Disentangled representation learning in cardiac image analysis (2019-03-22T00:00:00.000000Z)

TL;DR

Spatial Decomposition Network (SDNet) is proposed, which factorises 2D medical images into spatial anatomical factors and non-spatial modality factors and is ideally suited for several medical image analysis tasks, such as semi-supervised segmentation, multi-task segmentation and regression, and image-to-image synthesis.

Authors

S. Tsaftaris

7 papers

A. Chartsias

2 papers

G. Papanastasiou

2 papers

S. Semple

2 papers

D. Newby

2 papers

R. Dharmakumar

2 papers

T. Joyce

1 papers

M. Williams

1 papers

TL;DR

Authors

References55 items

Joint Motion Estimation and Segmentation from Undersampled Cardiac MR Image

ASDNet: Attention Based Semi-supervised Deep Networks for Medical Image Segmentation

Diverse Image-to-Image Translation via Disentangled Representations

Recurrent neural networks for aortic image sequence segmentation with sparse annotations

&OHgr;‐Net (Omega‐Net): Fully automatic, multi‐view cardiac MR detection, orientation, and segmentation with deep neural networks☆

Learning Interpretable Anatomical Features Through Deep Generative Models: Application to Cardiac Remodeling

Deep Learning Based Instance Segmentation in 3D Biomedical Images Using Weak Annotation

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis

Multimodal Unsupervised Image-to-Image Translation

A Variational U-Net for Conditional Appearance and Shape Generation

Understanding disentangling in β-VAE

3-D Consistent and Robust Segmentation of Cardiac Images by Deep Learning With Spatial Propagation

Factorised spatial representation learning: application in semi-supervised myocardial segmentation

Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

Disentangling by Factorising

On the Effectiveness of Least Squares Generative Adversarial Networks

Multi-content GAN for Few-Shot Font Style Transfer

Disentangling Factors of Variation by Mixing Them

Challenges in Disentangling Independent Factors of Variation

Toward Multimodal Image-to-Image Translation

Automated cardiovascular magnetic resonance image analysis with fully convolutional networks

Adversarial Image Synthesis for Unpaired Multi-modal Cardiac Data

Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images

Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation

An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation

FiLM: Visual Reasoning with a General Conditioning Layer

Convolutional neural network regression for short‐axis left ventricle segmentation in cardiac cine MR sequences

Scalable multimodal convolutional networks for brain tumour segmentation

Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation

Semantically Decomposing the Latent Spaces of Generative Adversarial Networks

Disentangling factors of variation in deep representation using adversarial training

beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI

Image Style Transfer Using Convolutional Neural Networks

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Adam: A Method for Stochastic Optimization

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

Challenges and methodologies of fully automatic whole heart segmentation: a review.

Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Detecting Myocardial Ischemia at Rest With Cardiac Phase–Resolved Blood Oxygen Level–Dependent Cardiovascular Magnetic Resonance

Representation Learning: A Review and New Perspectives

A Registration-Based Propagation Framework for Automatic Whole Heart Segmentation of Cardiac MRI

AUTO-ENCODING VARIATIONAL BAYES

GENERATIVE ADVERSARIAL NETS

Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II

Data preprocessing is as in Chartsias et al

c) We also use the self-train method of Bai

Dictionary-Driven Ischemia Detection From Cardiac Phase-Resolved Myocardial BOLD MRI at Rest

Machine Learning, PMLR

We also use data acquired at Edinburgh Imaging Facility QMRI with a 3T scanner

Field of Study

Journal Information

Name

Page

Volume