Non-invasive detection of cardiovascular disorders from radiology scans requires quantitative image analysis of the heart and its substructures. There are well-established measurements that radiologists use for diseases assessment such as ejection fraction, volume of four chambers, and myocardium mass. These measurements are derived as outcomes of precise segmentation of the heart and its substructures. The aim of this paper is to provide such measurements through an accurate image segmentation algorithm that automatically delineates seven substructures of the heart from MRI and/or CT scans. Our proposed method is based on multi-planar deep convolutional neural networks (CNN) with an adaptive fusion strategy where we automatically utilize complementary information from different planes of the 3D scans for improved delineations. For CT and MRI, we have separately designed three CNNs (the same architectural configuration) for three planes, and have trained the networks from scratch for voxel-wise labeling for the following cardiac structures: myocardium of left ventricle (Myo), left atrium (LA), left ventricle (LV), right atrium (RA), right ventricle (RV), ascending aorta (Ao), and main pulmonary artery (PA). We have evaluated the proposed method with 4-fold-cross-validation on the multi-modality whole heart segmentation challenge (MM-WHS 2017) dataset. A precision and dice index of 0.93 and 0.90, and 0.87 and 0.85 were achieved for CT and MR images, respectively. Cardiac CT volume was segmented in about 50 s, with cardiac MRI segmentation requiring around 17 s with multi-GPU/CUDA implementation.
[1]
Ling Shao,et al.
A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging
,
2016,
Magnetic Resonance Materials in Physics, Biology and Medicine.
[2]
Xiahai Zhuang,et al.
Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI
,
2016,
Medical Image Anal..
[3]
Hamid Jafarkhani,et al.
A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI
,
2015,
Medical Image Anal..
[4]
Pablo Lamata,et al.
Recurrent Fully Convolutional Neural Networks for Multi-slice MRI Cardiac Segmentation
,
2016,
RAMBO+HVSMR@MICCAI.
[5]
Pascal Vincent,et al.
The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family
,
2016,
ArXiv.
[6]
Kawal S. Rhode,et al.
CardiacNET: Segmentation of Left Atrium and Proximal Pulmonary Veins from MRI Using Multi-view CNN
,
2017,
MICCAI.
[7]
Martín Abadi,et al.
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
,
2016,
ArXiv.
[8]
Henggui Zhang,et al.
A deep learning network for right ventricle segmentation in short-axis MRI
,
2016,
2016 Computing in Cardiology Conference (CinC).
[9]
S. Ourselin,et al.
Automatic Whole Heart Segmentation Based on Atlas Propagation with A Priori Anatomical Information
,
2008
.