Abstract
Here we analyze the difficulties of segmentation without tag line of left ventricle MR images, and propose an algorithm for automatic segmentation of MRI volume data (VD) target profiles. Herein, we propose Geometric active contour model based on K-means clustering (KmGAC) method. Initially, using Hough operator to automatically locate initial contour of VD, the algorithm uses clustering approach to complete data subsampling and initial center determination. Next, according to the clustering rules, the proposed algorithm finishes MRI VD segmentation. Finally, the algorithm uses a category optimization method to improve segmentation results. Experiments show that the algorithm provides good segmentation results.
Similar content being viewed by others
References
Al-Daoud M, Roberts S (1996) New methods for the initialisation of clusters [J]. Pattern Recogn Lett 17(5):451–455
American Heart Association (1998) Heart and stroke statistical update. Website: www.Americanheart.org
Baeker E, Jain A (1981) A clustering performance measure based on fuzzy set decomposition. IEEE Trans Pattern Anal Mach Intell 3(l):66–75
Canny J A computational approach for edge detection. IEEE Trans Pattern
Da-meng DAI, De-jun MU (2012) A fast approach to k-means clustering for time series based on symbolic representation. Int J Advance Comput Technol 4(5):233–239
Frangi AF, Niessen WJ, Viergever MA (2001) Three-dimensional modeling for functional analysis of cardiac images: a review. IEEE Trans Med Imaging 20(1):2–5
Goldberg N (1991) Colour image quantization for high resolution graphics display [J]. Image Vis Comput 9(5):303–312
Gonzalez RC, Woods RE (2008) Digital image processing. Prentice Hall
Linde Y, Buzo A, Gray R (1980) An algorithm for vector quantizer design [J]. IEEE Trans Commun 28(1):84–95
Martin D, Fowlkes C, Tal D et al. (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics [C] / /. Proc 2001 Int Conf Comput Vision. Washing-ton, DC: IEEE Computer Society 416–423
Mignotte M (2008) Segmentation by fusion of histogram-based K-means clusters in different color spaces [J]. IEEE Trans Image Process 17(5):780–787
Paragios N (2002) A variational approach for the segmentation of the left ventricle in MR cardiac image analysis. Int J Comput Vis 50(3):345–362
Philip KP (1991) Automatic detection of myocardial contours in cine computed topographic images. PhD Thesis, University of Iowa
Poh CL, Kitriey RI, Shrestha RBK (2005) Visualisation of cardiac wall motion using MR images. Comput Cardiol 17–19
Singh C, Bhatia N, Kaur A (2008) Hough transform based fast skew detection and accurate skew correction methods. Pattern Recognit 41:3528–3546
Turnbull D, Elkan C (2005) Fast recognition of musical genres using RBF networks [J]. IEEE Trans Knowl Data Eng 17(4):580–584
Zeng X, Staib L, Schukz R, Duncan J (1998) Volumetric layer segmentation using coupled surfaces propagation. Proc IEEE Conf Comput Vision Patt Recognit, Santa Barbara, USA 708–715
Zhang T-w, Li P-h (2000) Review on active contour model (Snake model) [J]. J Software 11(6):751–757
Acknowledgments
This paper is supported by Science and Technology Plan of Gansu Province (No.1308RJZA266) and Gansu Radio & TV university youth fund project (NO.QN201501).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ji, D., Li, X., Yang, Q. et al. Analysis and segmentation of MRI volume data based on KmGAC model. Multimed Tools Appl 76, 17075–17093 (2017). https://doi.org/10.1007/s11042-016-3679-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3679-5