Image-based clustering and connected component labeling for rapid automated left and right ventricular endocardial volume extraction and segmentation in full cardiac cycle multi-frame MRI images of cardiac patients

AbstractA rapid method for left and right ventricular endocardial volume segmentation and clinical cardiac parameter calculation from MRI images of cardiac patients is presented. The clinical motivation is providing cardiologists a tool for assessing the cardiac function in a patient through the left ventricular endocardial volume’s ejection fraction. A new method combining adapted fuzzy membership-based c-means pixel clustering and connected regions component labeling is used for automatic segmentation of the left and right ventricular endocardial volumes. This proposed pixel clustering with labeling approach avoids manual initialization or user intervention and does not require specifying the region of interest. This method fully automatically extracts the left and right ventricular endocardial volumes and avoids manual tracing on all MRI image frames in the complete cardiac cycle from systole to diastole. The average computational processing time per frame is 0.6 s, making it much more efficient than deformable methods, which need several iterations for the evolution of the snake or contour. Accuracy of the automated method presented herein was validated against manual tracing-based extraction, performed with the guidance of cardiac experts, on several MRI frames. Dice coefficients between the proposed automatic versus manual traced ventricular endocardial volume segmentations were observed to be 0.9781 ± 0.0070 (for left ventricular endocardial volume) and 0.9819 ± 0.0058 (for right ventricular endocardial volume), and the Pearson correlation coefficients were observed to be 0.9655 ± 0.0206 (for left ventricular endocardial volume) and 0.9870 ± 0.0131 (for right ventricular endocardial volume). Graphical abstractThe left ventricular endocardial volume segmentation methodology illustrated as a series of algorithms.

[1]  Jürgen Weese,et al.  Automated segmentation of the left ventricle in cardiac MRI , 2004, Medical Image Anal..

[2]  Ioannis Seimenis,et al.  Relationship of number of phases per cardiac cycle and accuracy of measurement of left ventricular volumes, ejection fraction, and mass. , 2004, Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance.

[3]  H E Melton,et al.  Estimation of Left Ventricular Cavity Area With an On‐line, Semiautomated Echocardiographic Edge Detection System , 1992, Circulation.

[4]  Marcelo Lobosco,et al.  A Web-Based Tool for the Automatic Segmentation of Cardiac MRI , 2010 .

[5]  Gustav Konrad von Schulthess.  The Effects of Motion and Flow on Magnetic Resonance Imaging , 1989 .

[6]  Eduardo Jyh Herng Wu,et al.  Artificial neural network: border detection in echocardiography , 2008, Medical & Biological Engineering & Computing.

[7]  Yi Su,et al.  Automatic segmentation of left ventricle cavity from short-axis cardiac magnetic resonance images , 2017, Medical & Biological Engineering & Computing.

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

[9]  John S. Duncan,et al.  Measurement of end diastolic shape deformity using bending energy , 1988, Proceedings. Computers in Cardiology 1988.

[10]  Marco Das,et al.  Global left ventricular function in cardiac CT. Evaluation of an automated 3D region-growing segmentation algorithm , 2006, European Radiology.

[11]  J. Francis,et al.  Operator induced variability in left ventricular measurements with cardiovascular magnetic resonance is improved after training. , 2007, Journal of Cardiovascular Magnetic Resonance.

[12]  Olga Bondarenko,et al.  Effect of endocardial trabeculae on left ventricular measurements and measurement reproducibility at cardiovascular MR imaging. , 2005, Radiology.

[13]  David J. Skorton,et al.  Estimation of left ventricular cavity area with an on-line, semiautomated echocardiographic edge detection system. , 1991 .

[14]  Jasjit S. Suri,et al.  Computer Vision, Pattern Recognition and Image Processing in Left Ventricle Segmentation: The Last 50 Years , 2000, Pattern Analysis & Applications.

[15]  Jiebo Luo,et al.  Image segmentation via adaptive K-mean clustering and knowledge-based morphological operations with biomedical applications , 1998, IEEE Trans. Image Process..

[16]  N. Paragios.  A level set approach for shape-driven segmentation and tracking of the left ventricle , 2003, IEEE Transactions on Medical Imaging.

[17]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  A. Ardeshir Goshtasby,et al.  Segmentation of cardiac cine MR images for extraction of right and left ventricular chambers , 1995, IEEE Trans. Medical Imaging.

[19]  M. Carlsson,et al.  Time resolved three-dimensional automated segmentation of the left ventricle , 2005, Computers in Cardiology, 2005.

[20]  Liang Zhong,et al.  A curvature-based approach for left ventricular shape analysis from cardiac magnetic resonance imaging , 2009, Medical & Biological Engineering & Computing.

[21]  Paul F. Whelan,et al.  Automatic segmentation of the left ventricle cavity and myocardium in MRI data , 2006, Comput. Biol. Medicine.

[22]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..