Cardiac MRI Segmentation with Strong Anatomical Guarantees

07/05/2019
by   Nathan Painchaud, et al.
0

Recent publications have shown that the segmentation accuracy of modern-day convolutional neural networks (CNN) applied on cardiac MRI can reach the inter-expert variability, a great achievement in this area of research. However, despite these successes, CNNs still produce anatomically inaccurate segmentations as they provide no guarantee on the anatomical plausibility of their outcome, even when using a shape prior. In this paper, we propose a cardiac MRI segmentation method which always produces anatomically plausible results. At the core of the method is an adversarial variational autoencoder (aVAE) whose latent space encodes a smooth manifold on which lies a large spectrum of valid cardiac shapes. This aVAE is used to automatically warp anatomically inaccurate cardiac shapes towards a close but correct shape. Our method can accommodate any cardiac segmentation method and convert its anatomically implausible results to plausible ones without affecting its overall geometric and clinical metrics. With our method, CNNs can now produce results that are both within the inter-expert variability and always anatomically plausible.

READ FULL TEXT
research
06/15/2020

Cardiac Segmentation with Strong Anatomical Guarantees

Convolutional neural networks (CNN) have had unprecedented success in me...
research
12/03/2021

Echocardiography Segmentation with Enforced Temporal Consistency

Convolutional neural networks (CNN) have demonstrated their ability to s...
research
05/18/2020

On the effectiveness of GAN generated cardiac MRIs for segmentation

In this work, we propose a Variational Autoencoder (VAE) - Generative Ad...
research
05/22/2017

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

Incorporation of prior knowledge about organ shape and location is key t...
research
09/25/2019

A Radiomics Approach to Computer-Aided Diagnosis with Cardiac Cine-MRI

Use expert visualization or conventional clinical indices can lack accur...
research
07/02/2019

3D Cardiac Shape Prediction with Deep Neural Networks: Simultaneous Use of Images and Patient Metadata

Large prospective epidemiological studies acquire cardiovascular magneti...
research
10/04/2022

A Generative Shape Compositional Framework: Towards Representative Populations of Virtual Heart Chimaeras

Generating virtual populations of anatomy that capture sufficient variab...

Please sign up or login with your details

Forgot password? Click here to reset