An SPCNN-GVF-based approach for the automatic segmentation of left ventricle in cardiac cine MR images

PurposeAccurate segmentation of left ventricle (LV) is essential for the cardiac function analysis. However, it is labor intensive and time consuming for radiologists to delineate LV boundary manually. In this paper, we present a novel self-correcting framework for the fully automatic LV segmentation.MethodsFirstly, a time-domain method is designed to extract a rectangular region of interest around the heart. Then, the simplified pulse-coupled neural network (SPCNN) is employed to locate the LV cavity. Different from the existing approaches, SPCNN can realize the self-correcting segmentation due to its parameter controllability. Subsequently, the post-processing based on the maximum gradient searching is proposed to obtain the accurate endocardium. Finally, a new external force based on the shape similarity is defined and integrated into the gradient vector flow (GVF) snake with the balloon force to segment the epicardium.ResultsWe obtain encouraging segmentation results tested on the database provided by MICCAI 2009. The average percentage of good contours is 92.26 %, the average perpendicular distance is 2.38 mm, and the overlapping dice metric is 0.89. Besides, the experiment results show good correlations between the automatic segmentation and the manual delineation (for the LV ejection fraction and the LV myocardial mass, the correlation coefficients R are 0.9683 and 0.9278, respectively).ConclusionWe propose an effective and fast method combing the SPCNN and the improved GVF for the automatic segmentation of LV.

[1]  Yunde Jia,et al.  Segmentation of the Left Venctricle from MR Images via Snake Models Incorporating Shape Similarities , 2006, 2006 International Conference on Image Processing.

[2]  D CohenLaurent.  On active contour models and balloons , 1991 .

[3]  Alistair A. Young,et al.  The Cardiac Atlas Project—an imaging database for computational modeling and statistical atlases of the heart , 2011, Bioinform..

[4]  Junaed Sattar.  Snakes , Shapes and Gradient Vector Flow , 2022 .

[5]  Ioannis A. Kakadiaris,et al.  Localization and Segmentation of Left Ventricle in Cardiac Cine-MR Images , 2009, IEEE Transactions on Biomedical Engineering.

[6]  Laurent D. Cohen,et al.  On active contour models and balloons , 1991, CVGIP Image Underst..

[7]  Anqi Qiu,et al.  Robust Automatic Rodent Brain Extraction Using 3-D Pulse-Coupled Neural Networks (PCNN) , 2011, IEEE Transactions on Image Processing.

[8]  Li Liu,et al.  Pulse-coupled neural networks and one-class support vector machines for geometry invariant texture retrieval , 2010, Image Vis. Comput..

[9]  Manfred Opper,et al.  Region growing with pulse-coupled neural networks: an alternative to seeded region growing , 2002, IEEE Trans. Neural Networks.

[10]  Sarada Dakua,et al.  Annularcut: A graph-cut design for left ventricle segmentation from magnetic resonance images , 2014, IET Image Process..

[11]  Michel Couprie,et al.  Segmentation of 4D cardiac MRI: Automated method based on spatio-temporal watershed cuts , 2010, Image Vis. Comput..

[12]  Reza Aghaeizadeh Zoroofi,et al.  4D statistical shape modeling of the left ventricle in cardiac MR images , 2013, International Journal of Computer Assisted Radiology and Surgery.

[13]  Chao Gao,et al.  An Iterative Thresholding Segmentation Model Using a Modified Pulse Coupled Neural Network , 2013, Neural Processing Letters.

[14]  Patrick Clarysse,et al.  A dynamic elastic model for segmentation and tracking of the heart in MR image sequences , 2010, Medical Image Anal..

[15]  Alejandro F Frangi,et al.  Automatic cardiac LV segmentation in MRI using modified graph cuts with smoothness and interslice constraints , 2014, Magnetic resonance in medicine.

[16]  Pingkun Yan,et al.  Feature competition and partial sparse shape modeling for cardiac image sequences segmentation , 2015, Neurocomputing.

