Automatic Segmentation of Right Ventricle in Cine Cardiac Magnetic Resonance Image Based on a Dense and Multi-Scale U-net Method

doi:10.11938/cjmr20192794

Abstract

Abstract: Evaluating cardiac function from magnetic resonance images requires segmentation of the right ventricle (RV). The traditional segmentation methods, however, are often ineffective due to the complex structure of RV. Herein, a dense and multi-scale U-net (DMU-net) method is proposed to segment RV. Fifty six datasets were preprocessed, and the steps included normalization, enhancement and region of interest (ROI) extraction. Then a DMU-net was constructed by combining multi-scale aggregation with nested dense connection. The preprocessed datasets were then used to train and verify the DMU-net for predicting the results in 15 datasets with ROI extraction only. The mean of Dice index and Hausdorff distance obtained with the proposed method were 0.862 and 4.44 mm, respectively, which were better than those obtained with the conventional methods. Correlation coefficients of the endo-diastolic volume, endo-systolic volume, ejection fraction and stroke volume estimated were 0.992, 0.960, 0.987 and 0.982, respectively. The results demonstrated that the segmentation method based on the DMU-net has better relevance and consistency compared to manual segmentation, providing a promising tool the diagnosis of cardiac diseases.

Key words: cardiac magnetic resonance image, right ventricle segmentation, deep learning, dense and multi-scale U-net

CLC Number:

LIU Peng, ZHONG Yu-min, WANG Li-jia. Automatic Segmentation of Right Ventricle in Cine Cardiac Magnetic Resonance Image Based on a Dense and Multi-Scale U-net Method[J]. Chinese Journal of Magnetic Resonance, 2020, 37(4): 456-468.

