UPM Institutional Repository

Segmentation of masses from breast ultrasound images using parametric active contour algorithm


Citation

Jumaat, Abdul Kadir and Wan Abdul Rahman, Wan Eny Zarina and Ibrahim, Arsmah and Mahmud, Rozi (2010) Segmentation of masses from breast ultrasound images using parametric active contour algorithm. Procedia - Social and Behavioral Sciences, 8. pp. 640-647. ISSN 1877-0428

Abstract

The active contour (Snake) is a computer generated curve that can trace boundaries of images. As a method which applies the computer technology in mathematics, Snake is computationally formulated based on controlled continuous splines and adopts the mathematical concept of energy minimization. This paper presents the application of Snake for the segmentation of masses on breast ultrasound images. The images used are taken from Malaysian population. The boundaries of the masses identified may be used in classification of cancers or non-cancerous masses. Specifically the Balloon Snake is applied in segmenting the masses in the breast ultrasound images. Comparison on the masses areas segmented by the Balloon Snake is done against the areas traced by an expert (radiologist). It is found that from forty-five masses tested, the average percentage area difference of Balloon Snake is 4.47%. This implies that the accuracy of segmentation results for the Balloon Snake is 95.53%.


Download File

[img] PDF
48029.pdf
Restricted to Repository staff only

Download (332kB)

Additional Metadata

Item Type: Article
Divisions: Faculty of Medicine and Health Science
DOI Number: https://doi.org/10.1016/j.sbspro.2010.12.089
Publisher: Elsevier
Keywords: Active contour algorithm; Balloon Snake; Segmentation; Breast ultrasound image
Depositing User: Nabilah Mustapa
Date Deposited: 04 Aug 2016 08:33
Last Modified: 04 Aug 2016 08:33
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1016/j.sbspro.2010.12.089
URI: http://psasir.upm.edu.my/id/eprint/48029
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item