{"title":"Automatic LV Segmentation with K-means Clustering and Graph Searching on Cardiac MRI","authors":"Hae-Yeoun Lee","volume":99,"journal":"International Journal of Computer and Information Engineering","pagesStart":292,"pagesEnd":296,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10000872","abstract":"
Quantification of cardiac function is performed by
\r\ncalculating blood volume and ejection fraction in routine clinical
\r\npractice. However, these works have been performed by manual
\r\ncontouring, which requires computational costs and varies on the
\r\nobserver. In this paper, an automatic left ventricle segmentation
\r\nalgorithm on cardiac magnetic resonance images (MRI) is presented.
\r\nUsing knowledge on cardiac MRI, a K-mean clustering technique is
\r\napplied to segment blood region on a coil-sensitivity corrected image.
\r\nThen, a graph searching technique is used to correct segmentation
\r\nerrors from coil distortion and noises. Finally, blood volume and
\r\nejection fraction are calculated. Using cardiac MRI from 15 subjects,
\r\nthe presented algorithm is tested and compared with manual
\r\ncontouring by experts to show outstanding performance.<\/p>\r\n","references":"[1] H.-Y. Lee, N. Codella, M. Cham. J. Weinsaft, and Y. Wang, \"Automatic\r\nLeft Ventricle Segmentation using Iterative Thresholding and Active Contour Model with Adaptation on Short-Axis Cardiac MRI,\" IEEE\r\nTrans. on Biomedical Engineering, vol. 75(4), pp. 905-913, 2010.\r\n[2] J.S. Suri, \"Computer vision pattern recognition and image processing in\r\nleft ventricle segmentation: the last 50 years,\" Pattern Analysis and\r\nApplications, vol. 3, pp. 209-242, 2000.\r\n[3] A. Pednekar, U. Kurkure, R. Muthupillari, S. Flamm, and I.A. Kakadiaris,\r\n\"Automated Left Ventricle Segmentation in Cardiac MRI,\" IEEE Trans.\r\non Biomedical Engineering, vol. 53 (7), pp. 1425-1428, 2006.\r\n[4] M.-P. Jolly, \"Automatic Segmentation of the Left Ventricle in Cardiac\r\nMR and CT Images,\" International Journal of Computer Vision, vol. 70\r\n(2), pp. 151-163, 2006.\r\n[5] N. Paragios, \"A level set approach for shape-driven segmentation and\r\ntracking of the left ventricle,\" IEEE Trans. on Medical Imaging, vol. 22\r\n(6), pp. 773-776, 2003.\r\n[6] N. Codella, J. Weinsaft, M. Cham, M Janik, M. Prince, and Y. Wang,\r\n\"Automatic Soft Segmentation of the Left Ventricle using Myocardial\r\nEffusing Threshold Reduction and Intravoxel Computation,\" Radiology,\r\nvol. 248 (3), pp. 1004-1012, 2008.\r\n[7] T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman,\r\nA. Y. Wu, \u201cAn efficient k-means clustering algorithm: Analysis and\r\nimplementation,\u201d IEEE Trans. Pattern Analysis and Machine\r\nIntelligence, vol. 24, pp. 881\u2013892, 2002.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 99, 2015"}