[17]  Caroline Petitjean,et al.  A review of segmentation methods in short axis cardiac MR images , 2011, Medical Image Anal..

[18]  Simon K. Warfield,et al.  Left Ventricular Segmentation Challenge from Cardiac MRI: A Collation Study , 2011, STACOM.

[19]  Yide Ma,et al.  A New Automatic Parameter Setting Method of a Simplified PCNN for Image Segmentation , 2011, IEEE Transactions on Neural Networks.

[20]  Xiangyang Xu,et al.  Automatic left ventricle segmentation in cardiac MRI using topological stable-state thresholding and region restricted dynamic programming. , 2012, Academic radiology.

[21]  Yunde Jia,et al.  Segmentation of the left ventricle in cardiac cine MRI using a shape-constrained snake model , 2013, Comput. Vis. Image Underst..

[22]  Denis Friboulet,et al.  Fast automatic myocardial segmentation in 4D cine CMR datasets , 2014, Medical Image Anal..

[23]  J. Alison Noble,et al.  Data-driven shape parameterization for segmentation of the right ventricle from 3D+t echocardiography , 2015, Medical Image Anal..

[24]  Yu-Len Huang,et al.  Left ventricular myocardium segmentation on delayed phase of multi-detector row computed tomography , 2012, International Journal of Computer Assisted Radiology and Surgery.

[25]  Huaifei Hu,et al.  Hybrid segmentation of left ventricle in cardiac MRI using Gaussian-mixture model and region restricted dynamic programming. , 2013, Magnetic resonance imaging.

[26]  Mireille Garreau,et al.  Improved Estimation of Cardiac Function Parameters Using a Combination of Independent Automated Segmentation Results in Cardiovascular Magnetic Resonance Imaging , 2015, PloS one.

[27]  Frédérique Frouin,et al.  Fully automated segmentation of the left ventricle applied to cine MR images: Description and results on a database of 45 Subjects , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  Alistair A. Young,et al.  Big Heart Data: Advancing Health Informatics Through Data Sharing in Cardiovascular Imaging , 2015, IEEE Journal of Biomedical and Health Informatics.

[29]  Wieslaw Lucjan Nowinski,et al.  An Image-Based Comprehensive Approach for Automatic Segmentation of Left Ventricle from Cardiac Short Axis Cine MR Images , 2011, Journal of Digital Imaging.

[30]  Caroline Petitjean,et al.  Automatic cardiac ventricle segmentation in MR images: a validation study , 2011, International Journal of Computer Assisted Radiology and Surgery.

[31]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[32]  Alexander Dick,et al.  Segmentation of Left Ventricle in Cardiac Cine MRI: An Automatic Image-Driven Method , 2009, FIMH.

[33]  Frédérique Frouin,et al.  Nonsupervised Ranking of Different Segmentation Approaches: Application to the Estimation of the Left Ventricular Ejection Fraction From Cardiac Cine MRI Sequences , 2012, IEEE Transactions on Medical Imaging.

[34]  Einar Heiberg,et al.  Validation and Development of a New Automatic Algorithm for Time-Resolved Segmentation of the Left Ventricle in Magnetic Resonance Imaging , 2015, BioMed research international.

[35]  William M. Wells,et al.  Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation , 2004, IEEE Transactions on Medical Imaging.

[36]  Alain Lalande,et al.  Journal of Cardiovascular Magnetic Resonance Left Ventricular Ejection Fraction Calculation from Automatically Selected and Processed Diastolic and Systolic Frames in Short-axis Cine-mri , 2022 .

[37]  Sarada Dakua,et al.  LV Segmentation Using Stochastic Resonance and Evolutionary Cellular Automata , 2015, Int. J. Pattern Recognit. Artif. Intell..

[38]  Deng Xiang-y.  Automatic Image Segmentation Based on PCNN , 2014 .