Log In Sign Up

Pathology Synthesis of 3D Consistent Cardiac MR Im-ages Using 2D VAEs and GANs

by   Sina Amirrajab, et al.

We propose a method for synthesizing cardiac MR images with plausible heart shapes and realistic appearances for the purpose of generating labeled data for deep-learning (DL) training. It breaks down the image synthesis into label deformation and label-to-image translation tasks. The former is achieved via latent space interpolation in a VAE model, while the latter is accomplished via a conditional GAN model. We devise an approach for label manipulation in the latent space of the trained VAE model, namely pathology synthesis, aiming to synthesize a series of pseudo-pathological synthetic subjects with characteristics of a desired heart disease. Furthermore, we propose to model the relationship between 2D slices in the latent space of the VAE via estimating the correlation coefficient matrix between the latent vectors and utilizing it to correlate elements of randomly drawn samples before decoding to image space. This simple yet effective approach results in generating 3D consistent subjects from 2D slice-by-slice generations. Such an approach could provide a solution to diversify and enrich the available database of cardiac MR images and to pave the way for the development of generalizable DL-based image analysis algorithms. The code will be available at


page 5

page 7

page 9


On the effectiveness of GAN generated cardiac MRIs for segmentation

In this work, we propose a Variational Autoencoder (VAE) - Generative Ad...

sim2real: Cardiac MR Image Simulation-to-Real Translation via Unsupervised GANs

There has been considerable interest in the MR physics-based simulation ...

XCAT-GAN for Synthesizing 3D Consistent Labeled Cardiac MR Images on Anatomically Variable XCAT Phantoms

Generative adversarial networks (GANs) have provided promising data enri...

Identification of Rare Cortical Folding Patterns using Unsupervised Deep Learning

Like fingerprints, cortical folding patterns are unique to each brain ev...

Explicit Temporal Embedding in Deep Generative Latent Models for Longitudinal Medical Image Synthesis

Medical imaging plays a vital role in modern diagnostics and treatment. ...

CardiacGen: A Hierarchical Deep Generative Model for Cardiac Signals

We present CardiacGen, a Deep Learning framework for generating syntheti...

ImUnity: a generalizable VAE-GAN solution for multicenter MR image harmonization

ImUnity is an original deep-learning model designed for efficient and fl...