Sequential shape similarity for active contour based left ventricle segmentation in cardiac cine MR image

Ke Bi; Yue Tan; Ke Cheng; Qingfang Chen; Yuanquan Wang; Ke Bi; Yue Tan; Ke Cheng; Qingfang Chen; Yuanquan Wang

doi:10.3934/mbe.2022074

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 2: 1591-1608. doi: 10.3934/mbe.2022074

Previous Article Next Article

Research article Special Issues

Sequential shape similarity for active contour based left ventricle segmentation in cardiac cine MR image

Ke Bi ¹,
Yue Tan ²,
Ke Cheng ^{3
,
,},
Qingfang Chen ⁴,
Yuanquan Wang ^{2
,
,}

1.
School of Economics and Management, Jiangsu University of Science and Technology, Zhenjiang Jiangsu 212003, China
2.
School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China
3.
School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang Jiangsu 212003, China
4.
School of Electronics and Information, Jiangsu University of Science and Technology, Zhenjiang Jiangsu 212003, China

Received: 28 July 2021 Accepted: 03 December 2021 Published: 10 December 2021

Delineation of the boundaries of the Left Ventricle (LV) in cardiac Magnetic Resonance Images (MRI) is a hot topic due to its important diagnostic power. In this paper, an approach is proposed to extract the LV in a sequence of MR images. In the proposed paper, all images in the sequence are segmented simultaneously and the shape of the LV in each image is supposed to be similar to that of the LV in nearby images in the sequence. We coined the novel shape similarity constraint, and it is called sequential shape similarity (SSS in short). The proposed segmentation method takes the Active Contour Model as the base model and our previously proposed Gradient Vector Convolution (GVC) external force is also adopted. With the SSS constraint, the snake contour can accurately delineate the LV boundaries. We evaluate our method on two cardiac MRI datasets and the Mean Absolute Distance (MAD) metric and the Hausdorff Distance (HD) metric demonstrate that the proposed approach has good performance on segmenting the boundaries of the LV.
- magnetic resonance imaging,
- left ventricle,
- image segmentation,
- active contour,
- sequential shape similarity
Citation: Ke Bi, Yue Tan, Ke Cheng, Qingfang Chen, Yuanquan Wang. Sequential shape similarity for active contour based left ventricle segmentation in cardiac cine MR image[J]. Mathematical Biosciences and Engineering, 2022, 19(2): 1591-1608. doi: 10.3934/mbe.2022074

Related Papers:

Abstract

Delineation of the boundaries of the Left Ventricle (LV) in cardiac Magnetic Resonance Images (MRI) is a hot topic due to its important diagnostic power. In this paper, an approach is proposed to extract the LV in a sequence of MR images. In the proposed paper, all images in the sequence are segmented simultaneously and the shape of the LV in each image is supposed to be similar to that of the LV in nearby images in the sequence. We coined the novel shape similarity constraint, and it is called sequential shape similarity (SSS in short). The proposed segmentation method takes the Active Contour Model as the base model and our previously proposed Gradient Vector Convolution (GVC) external force is also adopted. With the SSS constraint, the snake contour can accurately delineate the LV boundaries. We evaluate our method on two cardiac MRI datasets and the Mean Absolute Distance (MAD) metric and the Hausdorff Distance (HD) metric demonstrate that the proposed approach has good performance on segmenting the boundaries of the LV.

