A 2-D Active Appearance Model For Prostate Segmentation in Ultrasound Images

Author

Medina, R. ; Bravo, A. ; Windyga, P. ; Toro, J. ; Yan, P. ; Onik, G.

Author_Institution

Grupo de Ingenieria Biomedica, Los Andes Univ., Merida

fYear

2006

Firstpage

3363

Lastpage

3366

Abstract

In this research we use an active appearance model (AAM) as the core of a robust segmentation algorithm that combines contour and texture information to learn shape variability through a training procedure in trans-rectal ultrasound (TRUS) images of the prostate. Training was carried out using a dataset of 95 images which are preprocessed using gray-level mathematical morphology operators. Preliminary results are promising. The segmentation can provide shapes that have an overlap with respect to a ground truth shape, traced by an expert, of up to 96%, and an average distance from point to curve of up to 1.3 pixels

Keywords

biomedical ultrasonics; image segmentation; image texture; medical image processing; 2-D active appearance model; contour; gray-level mathematical morphology operators; prostate segmentation; shape variability; texture; trans-rectal ultrasound images; Active appearance model; Biomedical applications of radiation; Diseases; Image edge detection; Image segmentation; Minimally invasive surgery; Oncological surgery; Prostate cancer; Shape; Ultrasonic imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the

Conference_Location

Shanghai

Print_ISBN

0-7803-8741-4

Type

conf

DOI

10.1109/IEMBS.2005.1617198

Filename

1617198