Dilated Convolutions in Neural Networks for Left Atrial Segmentation in 3D Gadolinium Enhanced-MRI

TL;DR

This paper introduces a 3D CNN with dilated convolutions and residual connections for automatic segmentation of the left atrial chamber in 3D Gadolinium-enhanced MRI, improving accuracy by capturing local and global features.

Contribution

The study proposes a novel 3D CNN architecture that integrates dilated convolutions and residual connections to enhance segmentation performance in cardiac MRI.

Findings

Improved segmentation accuracy over standard 3D U-Net.

Dilated convolutions help incorporate global context.

Enhanced domain adaptation capabilities.

Abstract

Segmentation of the left atrial chamber and assessing its morphology, are essential for improving our understanding of atrial fibrillation, the most common type of cardiac arrhythmia. Automation of this process in 3D gadolinium enhanced-MRI (GE-MRI) data is desirable, as manual delineation is time-consuming, challenging and observer-dependent. Recently, deep convolutional neural networks (CNNs) have gained tremendous traction and achieved state-of-the-art results in medical image segmentation. However, it is difficult to incorporate local and global information without using contracting (pooling) layers, which in turn reduces segmentation accuracy for smaller structures. In this paper, we propose a 3D CNN for volumetric segmentation of the left atrial chamber in LGE-MRI. Our network is based on the well known U-Net architecture. We employ a 3D fully convolutional network, with dilated convolutions in the lowest level of the network, and residual connections between encoder blocks to incorporate local and global knowledge. The results show that including global context through the use of dilated convolutions, helps in domain adaptation, and the overall segmentation accuracy is improved in comparison to a 3D U-Net.