Comparative Study on Various Random Walk Techniques for Left Ventricle Cavity Segmentation
Author(s) -
Ghada Abdel-Aziz,
Hamdy M. Kelash,
Osama S. Faragallah
Publication year - 2015
Publication title -
international journal of computer applications
Language(s) - English
Resource type - Journals
ISSN - 0975-8887
DOI - 10.5120/19339-0918
Subject(s) - computer science , segmentation , ventricle , random walk , artificial intelligence , statistics , medicine , cardiology , mathematics
Objective of image segmentation is to group regions with coherent characteristics. This paper presents a comparative study on Random walk techniques for Left ventricle segmentation. In this paper, LV cavity segmentation is demonstrated for each technique using multi-slice MR cardiac images. The quality of segmentation process is measured by comparing the resulted images of different Random walk techniques using DICE coefficient, PSNR and Hausdorff distance. The comparison includes measuring the execution time of each technique. General Terms Image segmentation, Random walk techniques, LV cavity segmentation
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom