Cardiac Segmentation With Strong Anatomical Guarantees

Convolutional neural networks (CNN) have had unprecedented success in medical imaging and, in particular, in medical image segmentation. However, despite the fact that segmentation results are closer than ever to the inter-expert variability, CNNs are not immune to producing anatomically inaccurate...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2020-11, Vol.39 (11), p.3703-3713
Main Authors: Painchaud, Nathan, Skandarani, Youssef, Judge, Thierry, Bernard, Olivier, Lalande, Alain, Jodoin, Pierre-Marc
Format: Article
Language:English
Subjects:
Artificial neural networks
cardiac segmentation
Cardiology and cardiovascular system
CNN
Computer Science
Heart
Human health and pathology
Image processing
Image segmentation
Life Sciences
Magnetic resonance imaging
Medical Imaging
MRI
Neural and Evolutionary Computing
Neural networks
Shape
Three-dimensional displays
Ultrasonic imaging
Ultrasound
variational autoencoder
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional neural networks (CNN) have had unprecedented success in medical imaging and, in particular, in medical image segmentation. However, despite the fact that segmentation results are closer than ever to the inter-expert variability, CNNs are not immune to producing anatomically inaccurate segmentations, even when built upon a shape prior. In this paper, we present a framework for producing cardiac image segmentation maps that are guaranteed to respect pre-defined anatomical criteria, while remaining within the inter-expert variability. The idea behind our method is to use a well-trained CNN, have it process cardiac images, identify the anatomically implausible results and warp these results toward the closest anatomically valid cardiac shape. This warping procedure is carried out with a constrained variational autoencoder (cVAE) trained to learn a representation of valid cardiac shapes through a smooth, yet constrained, latent space. With this cVAE, we can project any implausible shape into the cardiac latent space and steer it toward the closest correct shape. We tested our framework on short-axis MRI as well as apical two and four-chamber view ultrasound images, two modalities for which cardiac shapes are drastically different. With our method, CNNs can now produce results that are both within the inter-expert variability and always anatomically plausible without having to rely on a shape prior.
ISSN:0278-0062
1558-254X
DOI:10.1109/TMI.2020.3003240