learning technique and demonstrates that the estimated EFs correlate very well with those obtained from independent manual segmentations.
Regional Assessment of Cardiac Left Ventricular Myocardial Function via MRI Statistical Features
TLDR
A real-time machine-learning approach which uses some image features that can be easily computed, but that nevertheless correlate well with the segmental cardiac function, and demonstrates that, over a cardiac cycle, the statistical features are related to the proportion of blood within each segment.
Direct Estimation of Cardiac Biventricular Volumes With an Adapted Bayesian Formulation
TLDR
The proposed method introduces a novel likelihood function to exploit multiple appearance features, and a novel prior probability model to incorporate the area correlation between LV and RV cavities and enables a direct, efficient, and accurate assessment of global cardiac functions.
Direct and Simultaneous Four-Chamber Volume Estimation by Multi-Output Regression
TLDR
This paper proposes a new method for direct and simultaneous four-chamber volume estimation using multi-output regression that can disentangle complex relationship of image appearance and four- chamber volumes via statistical learning using a supervised descriptor learning SDL algorithm.
Prediction of Clinical Information from Cardiac MRI Using Manifold Learning
TLDR
It is demonstrated that it is possible to learn anatomical and functional information from cardiac MR imaging without explicit segmentation in order to predict clinical variables such as blood pressure with high accuracy.
...
...