References

[1] MENDIS S, PUSKA P, NORRVING B. Global atlas on cardiovascular disease prevention and control[M]. Geneva:Geneva World Health Organization, 2011:1-13.
[2] CAUDRON J, FARES J, VIVIER P H, et al. Diagnostic accuracy and variability of three semi-quantitative methods for assessing right ventricular systolic function from cardiac MRI in patients with acquired heart disease[J]. Eur Radiol, 2011, 21(10):2111-2120.
[3] HUANG X Q, ZHAO L L, CHEN L Y, et al. Accelerated cardiac CINE imaging with CAIPIRINHA and partial parallel acquisition[J]. Chinese J Magn Reson, 2017, 34(3):283-293. 黄小倩, 赵乐乐, 陈利勇, 等. 基于同时多层激发和并行成像的心脏磁共振电影成像[J]. 波谱学杂志, 2017, 34(3):283-293.
[4] PETITJEAN C, DACHER J N. A review of segmentation methods in short axis cardiac MR images[J]. Med Image Anal, 2011, 15(2):169-184.
[5] PETITJEAN C, ZULUAGA M A, BAI W, et al. Right ventricle segmentation from cardiac MRI:A collation study[J]. Med Image Anal, 2015, 19(1):187-202.
[6] PENG P, LEKADIR K, GOOVA A, et al. A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging[J]. Magn Reson Mater Phy, 2016, 29(2):155-195.
[7] AUGER D A, ZHONG X, EPSTEIN F H, et al. Semi-automated left ventricular segmentation based on a guide point model approach for 3D cine DENSE cardiovascular magnetic resonance[J]. J Cardiovasc Magn R, 2014, 16(1):8.
[8] GROSGEORGE D, PETITJEAN C, DACHER J N, et al. Graph cut segmentation with a statistical shape model in cardiac MRI[J]. Comput Vis Image Und, 2013, 117(9):1027-1035.
[9] LIU H, HU H F, XU X Y, et al. Automatic left ventricle segmentation in cardiac mri using topological stable-state thresholding and region restricted dynamic programming[J]. Acad Radiol, 2012, 19(6):723-731.
[10] BERNARD O, LALANDE A, ZOTTI C, et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis:Is the problem solved?[J]. IEEE T Med Imaging, 2018, 37(11):2514-2525.
[11] ZULUAGA M A, CARDOSO M J, OURSELIN S. Automatic right ventricle segmentation using multi-lablel fusion in cradiac MRI[C]//Medical Image Computing nd Computer-Assisted Intervention-MICCAI 2012. arXiv:2004, 02317.
[12] LI Y, WANG L J, NIE S D. Research progress of automatic right ventricle segmentation based on cardiac cine magnetic resonance image[J]. Journal of Biomedical Engineering, 2016, 33(6):1203-1208.李亚, 王丽嘉, 聂生东. 基于心脏电影磁共振图像的右心室自动分割研究进展[J]. 生物医学工程学杂志, 2016, 33(6):1203-1208.
[13] TRAN P V. A fully convolutional neural network for cardiac segmentation in short-axis MRI[J]. Computer Vision and Pattern Recognition, 2016. arXiv:1604.00494.
[14] RONNEBERGER O, FISCHER P, BROX T. U-Net:Convolutional networks for biomedical image segmentation[J]. Computer Vision and Pattern Recognition, 2015. arXiv:1505.04597.
[15] SU X Y, WANG L J, NIE S D, et al. Progress of right ventricle segmentation from short-axis images acquired with cardiac cine MRI[J]. Chinese J Magn Reson, 2019, 36(3):377-391. 苏新宇, 王丽嘉, 聂生东, 等. 基于心脏磁共振短轴电影图像的右心室分割新进展[J]. 波谱学杂志, 2019, 36(3):377-391.
[16] KHENED M, ALEX V, KRISHNAMURTHI G. Fully convolutional multi-scale residual densenets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers[J]. Med Image Anal, 2019, 51:21-45.
[17] HUANG G, LIU Z, LAURENS V D M, et al. Densely connected convolutional networks[J]. Computer Vision and Pattern Recognition, 2017. arXiv:1608.06993
[18] AVENDI M R, KHERADVAR A, JAFARKHANI H. A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI[J]. Med Image Anal, 2016, 30:108-119.
[19] YANG H, SUN J, LI H, et al. Deep fusion net for multi-atlas segmentation:application to cardiac MR images[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016, 2016:521-528.
[20] PATRAVALI J, JAIN S, CHILAMKURTHY S. 2D-3D fully convolutional neural networks for cardiac MR segmentation[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:130-139.
[21] ZHENG Q, DELINGETTE H, DUCHATEAU N, et al. 3D consistent & robust segmentation of cardiac images by deep learning with spatial propagation[J]. IEEE T Med Imaging, 2018, 37(9):2137-2148.
[22] LIEMAN S J, LE M, LAU F, et al. FastVentricle:cardiac segmentation with ENet[J]. Computer Vision and Pattern Recognition, 2017. arXiv:1704.04296
[23] ZOTTI C, LUO Z, HUMBERT O, et al. Gridnet with automatic shape prior registration for automatic mri cardiac segmentation[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:73-81.
[24] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[J]. Computer Vision and Pattern Recognition, 2014. arXiv:1409.4842
[25] ZHOU Z W, SIDDIQUEE M M R, TAIBAKHSH N, et al. UNet++:A nested U-Net architecture for medical image segmentation[J]. Computer Vision and Pattern Recognition, 2018. arXiv:1807.10165
[26] BADRINARAYANAN V, KENDALL A, CIPOLLA R. SegNet:A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE T Pattern Anal, 2017, 39(12):2481-2495.
[27] ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[J]. Computer Vision and Pattern Recognition, 2017. arXiv:1612.01105.
[28] WANG L J, SU X Y, LI Y, et al. Segmentation of right ventricle in cardiac cine MRI using COLLATE fusion-based Multi-Atlas[J]. Chinese J Magn Reson, 2018, 35(4):407-416.王丽嘉, 苏新宇, 李亚, 等. 基于COLLATE融合多图谱的心脏电影MRI右心室分割[J]. 波谱学杂志, 2018, 35(4):407-416.
[29] KYHL K, AHTAROVSKI K A, IVERSEN K, et al. The decrease of cardiac chamber volumes and output during positive-pressure ventilation[J]. Am J Physiol Heart Circ Physiol, 2013, 305(7):H1004-H1009.
[30] LEI X L, LIU H, HAN Y C, et al. Reference values of cardiac ventricular structure and function by steady-state free-procession MRI at 3.0T in healthy adult chinese volunteers[J]. J Magn Reson Imaging, 2017, 45(6):1684-1692.