T?cnicas neuronais de agrupamentos aplicadas ? detec??o de anomalias em mamogramas digitais

Made available in DSpace on 2014-12-17T14:55:25Z (GMT). No. of bitstreams: 1 HelianaBS_capa_ate_pag_15.pdf: 3788915 bytes, checksum: ebef897133149a151dde43b8e4730340 (MD5) Previous issue date: 2001-03-10 === Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico === This work proposes the...

Full description

Bibliographic Details
Main Author: Soares, Heliana Bezerra
Other Authors: CPF:10749896434
Format: Others
Language:Portuguese
Published: Universidade Federal do Rio Grande do Norte 2014
Subjects:
Online Access:http://repositorio.ufrn.br:8080/jspui/handle/123456789/15265
Description
Summary:Made available in DSpace on 2014-12-17T14:55:25Z (GMT). No. of bitstreams: 1 HelianaBS_capa_ate_pag_15.pdf: 3788915 bytes, checksum: ebef897133149a151dde43b8e4730340 (MD5) Previous issue date: 2001-03-10 === Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico === This work proposes the development of an intelligent system for analysis of digital mammograms, capable to detect and to classify masses and microcalcifications. The digital mammograms will be pre-processed through techniques of digital processing of images with the purpose of adapting the image to the detection system and automatic classification of the existent calcifications in the suckles. The model adopted for the detection and classification of the mammograms uses the neural network of Kohonen by the algorithm Self Organization Map - SOM. The algorithm of Vector quantization, Kmeans it is also used with the same purpose of the SOM. An analysis of the performance of the two algorithms in the automatic classification of digital mammograms is developed. The developed system will aid the radiologist in the diagnosis and accompaniment of the development of abnormalities === Este trabalho prop?e o desenvolvimento de um sistema inteligente para an?lise de mamogramas digitais, capaz de detectar e classificar massas e microcalcifica??es. O mamograma digital ser? pr?-processado atrav?s de t?cnicas de processamento digital de imagens com finalidade de adequar a imagem ao sistema de detec??o e classifica??o autom?tica das calcifica??es existentes na mama. O modelo adotado para a detec??o de anomalias e classifica??o dos mamogramas utiliza a rede neural de Kohonen treinada pelo algoritmo Self Organization Map - SOM. O algoritmo de quantiza??o vetorial, Kmeans ? tamb?m utilizado com a mesma finalidade do SOM. Uma an?lise de desempenho dos dois algoritmos para atuarem na classifica??o autom?tica de mamogramas digitais ? desenvolvida. O sistema desenvolvido auxiliar? ao mastologista no diagn?stico e acompanhamento do desenvolvimento de anormalidades