Scheduled System Maintenance:
On May 6th, single article purchases and IEEE account management will be unavailable from 8:00 AM - 12:00 PM ET (12:00 - 16:00 UTC). We apologize for the inconvenience.
By Topic

Left ventricular segmentation of cardiac magnetic resonance images using a novel edge following technique

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Somkantha, K. ; Dept. of Electr. Eng., Chiang Mai Univ., Chiang Mai ; Theera-Umpon, N. ; Auephanwiriyakul, S.

This paper presents a novel edge following technique for image segmentation designed to segment the left ventricle in cardiac magnetic resonance (MR) images. This is a required step to determine the volume of left ventricle in a cardiac MR image, which is an essential tool for cardiac diagnosis. The traditional method for extracting them from cardiac MR images is by human delineation. This method is accuracy but time consuming. So a new ventricular segmentation technique is proposed in order to reduce the analysis time with similar accuracy level compared to doctorspsila opinions. Our proposed technique can detect ventricle edges in MR images using the information from the vector image model and the edge map. We also compare the proposed segmentation technique with the active contour model (ACM) and the gradient vector flow (GVF) by using the opinions of two skilled doctors as the ground truth. The experimental results show that our technique is able to provide more accurate segmentation results than the classical contour models and visually close to the manual segmentation by the experts. The results evaluated using a numerical measure by mean of the probability of error in image segmentation also confirm the visual evaluation.

Published in:

Cybernetics and Intelligent Systems, 2008 IEEE Conference on

Date of Conference:

21-24 Sept. 2008