Progress of Right Ventricle Segmentation from Short-Axis Images Acquired with Cardiac Cine MRI

doi:10.11938/cjmr20182678

Abstract

Abstract: Right ventricle (RV) segmentation is essential for assessing cardiac function in patients with pulmonary hypertension, tetralogy of Fallot, and so on. However, it remains difficult due to the complex structure of heart, thin myocardium and large variability of the RV, as well as the interferences from the fat nearby. Due to its high temporal and spatial resolution, cardiac cine magnetic resonance imaging is widely used for functional evaluation of the heart. This article reviews the commonly-used methods for RV segmentation from the cardiac cine magnetic resonance images. The traditional algorithms are described first, followed by the novel multi-atlas and deep learning methods. Lastly, the evaluation standards for RV segmentation are introduced. It is concluded that the deep learning-based segmentation methods may have the potential to become the method of choice in clinical settings due to their high efficiency and accuracy in the diagnosis and prognosis of the heart-related diseases.

Key words: cardiac cine magnetic resonance imaging, short-axis image, right ventricle segmentation, multi-atlas, deep learning

CLC Number:

SU Xin-yu, WANG Li-jia, NIE Sheng-dong, HU Li-wei, ZHONG Yu-min. Progress of Right Ventricle Segmentation from Short-Axis Images Acquired with Cardiac Cine MRI[J]. Chinese Journal of Magnetic Resonance, 2019, 36(3): 377-391.

References

[1] BREWIS M J, BELLOFIORE A, VANDERPOOL R R, et al. Imaging right ventricular function to predict outcome in pulmonary arterial hypertension[J]. Int J Cardiol, 2016, 218:206-211.
[2] KUTTY S, SHANG Q, JOSEPH N, et al. Abnormal right atrial performance in repaired tetralogy of Fallot:A CMR feature tracking analysis[J]. Int J Cardiol, 2017, 248:136-142.
[3] VOELKEL N F, QUAIFE R A, LEINWAND L A, et al. Right ventricular function and failure:report of a national heart, lung, and blood institute working group on cellular and molecular mechanisms of right heart failure[J]. Circulation, 2006, 114(17):1883-1891.
[4] HAUTVAST G, LOBREGT S, BREEUWER M, et al. Automatic contour propagation in cine cardiac magnetic resonance images[J]. IEEE Trans Med Imaging, 2006, 25(11):1472-1482.
[5] 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.
[6] 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.
[7] ZULUAGA M, CARDOSO M, MODAT M, et al. Multi-atlas propagation whole heart segmentation from MRI and CTA using a local normalised correlation coefficient criterion[C]. Lodon:FIMH 2013:Functional Imaging and Modeling of the Heart, 2013, 7945:172-180.
[8] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]. Boston:2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015:3431-3440.
[9] BAI W J, SHI W Z, LEDIG C, et al. Multi-atlas segmentation with augmented features for cardiac MR images[J]. Med Image Anal, 2015, 19(1):98-109.
[10] LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Med Image Anal, 2017, 42:60-88.
[11] 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.
[12] KATOUZIAN A, PRAKASH A, KONOFAGOU E. A New automated technique for left-and right-ventricular segmentation in magnetic resonance imaging[J]. Conf Proc IEEE Eng Med Biol Soc, 2006, 1:3074-3077.
[13] WANG L J, PEI M C, CODELLA N C, et al. Left ventricle:fully automated segmentation based on spatiotemporal continuity and myocardium information in cine cardiac magnetic resonance imaging (LV-FAST)[J]. BioMed Res Int, 2015, 2015:367583.
[14] ROSADO-TORO J A, ABIDOV A, ALTBACH M I, et al. Segmentation of the right ventricle in four chamber cine cardiac MR images using polar dynamic programming[J]. Comput Med Imaging Graph, 2017, 62:15-25.
[15] GOSHTASBY A, TURNER D A. Segmentation of cardiac cine MR images for extraction of right and left ventricular chambers[J]. IEEE Trans Med Imaging, 1995, 14(1):56-64.
[16] WANG C W, PENG C W, CHEN H C. A simple and fully automatic right ventricle segmentation method for 4-dimensional cardiac MR images[C]//Nice:Proceedings of 3D Cardiovascular Imaging:A MICCAI Segmentation Challenge, 2012.
[17] YILMAZ P, WALLECAN K, KRISTANTO W, et al. Evaluation of a semi-automatic right ventricle segmentation method on short-axis MR images[J]. J Digit Imaging, 2018, 31(5):670-679.
[18] MAIER O M O, JIMENEZ D, SANTOS A, et al. Segmentation of RV in 4D cardiac MR volumes using region-merging graph cuts[C]//Krakow:2012 Computing in Cardiology, 2012:697-700.
[19] GROSGEORGE D, PETITJEAN C, DACHER J N, et al. Graph cut segmentationwith a statistical shape model in cardiac MRI[J]. Comput Vis Image Und, 2013, 117(9):1027-1035.
[20] ABI-NAHED J, JOLLY M P, YANG G Z. Robust active shape models:A robust, generic and simple automatic segmentation tool[C]//Copenhagen:Medical Image Computing and Computer Assisted Intervention, 2006:1-8.
[21] GROSGEORGE D, PETITJEAN C, CAUDRON J, et al. Automatic cardiac ventricle segmentation in MR images:a validation study[J]. Int J Comput Assist Radiol Surg, 2011, 6(5):573-581.
[22] ARRIETA C, URIBE S, SING-LONG C, et al. Simultaneous left and right ventricle segmentation using topology preserving level sets[J]. Biomed Signal Processing, 2017, 33:88-95.
[23] HUANG J S, HUANG X L, METAXAS D, et al. Dynamic texture based heart localization and segmentation in 4-D cardiac images[C]//Arlington:20074th IEEE International Symposium on Biomedical Imaging:From Nano to Macro, 2007:852-855.
[24] MITCHELL S C, LELIEVELDT B P, VAN DER GEEST R J, et al. Multistage hybrid active appearance model matching:Segmentation of left and right ventricles in cardiac MR images[J]. IEEE Trans Med Imaging, 2001, 20(5):415-423.
[25] ZHANG H H, WAHLE A, JOHNSON R K, et al. 4-D Cardiac MR image analysis:Left and right ventricular morphology and function[J]. IEEE Trans Med Imaging, 2010, 29(2):350-364.
[26] ROHLFING T, BRANDT R, MENZEL R, et al. Evaluation of atlas selection strategies for atlas based image segmentation with application to confocal microscopy images of bee brains[J]. NeuroImage, 2004, 21(4):1428-1442.
[27] ZHANG Y N, CHEN C S, KANG Y. Accurate segmentation of right ventricles based on multi-atlas with affinity propagation clustering selection[J]. Journal of Northeastern University (Natural Science), 2014, 35(6):795-799. 张耀楠, 陈传慎, 康雁. 基于仿射传播聚类选择的多Atlas右心室精准分割[J]. 东北大学学报(自然科学版), 2014, 35(6):795-799.
[28] AWATE S P, ZHU P H, WHITAKER R T. How many templates does it take for a good segmentation?:Error analysis in multiatlas segmentation as a function of database size[J]. Med Image Comput Compu Assist Interv, 2012, 7509:103-114.
