ROBUST DEFORMABLE MODEL FOR SEGMENTING THE LEFT VENTRICLE IN 3D VOLUMES OF ULTRASOUND DATA

Carlos Santiago, Jorge S. Marques, Jacinto Nascimento

2012

Abstract

The segmentation of the left ventricle (LV) in echocardiographic data has proven itself a useful methodology to assess cardiac function and to detect abnormalities. Traditionally, cardiologists segment the LV border at the end-systolic and end-diastolic phases to determine the ejection fraction. However, the manual segmentation of the LV is a tedious and time demanding task, which means automated segmentation systems can provide a powerful tool to improve workflow in a clinical setup. This paper proposes a robust 3D segmentation system consisting of a deformable model that uses a probabilistic data association filter (PDAF) to robustly detect the LV border. Results show that the algorithm performs well in both synthetic and real data, without significantly compromising its performance. The obtained LV segmentations are compared with the manual segmentations performed by an expert, yielding an average distance of 4 pixel between points from both segmentations.

Paper Citation

in Harvard Style

Santiago C., S. Marques J. and Nascimento J. (2012). ROBUST DEFORMABLE MODEL FOR SEGMENTING THE LEFT VENTRICLE IN 3D VOLUMES OF ULTRASOUND DATA . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: SADM, (ICPRAM 2012) ISBN 978-989-8425-98-0, pages 333-340. DOI: 10.5220/0003858403330340

in Bibtex Style

@conference{sadm12,
author={Carlos Santiago and Jorge S. Marques and Jacinto Nascimento},
title={ROBUST DEFORMABLE MODEL FOR SEGMENTING THE LEFT VENTRICLE IN 3D VOLUMES OF ULTRASOUND DATA},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: SADM, (ICPRAM 2012)},
year={2012},
pages={333-340},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003858403330340},
isbn={978-989-8425-98-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: SADM, (ICPRAM 2012)
TI - ROBUST DEFORMABLE MODEL FOR SEGMENTING THE LEFT VENTRICLE IN 3D VOLUMES OF ULTRASOUND DATA
SN - 978-989-8425-98-0
AU - Santiago C.
AU - S. Marques J.
AU - Nascimento J.
PY - 2012
SP - 333
EP - 340
DO - 10.5220/0003858403330340