FRANÇAIS
A showcase of ÉTS researchers’ publications and other contributions
SEARCH

A neural network learned information measures for heart motion abnormality detection

Downloads

Downloads per month over past year

Nambakhsh, M. S., Punithakumar, Kumaradevan, Ben Ayed, Ismail, Goela, Aashish, Islam, Ali, Peters, Terry et Li, Shuo. 2011. « A neural network learned information measures for heart motion abnormality detection ». In Progress in Biomedical Optics and Imaging (Lake Buena Vista, FL, USA, Feb. 14-16, 2011) Coll. « Proceedings of SPIE », vol. 7962. SPIE.

[img]
Preview
PDF
Ben Ayed I. 2011 10518 A neural network learned information measures for heart motion abnormality detection.pdf

Download (766kB) | Preview

Abstract

In this study, we propose an information theoretic neural network for normal/abnormal left ventricular motion classification which outperforms significantly other recent methods in the literature. The proposed framework consists of a supervised 3-layer artificial neural network (ANN) which uses hyperbolic tangent sigmoid and linear transfer functions for hidden and output layers, respectively. The ANN is fed by information theoretic measures of left ventricular wall motion such as Shannon’s differential entropy (SDE), Rényi entropy and Fisher information, which measure global information of subjects distribution. Using 395×20 segmented LV cavities of short-axis magnetic resonance images (MRI) acquired from 48 subjects, the experimental results show that the proposed method outperforms Support Vector Machine (SVM) and thresholding based information theoretic classifiers. It yields a specificity equal to 90%, a sensitivity of 91%, and a remarkable Area Under Curve (AUC) for Receiver Operating Characteristic (ROC), equal to 93.2%.

Item Type: Conference proceeding
ISBN: 16057422
Professor:
Professor
Ben Ayed, Ismail
Affiliation: Autres
Date Deposited: 11 Sep 2015 15:25
Last Modified: 01 Dec 2015 14:29
URI: https://espace2.etsmtl.ca/id/eprint/10518

Actions (login required)

View Item View Item