[29] YU J, CHEN X, ZHOU Y P. Improved multi-step registration method for cardiac nuclear magnetic resonance image[J]. Software Guide, 2016, 15(5):207-209. 余军, 陈雪, 周勇攀. 一种改进的心脏核磁共振图像多步配准方法[J]. 软件导刊, 2016, 15(5):207-209.
[30] PUNITHAKUMAR K, NOGA M, BEN AYED I, et al. Right ventricular segmentation in cardiac MRI with moving mesh correspondences[J]. Comput Med Imaging Graph, 2015, 43:15-25.
[31] LORENZO-VALDÉS M, SANCHEZ-ORTIZ G I, MOHIADDIN R, et al. Atlas-based segmentation and tracking of 3D cardiac MR images using non-rigid registration[C]//Tokyo:Medical Image Computing and Computer Assisted Intervention. 2002:642-650.
[32] SHI W Z, ZHUANG X H, PIZARRO L, et al. Registration using sparse free-form deformations[J]. Med Image Comput Comput Assist Interv, 2012, 15(pt2):659-666.
[33] BAI W J, SHI W Z, O'REGAN D P, et al. A probabilistic patch-based label fusion model for multi-atlas segmentation with registration refinement:Application to cardiac MR images[J]. IEEE Trans Med Imaging, 2013, 32(7):1302-1315.
[34] OU Y M, SOTIRAS A, PARAGIOS N, et al. DRAMMS:deformable registration via attribute matching and mutual-saliency weighting[J]. Med Image Anal, 2011, 15(4):622-639.
[35] ZHUANG X, HAWKES D J, CRUM W R, et al. Robust registration between cardiac MRI images and atlas for segmentation propagation[C]//USA:SPIE Medical Imaging Symposium. 2008:1-11
[36] ZHUANG X H. Multivariate mixture model for myocardial segmentation combining multi-source images[J]. IEEE T Pattern Anal, 2018:1.
[37] ASMAN A J, LANDMAN B A. Robust statistical label fusion through consensus level, labeler accuracy, and truth estimation (COLLATE)[J]. IEEE Trans Med Imaging, 2011, 30(10):1779-1794.
[38] ASMAN A J, LANDMAN B A. Non-local statistical label fusion for multi-atlas segmentation[J]. Med Image Anal, 2013, 17(2):194-208.
[39] LORENZO-VALDÉS M, SANCHEZ-ORTIZ G I, MOHIADDIN R, et al. Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm[J]. Med Image Anal, 2004, 8(3):255-265.
[40] 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.
[41] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323:533-536.
[42] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[43] HINTON G E,OSINDERO S,TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Comput, 2006, 18(7):1527-1554.
[44] GARCIA-GARCIA A, ORTS-ESCOLANO S, OPREA S, et al. A reviewon deep learning techniques applied to semanticsegmentation[J]. Computer Vision and Pattern Recognition, 2017. arXiv:1704.06857
[45] RONNEBERGER O, FISCHER P, BROX T. U-Net:Convolutional networks for biomedical image segmentation[J]. Computer Vision and Pattern Recognition, 2015. arXiv:1505.04597.
[46] 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.
[47] POUDEL R P K, LAMATA P, MONTANA G. Recurrent fully convolutional neural networks for multi-slice MRI cardiac segmentation[J]. MICCAI Workshop RAMBO, 2016. arXiv:1608.03974.
[48] OKTAY O, BAI W, LEE M, et al. Multi-input cardiac image super-resolution using convolutional neural networks[C]//MICCAI Workshop RAMBO, 2016. 246-254.
[49] CHEN J, ZHANG H V, ZHANG W W, et al. Correlated regression feature learning for automated right ventricle segmentation[J]. IEEE J Trans Eng Health Med, 2018, 6:1800610.
[50] DU X Q, ZHANG W W, ZHANG H Y, et al. Deep regression segmentation for cardiac bi-ventricle MR images[J]. IEEE Access, 2018, 6:3828-3838.
[51] 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.
[52] BAUMGARTNER C F, KOCH L M, POLLEFEYS M, et al. An Exploration of 2D and 3D deep learning techniques for cardiac MR image segmentation[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:111-119.
[53] ISENSEE F, JAEGER P, FULL P, et al. Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:120-129.
[54] 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.
[55] YANG X, BIAN C, YU L, et al. Class-balanced deep neural network for automatic ventricular structure segmentation[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:152-160.
[56] JANG J, HA S, KIM S, et al. Automatic segmentation of LV and RV in cardiac MRI[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:161-169.
[57] KHENED M, ALEX V, KRISHNAMURTHI G. Densely connected fully convolutional network for short-axis cardiac cine mr image segmentation and heart diagnosis using random forest[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:140-151.
[58] ROHE M M, SERMESANT M, PENNEC X. Automatic multi-atlas segmentation of myocardium with SVF-Net[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:170-177.
[59] 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.
[60] WOLTERINK J M, LEINER T, VIERGEVER M A, et al. Automatic segmentation and disease classification using cardiac cine MR images[C]//Quebec:ACDC and MMWHS Challenges, 2017, 10663:101-110.
[61] RUPPRECHT C, HUAROC E, BAUST M, et al. Deep active contours[J]. Computer Vision and Pattern Recognition, 2016. arXiv:1607.05074.
[62] 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[J]. Med Image Anal, 2017, 35:159-171.