Factorised Representation Learning in Cardiac Image Analysis

@article{Chartsias2019FactorisedRL,
  title={Factorised Representation Learning in Cardiac Image Analysis},
  author={Agisilaos Chartsias and Thomas Joyce and Giorgos Papanastasiou and Michelle Claire Williams and David E. Newby and Rohan Dharmakumar and Sotirios A. Tsaftaris},
  journal={Medical image analysis},
  year={2019},
  volume={58},
  pages={
          101535
        }
}
Typically, a medical image offers spatial information on the anatomy (and pathology) modulated by imaging specific characteristics. [...] Key Method To explore the properties of the learned factorisation, we perform latent-space arithmetic and show that we can synthesise CT from MR and vice versa, by swapping the modality factors. We also demonstrate that the factor holding image specific information can be used to predict the input modality with high accuracy. Code will be made available at https://github.com…Expand
Multimodal Cardiac Segmentation Using Disentangled Representation Learning
TLDR
It is shown that multi-input outperforms single-input models, and that it can train a (semi-supervised) model with few (or no) annotations for one of the modalities, as well as applications in Late Gadolinium Enhanced and cine MRI segmentation. Expand
Multimodal cardiac segmentation using disentangled representations
TLDR
A method suitable for multimodal and multi-input learning and analysis, that disentangles anatomical and imaging factors, and combines anatomical content across the modalities to extract more accurate segmentation masks is proposed. Expand
Deep Learning for Cardiac Image Segmentation: A Review
TLDR
A review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging, computed tomography, and ultrasound and major anatomical structures of interest. Expand
Disentangled Representations for Domain-generalized Cardiac Segmentation
TLDR
This paper proposes two data augmentation methods that focus on improving the domain adaptation and generalization abilities of state-to-the-art cardiac segmentation models, and generates more diverse data by rescaling images to different resolutions within a range spanning different scanner protocols. Expand
3D Medical Image Synthesis by Factorised Representation and Deformable Model Learning
TLDR
A factored model based approach to data synthesis has a number of advantages: Firstly, it allows for coherent synthesis of realistic 3D data, as it is only necessary to learn low dimensional generative models over deformations and renderings rather than over the high dimensional 3D images themselves. Expand
Semi-supervised Pathology Segmentation with Disentangled Representations
TLDR
The model is trained in a semi-supervised fashion with new reconstruction losses directly aiming to improve pathology segmentation with limited annotations, and a joint optimization strategy is proposed to fully take advantage of the available annotations. Expand
Artificial Intelligence in Computer Vision: Cardiac MRI and Multimodality Imaging Segmentation
Anatomical segmentation has played a major role within clinical cardiology. Novel techniques through artificial intelligence-based computer vision have revolutionized this process through bothExpand
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. Expand
Recent Advances in Fibrosis and Scar Segmentation From Cardiac MRI: A State-of-the-Art Review and Future Perspectives
  • Yinzhe Wu, Zeyu Tang, Binghuan Li, D. Firmin, Guang Yang
  • Medicine, Computer Science
  • Frontiers in Physiology
  • 2021
TLDR
A state-of-the-art review of conventional and current state of theart approaches utilizing different modalities for accurate cardiac fibrosis and scar segmentation is conducted. Expand
INSIDE: Steering Spatial Attention with Non-Imaging Information in CNNs
TLDR
This paper proposes a mechanism to allow for spatial localisation conditioned on non-imaging information, using a feature-wise attention mechanism comprising a differentiable parametrised function (e.g. Gaussian), prior to applying thefeature-wise modulation. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 56 REFERENCES
Factorised spatial representation learning: application in semi-supervised myocardial segmentation
TLDR
This paper proposes a methodology of latent space factorisation relying on the cycle-consistency principle and demonstrates the proposed method's utility in a semi-supervised setting: it achieves comparable performance to fully supervised networks using a fraction of labelled images in experiments on ACDC and a dataset from Edinburgh Imaging Facility QMRI. Expand
Joint Motion Estimation and Segmentation from Undersampled Cardiac MR Image
TLDR
Experimental results show that the proposed model is robust to undersampled data and is capable of predicting results that are close to that from fully-sampled ones, while bypassing the usual image reconstruction stage. Expand
Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation
TLDR
This work proposes a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end and demonstrates how the learnt deep models of 3-D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies. Expand
Recurrent neural networks for aortic image sequence segmentation with sparse annotations
TLDR
Experiments demonstrate that the proposed image sequence segmentation algorithm by combining a fully convolutional network with a recurrent neural network significantly improves both accuracy and temporal smoothness of segmentation, compared to a baseline method that utilises spatial information only. Expand
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. Expand
An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation
TLDR
A fully automated framework for segmentation of the left and right ventricular cavities and the myocardium on short-axis cardiac MR images is presented and it is found that processing the images in a slice-by-slice fashion using 2D networks is beneficial due to a relatively large slice thickness. Expand
Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation
TLDR
A semi-supervised learning approach, in which a segmentation network is trained from both labelled and unlabelled data, which outperforms a state-of-the-art multi-atlas segmentation method by a large margin and the speed is substantially faster. Expand
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. Expand
Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?
TLDR
How far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies is measured, to open the door to highly accurate and fully automatic analysis of cardiac CMRI. Expand
A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging
TLDR
The goal of this review paper is to discuss the structural and functional CMR indices that have been proposed thus far for clinical assessment of the cardiac chambers, including indices definitions, the requirements for the calculations, exemplar applications in cardiovascular diseases, and the corresponding normal ranges. Expand
...
1
2
3
4
5
...