References

[1]	P. Croisille, D. Revel, MR imaging of the heart: functional imaging, Eur. Radiol., 10 (2000), 7–11. doi: 10.1007/s003300050003. doi: 10.1007/s003300050003
[2]	J. P. Earls, V. B. Ho, T. K. Foo, E. Castillo, S. D. Flamm, Cardiac MRI: recent progress and continued challenges, J. Magn. Reson. Imaging: JMRI, 16 (2002), 111–127. doi: 10.1002/jmri.10154. doi: 10.1002/jmri.10154
[3]	A. F. Frangi, W. J. Niessen, M. A. Viergever, Three-dimensional modeling for functional analysis of cardiac images, a review, IEEE Trans. Med. Imaging, 20 (2001), 2–5. doi: 10.1109/42.906421. doi: 10.1109/42.906421
[4]	D. Nguyen, K. Masterson, J. P. Vallée, Comparative evaluation of active contour model extensions for automated cardiac MR image segmentation by regional error assessment, Magn. Reson. Mater. Phys., Biol. Med., 20 (2007), 69–82. doi: 10.1007/s10334-007-0069-z. doi: 10.1007/s10334-007-0069-z
[5]	A. Fernández-Caballero, J. M. Vega-Riesco, Determining heart parameters through left ventricular automatic segmentation for heart disease diagnosis, Expert Syst. Appl., 36 (2009), 2234–2249. doi: 10.1016/j.eswa.2007.12.045. doi: 10.1016/j.eswa.2007.12.045
[6]	H. Hu, H. Liu, Z. Gao, L. Huang, Hybrid segmentation of left ventricle in cardiac MRI using gaussian-mixture model and region restricted dynamic programming, Magn. Reson. Imaging, 31 (2013), 575–584. doi: 10.1016/j.mri.2012.10.004. doi: 10.1016/j.mri.2012.10.004
[7]	M. Lorenzo-Valdés, G. I. Sanchez-Ortiz, A. G. Elkington, R. H. Mohiaddin, D. Rueckert, Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm, Med. Image Anal., 8 (2004), 255–265. doi: 10.1016/j.media.2004.09.005. doi: 10.1016/j.media.2004.09.005
[8]	W. Bai, W. Shi, C. Ledig, D. Rueckert, Multi-atlas segmentation with augmented features for cardiac MR images, Med. Image Anal., 19 (2015), 98–109. doi: 10.1016/j.media.2014.09.005. doi: 10.1016/j.media.2014.09.005
[9]	J. Cousty, L. Najman, M. Couprie, S. Clément-Guinaudeau, T. Goissen, J. Garot, Segmentation of 4D cardiac MRI: Automated method based on spatio-temporal watershed cuts, Image Vision Comput., 28 (2010), 1229–1243. doi: 10.1016/j.imavis.2010.01.001. doi: 10.1016/j.imavis.2010.01.001
[10]	M. G. Uzunbaş, S. Zhang, K. M. Pohl, D. Metaxas, L. Axel, Segmentation of myocardium using deformable regions and graph cuts, in 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), (2012), 254–257. doi: 10.1109/ISBI.2012.6235532.
[11]	Y. Wu, Y. Wang, Y. Jia, Segmentation of the left ventricle in cardiac cine MRI using a shape-constrained snake model, Comput. Vision Image Understanding, 117 (2013), 990–1003. doi: 10.1016/j.cviu.2012.12.008. doi: 10.1016/j.cviu.2012.12.008
[12]	Z. Zhang, C. Duan, T. Lin, S. Zhou, Y. Wang, X. Gao, GVFOM: a novel external force for active contour based image segmentation, Inf. Sci., 506 (2020), 1–18. doi: 10.1016/j.ins.2019.08.003. doi: 10.1016/j.ins.2019.08.003
[13]	M. F. Santarelli, V. Positano, C. Michelassi, M. Lombardi, L. Landini, Automated cardiac MR image segmentation: theory and measurement evaluation, Med. Eng. Phys., 25 (2003), 149–159. doi: 10.1016/S1350-4533(02)00144-3. doi: 10.1016/S1350-4533(02)00144-3
[14]	S. Ranganath, Contour extraction from cardiac MRI studies using snakes, IEEE Trans. Med. Imaging, 14 (1995), 328–338. doi: 10.1109/42.387714. doi: 10.1109/42.387714
[15]	T. McInerney, D. Terzopoulos, A dynamic finite element surface model for segmentation and tracking in multidimensional medical images with application to cardiac 4D image analysis, Comput. Med. Imaging Graphics, 19 (1995), 69–83, 1995. doi: 10.1016/0895-6111(94)00040-9. doi: 10.1016/0895-6111(94)00040-9
[16]	J. Liang, G. Ding, Y. Wu, Segmentation of the left ventricle from cardiac MR images based on radial GVF snake, in 2008 International Conference on BioMedical Engineering and Informatics, IEEE, 2 (2008), 238–242. doi: 10.1109/BMEI.2008.188.
