Estudo da caracterização de nódulos em mamogramas através de uma configuração de rede neural artificial
Data
2017-11-15
Autores
Título da Revista
ISSN da Revista
Título de Volume
Editor
Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo
Escola de Engenharia de São Carlos
Universidade de São Paulo
Escola de Engenharia de São Carlos
Resumo
Descrição
Este trabalho apresenta um estudo de classificação de nódulos em mamograma digitalizados através de um classificador de rede neural artificial (RNA). O algoritmo de treinamento de \"backpropagation\" foi utilizado para ajustar os pesos da RNA. O objetivo principal deste trabalho foi determinar um método para analisar e selecionar a melhor configuração de atributos e topologia da RNA para classificar lesões mamárias do tipo nódulo. Foram escolhidas 118 imagens de regiões de interesse (ROI), sendo 68 benignas e 50 malignas de duas bases de imagens: uma do Hospital das Clínicas de Ribeirão Preto, da Universidade de São Paulo, e outra do MIAS-UK (Mammographic Image Analysis Society). O processo completo envolveu quatro etapas: detecção, extração e seleção de atributos, e classificação. Na etapa de detecção, as imagens foram submetidas ao processo combinado das técnicas segmentação de thresholding, morfologia matemática e crescimento de região. Foram extraídos 14 atributos de textura e 14 atributos de forma. Para selecionar os atributos mais discriminantes, foi utilizado o método de Jeffries-Matusita. Foram selecionados três grupos de atributos de forma, três de atributos de textura e três de atributos combinados. Análise pela curva ROC foram dirigidas para avaliar o desempenho do classificador de rede neural artificial (RNA). Os melhores resultados obtidos foram: para o grupo de atributos de forma com 5 unidades escondidas, a área dentro da curva ROC foi de 0.99, taxa de acerto de 98,21%, taxa de especificidade de 98,37% e taxa de sensibilidade de 98.00%; para o grupo de atributos de textura com 4 unidades escondidas, a área dentro da curva foi de 0.98, taxa de acerto de 97,08%, taxa de especificidade de 98,53% e taxa de sensibilidade de 95.11%; para o grupo de atributos combinados de textura e forma com 3 unidades escondidas, a área dentro da curva foi de 0.99, taxa de acerto de 98,21%, taxa de especificidade de 100.00% e taxa de sensibilidade de 95.78%.
This work presents a study of masses classification in digitized mammograms by means of artificial neural network (ANN). The backpropagation training algorithm was used to adjust the weights of ANN. The aim of this work was to determine a methodology to analyze and selection of the best feature subset and ANN topology to classify masses lesions. A total of 118 regions of interest images were chosen (68 benign and 50 malignant lesions) from two image databases: one from \"Hospital das Clínicas de Ribeirão Preto\", at the University of São Paulo, and other from Mammographic lmage Analysis Society (MIAS-UK). The whole process involved four steps: segmentation, feature extraction, selection, and classification. In the first step, the images were submitted to a combined process of thresholding, mathematical morphology, and region growing techniques. In the second step, fourteen texture features and fourteen shape features were extracted. The Jeffries-Matusita method was used to select the best features. The results of this stage were the selection of three shape feature sets, three texture feature sets, and three combined feature sets. The Receiver Operating Characteristic (ROC) analysis were conducted to evaluated the ANN classifier performance. The best result obtained for shape feature set was obtained using a ANN with 5 hidden units, the area under ROC curve was of 0.99, classification rate of 98.21%, specificity rate of 98.37% and sensitivity rate of 98.00%. For texture feature set, the best result was using a ANN with 4 hidden units, the area under ROC curve was of 0.98, classification rate of 97.08%, specificity rate of 98.53% and sensitivity rate of 95.11%. Finally, for the combined feature set (texture and shape) the best result obtained was using a ANN with 3 hidden units, the area under ROC curve was of 0.99, classification rate of 98.21%, specificity rate of 100.00% and sensitivity rate of 95.78%.
This work presents a study of masses classification in digitized mammograms by means of artificial neural network (ANN). The backpropagation training algorithm was used to adjust the weights of ANN. The aim of this work was to determine a methodology to analyze and selection of the best feature subset and ANN topology to classify masses lesions. A total of 118 regions of interest images were chosen (68 benign and 50 malignant lesions) from two image databases: one from \"Hospital das Clínicas de Ribeirão Preto\", at the University of São Paulo, and other from Mammographic lmage Analysis Society (MIAS-UK). The whole process involved four steps: segmentation, feature extraction, selection, and classification. In the first step, the images were submitted to a combined process of thresholding, mathematical morphology, and region growing techniques. In the second step, fourteen texture features and fourteen shape features were extracted. The Jeffries-Matusita method was used to select the best features. The results of this stage were the selection of three shape feature sets, three texture feature sets, and three combined feature sets. The Receiver Operating Characteristic (ROC) analysis were conducted to evaluated the ANN classifier performance. The best result obtained for shape feature set was obtained using a ANN with 5 hidden units, the area under ROC curve was of 0.99, classification rate of 98.21%, specificity rate of 98.37% and sensitivity rate of 98.00%. For texture feature set, the best result was using a ANN with 4 hidden units, the area under ROC curve was of 0.98, classification rate of 97.08%, specificity rate of 98.53% and sensitivity rate of 95.11%. Finally, for the combined feature set (texture and shape) the best result obtained was using a ANN with 3 hidden units, the area under ROC curve was of 0.99, classification rate of 98.21%, specificity rate of 100.00% and sensitivity rate of 95.78%.
Palavras-chave
Rede neural artificial, Reconhecimento de padrões, Câncer de mama, Diagnóstico auxiliado por computador, Mamograma digital, Pattern recognition, Digital mammograms, Computer aided diagnosis, Breast cancer, Artificial neural network