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
- 130 Downloads
A 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).
KeywordsLeft ventricular endocardial volume Cardiac MRI Image segmentation Medical imaging Image processing
The author would like to acknowledge and thank the source of the image data used in this study: The cardiac patient datasets were provided and taken from the University of Auckland Bioengineering Institute and the Auckland MRI Research Group database on the AMRG Cardiac MRI Atlas Project.
As the Auckland MRI Research Group database on the Cardiac Atlas Project is a multi-institutional international collaboration, all image data in it complies with the legislative and local Institutional Review Board (IRB) requirements, and has the approvals of the local IRB and local ethics committees at the University of Auckland in New Zealand and also has the approvals of the local IRB and local ethics committees at the University of California at Los Angeles (USA).
All the image data is also de-identified, with all names and identifiers anonymized, using the LONI Debabeler (http://loni.usc.edu/Software/Debabeler), a HIPAA compliant software package.
The author would like to acknowledge and thank the cardiologists from Amity Institute of Public Health, Amity University, Noida, U.P., India, who trained and guided the author on how to delineate the ventricular endocardial volumes in cardiac MRI images using MATLAB®.
- 1.Duncan JS, Smeulders A, Lee F, Zaret BL (1988) Measurement of end diastolic shape deformity using bending energy. Comput Cardiol:277–280Google Scholar
- 15.de Paula TH, Lobosco M, dos Santos RW (2010) A web-based tool for the automatic segmentation of cardiac MRI, In XII Mediterranean Conference on Medical and Biological Engineering and Computing 2010, pp. 667–670, springer Berlin HeidelbergGoogle Scholar
- 17.Yang X, Song Q, Su Y (2017) Automatic segmentation of left ventricular volume cavity from short-axis cardiac magnetic resonance images, Medical & Biological Engineering & Computing, pp. 1–15Google Scholar
- 21.Heiberg E, Wigstrom L, Carlsson M, Bolger AF, Karlsson M (2005) Time resolved three-dimensional automated segmentation of the left ventricle, Comput Cardiol pp. 599-602, IEEEGoogle Scholar