[17]	C. Feng, S. Zhang, D. Zhao, C. Li, Simultaneous extraction of endocardial and epicardial contours of the left ventricle by distance regularized level sets, Med. Phys., 43 (2016), 2741–2755. doi: 10.1118/1.4947126. doi: 10.1118/1.4947126
[18]	Y. Liu, G. Captur, J. C. Moon, S. Guo, X. Yang, S. Zhang, et al., Distance regularized two level sets for segmentation of left and right ventricles from cine-MRI, Magn. Reson. Imaging, 34 (2016), 699–706. doi: 10.1016/j.mri.2015.12.027. doi: 10.1016/j.mri.2015.12.027
[19]	J. Lu, C. Feng, J. Yang, W. Li, D. Zhao, C. Wan, Segmentation of the cardiac ventricle using two layer level sets with prior shape constraint. Biomedical Signal Processing and Control, 68 (2021), 102671. doi: 10.1016/j.bspc.2021.102671. doi: 10.1016/j.bspc.2021.102671
[20]	C. Feng, C. Li, D. Zhao, C. Davatzikos, H. Litt, Segmentation of the left ventricle using distance regularized two-layer level set approach, in International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Berlin, Heidelberg, (2013), 477–484. doi: 10.1007/978-3-642-40811-3_60.
[21]	J. Lu, C. Feng, W. Li, D. Zhao, ROI localization and initialization method for left ventricle segmentation, in Proceedings of the Third International Symposium on Image Computing and Digital Medicine, (2019), 12–16.
[22]	J. Lu, C. Feng, D. Zhao, Segmentation of the cardiac left ventricle from cine magnetic resonance images using local inhomogeneous intensity clustering with prior shape constraint, J. Med. Imaging Health Inf., 9 (2019), 70–77. doi: 10.1166/jmihi.2019.2542. doi: 10.1166/jmihi.2019.2542
[23]	I. B. Ayed, S. Li, I. Ross, Embedding overlap priors in variational left ventricle tracking, IEEE Trans. Med. Imaging, 28 (2009), 1902–1913. doi: 10.1109/TMI.2009.2022087. doi: 10.1109/TMI.2009.2022087
[24]	I. B. Ayed, H. Chen, K. Punithakumar, I. Ross, S. Li, Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measure, Med. Image Anal., 16 (2012), 87–100. doi: 10.1016/j.media.2011.05.009. doi: 10.1016/j.media.2011.05.009
[25]	N. Paragios, A level set approach for shape-driven segmentation and tracking of the left ventricle, IEEE Trans. Med. Imaging, 22 (2003), 773–776. doi: 10.1109/TMI.2003.814785. doi: 10.1109/TMI.2003.814785
[26]	M. Lynch, O. Ghita, P. F. Whelan, Segmentation of the left ventricle of the heart in 3-D+t MRI data using an optimized nonrigid temporal model, IEEE Trans. Med. Imaging, 27 (2008), 195–203. doi: 10.1109/TMI.2007.904681. doi: 10.1109/TMI.2007.904681
[27]	M. Lynch, O. Ghita, P. F. Whelan, Left-ventricle myocardium segmentation using a coupled level-set with a priori knowledge, Comput. Med. Imaging Graphics, 30 (2006), 255–262. doi: 10.1016/j.compmedimag.2006.03.009. doi: 10.1016/j.compmedimag.2006.03.009
[28]	C. Pluempitiwiriyawej, J. M. F. Moura, Y. L. Wu, C. Ho, STACS: new active contour scheme for cardiac MR image segmentation, IEEE Trans. Med. Imaging, 24 (2005), 593–603. doi: 10.1109/TMI.2005.843740. doi: 10.1109/TMI.2005.843740
[29]	T. Chen, J. Babb, P. Kellman, L. Axel, D. Kim, Semiautomated segmentation of myocardial contours for fast strain analysis in cine displacement-encoded MRI, IEEE Trans. Med. Imaging, 27 (2008), 1084–1094. doi: 10.1109/TMI.2008.918327. doi: 10.1109/TMI.2008.918327
[30]	J. Woo, P. J. Slomka, C. C. J. Kuo, B. W. Hong, Multiphase segmentation using an implicit dual shape prior: Application to detection of left ventricle in cardiac MRI, Comput. Vision Image Understanding, 117 (2013), 1084–1094. doi: 10.1016/j.cviu.2012.11.012. doi: 10.1016/j.cviu.2012.11.012
[31]	H. Lee, N. C. F. Codella, M. D. Cham, J. W. Weinsaft, Y. Wang, Automatic left ventricle segmentation using iterative thresholding and an active contour model with adaptation on short-axis cardiac MRI, IEEE Trans. Biomed. Eng., 57 (2010), 905–913. doi: 10.1109/TBME.2009.2014545. doi: 10.1109/TBME.2009.2014545
[32]	R. Beichel, H. Bischof, F. Leberl, M. Sonka, Robust active appearance models and their application to medical image analysis, IEEE Trans. Med. Imaging, 24 (2005), 1151–1169. doi: 10.1109/TMI.2005.853237. doi: 10.1109/TMI.2005.853237
