Submitted by Fabio Sobreira Campos da Costa (fabio.sobreira@ufpe.br) on 2016-09-20T13:30:20Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) ArthurDiegoDiasRocha.pdf: 4681451 bytes, checksum: 976cd7abe56f828ff55cbd595fdc6c6f (MD5) / Made available in DSpace on 2016-09-20T13:30:21Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) ArthurDiegoDiasRocha.pdf: 4681451 bytes, checksum: 976cd7abe56f828ff55cbd595fdc6c6f (MD5) Previous issue date: 2016-02-22 / FACEPE / O c^ancer de mama e o mais comum entre as mulheres no mundo e no Brasil, depois do de pele n~ao melanoma. De acordo com o Instituto Nacional de C^ancer, em 2013 foram registradas 14.388 mortes devido a esta mol estia. O c^ancer de mama e uma preocupa c~ao n~ao somente nacional, mas mundial. O m etodo utilizado para a sua detec c~ao e a mamogra a, que e uma t ecnica de imagem que utiliza a emiss~ao Raios-X incidentes na mama e capta a parte da radia c~ao n~ao absorvida pelos tecidos mam arios. A mamogra a e um exame de dif cil an alise pelo motivo de, em muitos casos, a densidade tecidual do tumor ser bastante parecida com a densidade de alguns tecidos saud aveis da mama. Uma abordagem interessante e a utiliza c~ao de t ecnicas computadorizadas de aux lio ao diagn ostico, ou seja, ferramentas baseadas em processamento de imagens e intelig^encia computacional projetadas para o apoio ao pro ssional radiologista. Estudos pr evios demonstram que considerar a domin^ancia tecidual mam aria nas ferramentas computacionais de apoio ao diagn ostico melhora consideravelmente as taxas de acerto. Para este trabalho, e proposta a constru c~ao de um sistema de classi ca c~ao de tumores de mama baseado descritores de Zernike como um descritor de forma das les~oes de mama, associado as m aquinas de vetor de suporte como classi cador. S~ao comparadas diferentes t ecnicas de sele c~ao de atributos com o objetivo de reduzir o custo computacional do sistema, mas sempre levando em conta a necessidade de se manter altas taxas de acerto, j a que isto pode re etir em erros de diagn ostico de c^ancer de mama. Atrav es dos dados analisados, e notado que a t ecnica linear de an alise de componentes principais (aliada a transformada de wavelets morfol ogica como etapa de pr e-processamento) se mostrou uma otima t ecnica para realiza c~ao de redu c~ao de atributos com um menor impacto nas taxas de acerto do sistema de apoio ao diagn ostico do c^ancer de mama, onde s~ao obtidas taxas de m edias de redu c~ao de acerto em torno de 2% (uma queda m edia de aproximadamente 95% para 93%), onde a redu c~ao do tamanho do vetor de atributos e de cerca de 64% (dentre os diferentes tipos de tecido, s~ao selecionados de 70 a 89 atributos do total de 224). / Breast cancer is one of the most common type of cancer among women. According to Brazil's national institute of cancer, in 2013 it was registered 14,388 deaths due to this disease. Breast cancer is not only a national but worldwide concern. The most used method to its detection is mammography which is an image technique that uses X ray emission and measures the non-absorbed radiation by the breast internal tissues. Mammography is a hard to analyze image exam, mainly because in many cases tumor's density is much alike some of the healthy tissues' density. An interesting approach is the use of computeraided techniques for diagnosis, meaning the use of image processing and computational intelligence tools designed to support and aid radiologists in their tasks. Previous studies show that considering the di erent types of breast tissue dominance improves considerably the rate of correct classi cation by these computational tools. It is proposed for this work the development of a breast tumor classi cation system based on Zernike descriptors as shape descriptors of these breast lesions along with support vector machines as machine learning algorithms for classi cation. Some feature selection techniques are compared for reducing the whole system computational cost but always taking into consideration that the classi cation rates must be kept as high as possible. Of the techniques studied in this work, principal components analysis along with morphological wavelet transform for image preprocessing has shown itself as a great technique for feature reduction with lesser impact on classi cation rates. It was achieved a mean 2% loss in those rates (from about 95% to 93% as mean values) with a mean feature reduction of about 64% (in the range of 70 to 89 features from 224).