Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets
This work addresses the challenge of accurate whole-heart and great vessel segmentation for computer-assisted diagnosis of cardiovascular disease, representing an incremental improvement over existing methods.
The authors tackled the problem of automatic 3D cardiovascular MR segmentation by proposing DenseVoxNet, a densely-connected volumetric convolutional neural network, which achieved the best dice coefficient on the HVSMR 2016 challenge and outperformed other 3D ConvNets with fewer parameters.
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.