[33]	J. Montagnat, H. Delingette, 4D deformable models with temporal constraints: application to 4D cardiac image segmentation, Med. Image Anal., 9 (2005), 87–100. doi: 10.1016/j.media.2004.06.025. doi: 10.1016/j.media.2004.06.025
[34]	H. C. van Assen, M. G. Danilouchkine, A. F. Frangi, S. Ordás, J. J. M. Westenberg, J. H. C. Reiber, et al., SPASM: A 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data, Med. Image Anal., 10 (2006), 286–303. doi: 10.1016/j.media.2005.12.001. doi: 10.1016/j.media.2005.12.001
[35]	A. F. Frangi, D. Rueckert, J. A. Schnabel, W. J. Niessen, Automatic construction of multiple-object three-dimensional statistical shape models: application to cardiac modeling, IEEE Trans. Med. Imaging, 21 (2002), 1151–1166. doi: 10.1109/TMI.2002.804426. doi: 10.1109/TMI.2002.804426
[36]	J. Lötjönen, S. Kivistö, J. Koikkalainen, D. Smutek, K. Lauerma, Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images, Med. Image Anal., 8 (2004), 371–386. doi: 10.1016/j.media.2004.06.013. doi: 10.1016/j.media.2004.06.013
[37]	M. P. Jolly, Automatic segmentation of the left ventricle in cardiac MR and CT images, Int. J. Comput. Vision, 70 (2006), 151–163. doi: 10.1007/s11263-006-7936-3. doi: 10.1007/s11263-006-7936-3
[38]	X. Artaechevarria, A. Munoz-Barrutia, C. Ortiz-de-Solorzano, Combination strategies in multi-atlas image segmentation: application to brain MR data, IEEE Trans. Med. Imaging, 28 (2009), 1266–1277. doi: 10.1109/TMI.2009.2014372. doi: 10.1109/TMI.2009.2014372
[39]	C. Petitjean, J. N. Dacher, A review of segmentation methods in short axis cardiac MR images, Med. Image Anal., 15 (2011), 169–184. doi: 10.1016/j.media.2010.12.004. doi: 10.1016/j.media.2010.12.004
[40]	P. Peng, K. Lekadir, A. Gooya, L. Shao, S. E. Petersen, A. F. Frangi, A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging, Magn. Reson. Mater. Phys., Biol. Med., 29 (2016), 155–195. doi: 10.1007/s10334-015-0521-4. doi: 10.1007/s10334-015-0521-4
[41]	M. Kass, A. Witkin, D. Terzopoulos, Snakes: Active contour models, Int. J. Comput. Vision, 1 (1988), 321–331. doi: 10.1007/BF00133570. doi: 10.1007/BF00133570
[42]	C. Xu, J. L. Prince, Snakes, shapes, and gradient vector flow, IEEE Trans. Image Process., 7 (1998), 359–369. doi: 10.1109/83.661186. doi: 10.1109/83.661186
[43]	H. Zhang, W. Zhang, W. Shen, N. Li, Y. Chen, S. Li, et al., Automatic segmentation of the cardiac MR images based on nested fully convolutional dense network with dilated convolution, Biomed. Signal Process. Control, 68 (2021), 102684. doi: 10.1016/j.bspc.2021.102684. doi: 10.1016/j.bspc.2021.102684
[44]	W. Wang, Y. Wang, Y. Wu, T. Lin, S. Li, B. Chen, Quantification of full left ventricular metrics via deep regression learning with contour-guidance, IEEE Access, 7 (2019), 47918–47928. doi: 10.1109/ACCESS.2019.2907564. doi: 10.1109/ACCESS.2019.2907564
[45]	W. Shen, W. Wu, H. Zhang, Z. Sun, J. Ma, S. Guo, et al., Automatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net, Inverse Probl. Imaging, 15 (2021). doi: 10.3934/ipi.2020057. doi: 10.3934/ipi.2020057
[46]	T. A. Ngo, Z. Lu, G. Carneiro, 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 (2017), 159–171. doi: 10.1016/j.media.2016.05.009. doi: 10.1016/j.media.2016.05.009
[47]	M. R. Avendi, A. Kheradvar, H. Jafarkhani, A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI, Med. Image Anal., 30 (2016), 108–119. doi: 10.1016/j.media.2016.01.005. doi: 10.1016/j.media.2016.01.005
[48]	Y. Wang, Y. Jia, External force for active contours: gradient vector convolution, in PRICAI 2008: Trends in Artificial Intelligence, Berlin, Heidelberg, (2008), 466–472. doi: 10.1007/978-3-540-89197-0_43.
[49]	W. Xue, G. Brahm, S. Pandey, S. Leung, S. Li, Full left ventricle quantification via deep multitask relationships learning, Med. Image Anal., 43 (2018), 54–65. doi: 10.1016/j.media.2017.09.005. doi: 10.1016/j.media.2017.09.005

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)