Deep learning cardiac motion analysis for human survival prediction

@article{Bello2019DeepLC,
  title={Deep learning cardiac motion analysis for human survival prediction},
  author={Ghalib A. Bello and Timothy J. W. Dawes and Jinming Duan and Carlo Biffi and Antonio de Marvao and Luke S G Howard and J. Simon R. Gibbs and Martin R. Wilkins and Stuart A. Cook and Daniel Rueckert and Declan P. O’Regan},
  journal={Nature machine intelligence},
  year={2019},
  volume={1},
  pages={95 - 104}
}
Motion analysis is used in computer vision to understand the behaviour of moving objects in sequences of images. Optimizing the interpretation of dynamic biological systems requires accurate and precise motion tracking as well as efficient representations of high-dimensional motion trajectories so that these can be used for prediction tasks. Here we use image sequences of the heart, acquired using cardiac magnetic resonance imaging, to create time-resolved three-dimensional segmentations using… 

Figures and Tables from this paper

Joint analysis of clinical risk factors and 4D cardiac motion for survival prediction using a hybrid deep learning network
In this work, a novel approach is proposed for joint analysis of high dimensional time-resolved cardiac motion features obtained from segmented cardiac MRI and low dimensional clinical risk factors
Artificial Intelligence in Cardiac Imaging With Statistical Atlases of Cardiac Anatomy
TLDR
A mini review highlighting recent advances in statistical atlasing of cardiac function in the context of artificial intelligence in cardiac imaging is provided.
EchoNet-Dynamic: a Large New Cardiac Motion Video Data Resource for Medical Machine Learning
TLDR
This is the largest labeled medical video dataset made available publicly to researchers and medical professionals and first public report of video-based 3D convolutional architectures to assess cardiac function.
A Deep Learning Based Cardiac Cine Segmentation Framework for Clinicians - Transfer Learning Application to 7T
TLDR
Data requirements for transfer learning to cardiac 7T in humans where the segmentation task can be challenging are assessed and guidelines, tools, and annotated data are provided to enable transfer learning approaches of other researchers and clinicians.
Fully Automated 3D Cardiac MRI Localisation and Segmentation Using Deep Neural Networks
TLDR
This paper proposes two strategies for localizing and segmenting the heart ventricles and myocardium, termed multi-stage and end-to-end, using a 3D convolutional neural network, and evaluates the two proposed segmentation strategies on two cardiac MRI datasets.
Neural network-based left ventricle geometry prediction from CMR images with application in biomechanics
Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network
TLDR
This paper proposes a novel recurrent generative adversarial network model for cardiac MRI motion artifact reduction that utilizes bi-directional convolutional long short-term memory (ConvLSTM) and multi-scale convolutions to improve the performance of the proposed network.
Deep Learning Interpretation of Echocardiograms
TLDR
It is shown that deep learning applied to echocardiography can identify local cardiac structures, estimate cardiac function, and predict systemic phenotypes that modify cardiovascular risk but not readily identifiable to human interpretation.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 119 REFERENCES
Learning Interpretable Anatomical Features Through Deep Generative Models: Application to Cardiac Remodeling
TLDR
The proposed 3D convolutional generative model leverages interpretable task-specific anatomic patterns learned from 3D segmentations and allows to visualise and quantify the learned pathology-specific remodeling patterns in the original input space of the images.
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks
TLDR
An automated analysis method based on a fully convolutional network achieves a performance on par with human experts in analysing CMR images and deriving clinically relevant measures.
Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach
TLDR
A multi-task deep learning approach with atlas propagation is combined to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images that is robust and capable of producing accurate, high-resolution, and anatomically smooth bi- ventricular 3D models, despite the presence of artifacts in input CMR volumes.
Automatic 3D bi-ventricular segmentation of cardiac images by a shape-constrained multi-task deep learning approach
TLDR
A multi-task deep learning approach with atlas propagation is combined to develop a shape-constrained bi-ventricular segmentation pipeline for short-axis CMR volumetric images that is robust and capable of producing accurate, high-resolution and anatomically smooth bi- ventricular 3D models, despite the artefacts in input CMR volumes.
Deep Representation Learning for Human Motion Prediction and Classification
TLDR
The results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction.
A multimodal spatiotemporal cardiac motion atlas from MR and ultrasound data
Deep Spectral-Based Shape Features for Alzheimer's Disease Classification
TLDR
The proposed method uses triangulated surface meshes extracted from segmented hippocampus structures in MRI and point-to-point correspondences are established among population of surfaces using a spectral matching method to classify Alzheimer’s patients from normal subjects.
Morphologically normalized left ventricular motion indicators from MRI feature tracking characterize myocardial infarction
TLDR
In conclusion, LV spatio-temporal motion attributes accurately characterize the presence of infarction, and this approach is easily generalizable to different pathologies, enabling more precise study of the pathophysiological consequences of a wide spectrum of cardiac diseases.
Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models
TLDR
It is illustrated that deep survival models can successfully transfer information across diseases to improve prognostic accuracy and provide an open-source software implementation of this framework called SurvivalNet that enables automatic training, evaluation and interpretation ofDeep survival models.
...
1
2
3
4
5
...