Abstract
In this paper, we propose a fully automatic MRI cardiac segmentation method based on a novel deep convolutional neural network (CNN) designed for the 2017 ACDC MICCAI challenge. The novelty of our network comes with its embedded shape prior and its loss function tailored to the cardiac anatomy. Our model includes a cardiac center-of-mass regression module which allows for an automatic shape prior registration. Also, since our method processes raw MR images without any manual preprocessing and/or image cropping, our CNN learns both high-level features (useful to distinguish the heart from other organs with a similar shape) and low-level features (useful to get accurate segmentation results). Those features are learned with a multi-resolution conv-deconv “grid” architecture which can be seen as an extension of the U-Net.
Experimental results reveal that our method can segment the left and right ventricles as well as the myocardium from a 3D MRI cardiac volume in 0.4 s with an average Dice coefficient of 0.90 and an average Hausdorff distance of \(10.4\) mm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
No need to store the probability of “Back” since the 4 probabilities sum up to 1.
References
Epstein, F.H.: MRI of left ventricular function. J Nucl. Cardiol 14(5), 729–744 (2007)
Vick, G.W.: The gold standard for noninvasive imaging in coronary heart disease: magnetic resonance imaging. Curr. opin. cardiol. 24(6), 567–579 (2009)
Peng, P., et al.: A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging. MAGMA 29(2), 155–195 (2016)
Petitjean, C., et al.: Right ventricle segmentation from cardiac MRI: a collation study. Med. Image Anal. 19(1), 187–202 (2015)
Auger, D.A., et al.: Semi-automated left ventricular segmentation based on a guide point model approach for 3D cine DENSE cardiovascular magnetic resonance. J. Cardiovasc. Magn. Reson. 16(1), 8 (2014)
Grosgeorge, D., Petitjean, C., Dacher, J.-N., Ruan, S.: Graph cut segmentation with a statistical shape model in cardiac MRI. CVIU 117(9), 1027–1035 (2013)
Petitjean, C., Dacher, J.: A review of segmentation methods in short axis cardiac MR images. Med. Image Anal. 15(2), 169–184 (2011)
Wang, L., Pei, M., Codella, N.C.F., et al.: Left ventricle: fully automated segmentation based on spatiotemporal continuity and myocardium information in cine cardiac magnetic resonance imaging (LV-FAST). BioMed Res. Int. 2015, 9 (2015). https://doi.org/10.1155/2015/367583. Article ID 367583
Liu, Y., Captur, G., et al.: Distance regularized two level sets for segmentation of left and right ventricles from cine-MRI. Magn. Reson. Img. 34(5), 699–706 (2016)
Tran, P.V.: A fully convolutional neural network for cardiac segmentation in short-axis MRI. arXiv preprint arXiv:1604.00494 (2016)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of CVPR, pp. 3431–3440 (2015)
Noh, H., Hong, S., Han, S.: Learning deconvolution network for semantic segmentation. In: Proceedings of ICCV (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Proceedings of MICCAI, pp. 234–241 (2015)
Tan, L.K., et al.: Cardiac left ventricle segmentation using convolutional neural network regression. In: Proceedings of IECBES, pp. 490–493. IEEE (2016)
Ngo, T.A., Lu, Z., Carneiro, G.: Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance. Med. Image Anal. 35(1), 159–171 (2017)
Kastler, B.: Cardiovascular anatomy and atlas of MR normal anatomy. MRI of Cardiovascular Malformations, pp. 17–39. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-540-30702-0_2
ACDC-MICCAI challenge. http://acdc.creatis.insa-lyon.fr/
Tavakoli, V., Amini, A.A.: A survey of shaped-based registration and segmentation techniques for cardiac images. CVIU 117(9), 966–989 (2013)
Luo, Z., Mishra, A., Achkar, A., Eichel, J., Li, S.-Z., Jodoin, P.-M.: Non-local deep features for salient object detection. In: proceeding of CVPR (2017)
Srivastava, N., Hinton, G., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. of Mach. Learn. Res. 15, 1929–1958 (2014)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of ICLR (2015)
Zou, K.H., et al.: Statistical validation of image segmentation quality based on a spatial overlap index 1: scientific reports. Acad. rad. 11(2), 178–189 (2004)
Huttenlocher, D., Klanderman, G., Rucklidge, W.J.: Comparing images using the Hausdorff distance. IEEE Trans PAMI 15(9), 850–863 (1993)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Zotti, C., Luo, Z., Humbert, O., Lalande, A., Jodoin, PM. (2018). GridNet with Automatic Shape Prior Registration for Automatic MRI Cardiac Segmentation. In: Pop, M., et al. Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges. STACOM 2017. Lecture Notes in Computer Science(), vol 10663. Springer, Cham. https://doi.org/10.1007/978-3-319-75541-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-75541-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-75540-3
Online ISBN: 978-3-319-75541-0
eBook Packages: Computer ScienceComputer Science (R0)