Density Estimation for Medical Image Segmentation

• Grant number: 08/10994-5
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: March 01, 2009
• End date: December 31, 2010
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Applied Probability and Statistics
• Principal Investigator: Luzia Aparecida Trinca
• Grantee: Giovana Marassi Zambon
• Host Institution: Instituto de Biociências (IBB). Universidade Estadual Paulista (UNESP). Campus de Botucatu. Botucatu , SP, Brazil

Abstract

The aim of this project is to consider the problem of density estimation applied to the segmentation of medical images. Medical images are used to help the diagnostic of tumor diseases as well as to plan and deliver treatment. A computer image is an array of values representing colors in some scale. The smallest element of the image to which it is possible to assign a value is called pixel. Segmentation is the process of dividing the image in portions through the classification of each pixel. The simplest way of classification is by thresholding, given the number of portions and the threshold values. Another method is contructing a histogram of the pixel values and assign a portion to each pike. The threshold is the mean between two pikes. As the histogram does not form a smooth curve it is difficult to discern between true pikes and random variation. Density estimation methods allow the estimation of a smooth curve. Image data can be considered as mixture of different densities. In this project parametric and nonparametric methods for density estimation will be addressed.