Advisor(s)
Abstract(s)
O presente trabalho apresenta um método baseado em reconhecimento de padrões proteômicos para o diagnóstico precoce do câncer de próstata, utilizando técnicas computacionais, aplicadas na base de dados de padrões proteômicos SELDI-TOF. O método baseia-se em classificar o indivíduo quanto ao estágio de portabilidade do câncer de próstata. Para tanto, usa-se a técnica de Análise de Componentes Independente (ICA) para extrair as características, depois o algoritmo de Máxima Relevância e Mínima Redundância para reduzir o custo computacional, e finalmente a Máquina de Vetores de Suporte para a classificação. Obtêm-se o melhor resultado do método com um vetor de 27 características, alcançando acurácia, especificidade e sensibilidade, respectivamente de 89,21%, 83,68% e 95,08%.
This paper presents a method based on the recognition of proteomic patterns for the early diagnosis of prostate cancer, using computational techniques, applied in the database of SELDI-TOF proteomic patterns. The method is based on classifying the individual as to the portability stage of prostate cancer. To do so, the Independent Component Analysis (ICA) technique is used to extract the characteristics, after which are utilized the algorithm of Maximum Relevance and Minimum Redundancy to reduce the computational cost, and finally the Support Vector Machine to obtain the classification. The best result of the method was obtained with a vector of 27 characteristics, achieving accuracy, specificity and sensitivity, respectively of 89.21%, 83.68% and 95.08%.
This paper presents a method based on the recognition of proteomic patterns for the early diagnosis of prostate cancer, using computational techniques, applied in the database of SELDI-TOF proteomic patterns. The method is based on classifying the individual as to the portability stage of prostate cancer. To do so, the Independent Component Analysis (ICA) technique is used to extract the characteristics, after which are utilized the algorithm of Maximum Relevance and Minimum Redundancy to reduce the computational cost, and finally the Support Vector Machine to obtain the classification. The best result of the method was obtained with a vector of 27 characteristics, achieving accuracy, specificity and sensitivity, respectively of 89.21%, 83.68% and 95.08%.
Description
Keywords
Análise de componentes independentes Câncer de próstata Máquina de vetor de suporte Máxima relevância e mínima redudância Reconhecimento de padrões Independent component analysis Prostate cancer Support vector machine Maximum relevance and minimum redundancy Pattern recognition
Citation
Montes, Elzenir; [et al.] - Aplicação de um método computacional para o diagnóstico precoce do câncer de próstata usando reconhecimento de padrões proteômicos. "Revista de Ciências da Computação" [Em linha]. ISSN 1646-6330 (Print) 2182-1801 (Online). Vol. 11, nº 11 (2016), p. 35-46
Publisher
Universidade Aberta