By Topic

Processing algorithms for the analysis of videocolonoscopy images

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Sandra N. Lima C. ; Unidad de Investigación en Inteligencia Artificial, Decanato de Ciencias y Tecnología, Universidad Centroccidental “Lisandro Alvarado”, Barquisimeto, Venezuela ; Maritza Bracho de Rodríguez

The cancer is the second cause of death in Venezuela. In Lara State, the malign tumors of the digest organs, including the colorectal area, represent the 4.13% of the registered death. The specialists ensure that early detection of this disease increases the probability of healing. This paper presents a collection of algorithms developed for the automatic analysis of endoscopic color images of tissues of the colon. The analysis begins with the preprocessing of the image, then segmentation and features extraction are applied and finally an artificial neural network is used for the classification. In the experiments an architecture of 60×6×1 resulted the most appropriate with accuracy of 97% and 72% in the training and test sets respectively. These results are very important because the classifier is not provided with another previous data of the patient, such as gender, age and medical history.

Published in:

Informatica (CLEI), 2012 XXXVIII Conferencia Latinoamericana En

Date of Conference:

1-5 Oct. 2012