Detalhes bibliográficos
Ano de defesa: |
2011 |
Autor(a) principal: |
Sousa, Ulysses Santos
 |
Orientador(a): |
PAIVA, Anselmo Cardoso de
 |
Banca de defesa: |
Abdelouahab, Zair
 |
Tipo de documento: |
Dissertação
|
Tipo de acesso: |
Acesso aberto |
Idioma: |
por |
Instituição de defesa: |
Universidade Federal do Maranhão
|
Programa de Pós-Graduação: |
PROGRAMA DE PÓS-GRADUAÇÃO EM ENGENHARIA DE ELETRICIDADE/CCET
|
Departamento: |
Engenharia
|
País: |
BR
|
Palavras-chave em Português: |
|
Palavras-chave em Inglês: |
|
Área do conhecimento CNPq: |
|
Link de acesso: |
http://tedebc.ufma.br:8080/jspui/handle/tede/467
|
Resumo: |
Cancer is one of the biggest health problems worldwide, and the breast cancer is the one that causes more deaths among women. Also it is the second most frequent type in the world. The chances of survival for a patient with breast cancer increases the sooner this disease is discovered. Several Computer Aided Detection/Diagnosis Systems has been used to assist health professionals. This work presents a methodology to discriminate and classify mammographic tissues regions in mass and non-mass. For this purpose the Shannon-Wiener‟s Diversity Index, which is applied to measure the biodiversity in ecosystem, is used to describe pattern of breast image region with four approaches: global, in circles, in rings and directional. After, a Support Vector Machine is used to classify the regions in mass and non-mass. The methodology presents promising results for classification of mammographic tissues regions in mass and non-mass, achieving 99.85% maximum accuracy. |