Advanced search
Start date
Betweenand


Transfer function based methodology to preprocessing digital mammographic image and its application on computer-aided diagnosis schemes

Full text
Author(s):
Marcelo Andrade da Costa Vieira
Total Authors: 1
Document type: Doctoral Thesis
Press: São Carlos.
Institution: Universidade de São Paulo (USP). Escola de Engenharia de São Carlos (EESC/SBD)
Defense date:
Examining board members:
Homero Schiabel; Paulo Roberto Costa; Regina Bitelli Medeiros; Maria Cristina Ferreira de Oliveira; Ana Maria Marques da Silva
Advisor: Homero Schiabel
Abstract

The purpose of this work is to evaluate the quality of radiological equipment and their images in order to use these evaluations to improve the performance of a computer-aided diagnosis (CAD) scheme. The mean idea is about the development of image processing techniques to enhance digital mammograms according to the characteristics of the X-ray unit used for image acquisition. This work is basically divided in two parts. In the first one, it were determined the characteristics related to spatial and contrast resolution of several mammographic equipment, evaluated respectively from the optical transfer function and noise Wiener spectrum. This evaluation allowed, in a second part, the development of a preprocessing technique to enhance different set of digital mammographic images, gathered according to the equipment used on its acquisition process. Thus, each mammographic image had its quality improved in conformity with the characteristics of the equipment used on its acquisition, determined in the first part of this work. These images, after the enhancement process, were used on a previously developed CAD scheme. It was observed an improvement of 12% on the CAD performance using pre-processed mammograms compared to the results obtained when using non-enhanced mammographic images. (AU)