Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets

TL;DR

This paper introduces DenseVoxNet, a densely-connected 3D convolutional neural network that effectively segments cardiac and vascular structures from MR images, outperforming existing methods with fewer parameters.

Contribution

The paper presents a novel densely-connected volumetric CNN architecture for 3D cardiac MR segmentation, improving training stability and reducing parameter count.

Findings

Achieves the best dice coefficient in HVSMR 2016 challenge

Outperforms other 3D ConvNets in accuracy

Uses fewer parameters than comparable models

Abstract

Automatic and accurate whole-heart and great vessel segmentation from 3D cardiac magnetic resonance (MR) images plays an important role in the computer-assisted diagnosis and treatment of cardiovascular disease. However, this task is very challenging due to ambiguous cardiac borders and large anatomical variations among different subjects. In this paper, we propose a novel densely-connected volumetric convolutional neural network, referred as DenseVoxNet, to automatically segment the cardiac and vascular structures from 3D cardiac MR images. The DenseVoxNet adopts the 3D fully convolutional architecture for effective volume-to-volume prediction. From the learning perspective, our DenseVoxNet has three compelling advantages. First, it preserves the maximum information flow between layers by a densely-connected mechanism and hence eases the network training. Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data. Third, we add auxiliary side paths to strengthen the gradient propagation and stabilize the learning process. We demonstrate the effectiveness of DenseVoxNet by comparing it with the state-of-the-art approaches from HVSMR 2016 challenge in conjunction with MICCAI, and our network achieves the best dice coefficient. We also show that our network can achieve better performance than other 3D ConvNets but with fewer parameters.