Detección semiautomática de contornos en imágenes de ecocardiografía modo m.
No. 20 (2004-11-01)Author(s)
-
Camilo Lamus G-H.*Estudiante de Ingeniería Biomédica, Escuela de Ingeniería de Antioquia – Instituto de Ciencias de la Salud CES, bmcalam@eia.edu.co.
-
Elsa M. Nieto P.**Profesor Instructor, Ingeniería Mecánica, Universidad de los Andes, el-nieto@uniandes.edu.co.
-
Marcela Hernández Hoyos***Profesor Asistente, Ingeniería de Sistemás y Computación, Universidad de los Andes, marc-her-@uniandes.edu.co.
Abstract
This paper is focused on the extraction of myocardial borders (septum, endocardium and epicardium) on M-mode echocardiograms. The proposed method combines two algorithms, each developed specially to extract certain borders. The extraction of the epicardium is done by means of a basic maximum tracking algorithm [8]. For the extraction of the endocardium and the left wall of the interventricular septum, a 2 stages discontinuity detector [6] is used. In the first stage the local mean of the image is calculated, and for the second stage the local variance is used. The output of this detector represents the discontinuities in the Mmode echocardographic image. Additionally, the method allows for manually correction of errors in the detection. Experimental examples are presented to test the performance of the methodology.