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

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.

[1]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[2]  Peter Kontschieder,et al.  Structured class-labels in random forests for semantic image labelling , 2011, 2011 International Conference on Computer Vision.

[3]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Xin Yang,et al.  3D FractalNet: Dense Volumetric Segmentation for Cardiovascular MRI Volumes , 2016, RAMBO+HVSMR@MICCAI.

[6]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Xiahai Zhuang,et al.  Challenges and methodologies of fully automatic whole heart segmentation: a review. , 2013, Journal of healthcare engineering.

[8]  Anirban Mukhopadhyay Total Variation Random Forest: Fully Automatic MRI Segmentation in Congenital Heart Diseases , 2016, RAMBO+HVSMR@MICCAI.

[9]  Tim Leiner,et al.  Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease , 2016, RAMBO+HVSMR@MICCAI.

[10]  Shan Gao,et al.  Automated Cardiovascular Segmentation in Patients with Congenital Heart Disease from 3D CMR Scans: Combining Multi-atlases and Level-Sets , 2016, RAMBO+HVSMR@MICCAI.

[11]  Georgios Tziritas,et al.  Fully-Automatic Segmentation of Cardiac Images Using 3-D MRF Model Optimization and Substructures Tracking , 2016, RAMBO+HVSMR@MICCAI.

[12]  Polina Golland,et al.  Interactive Whole-Heart Segmentation in Congenital Heart Disease , 2015, MICCAI.

[13]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[14]  Hao Chen,et al.  3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes , 2016, MICCAI.

[15]  Hao Chen,et al.  VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images , 2017, NeuroImage.