Metodologia de extração automática de características da mão para a estimação da idade óssea utilizando redes neurais artificiais no processo de decisão / Methodology of automatic extraction of hand characteristics for the estimation of the bone age using artificial neural nets in the decision process

AUTOR(ES)
DATA DE PUBLICAÇÃO

2006

RESUMO

Grounded an Eklof &Ringertz’s method and using artificial neural networks as classifier, the main purpoise of this work is to present a methodology to reckon the bone age to the effect to help the radiologist’s diagnosis and to reduce the dimensionality of the data analyzed by neural network, reducing the quantity of the ossification’s centers of the used method. The methodology holds an automatic process to the hands radiographies image’s features. The multilayer perceptron neural network is used in the classification stage, with the Levemberg-Marquardt’s training algorithm. The taken image’s features are used as an input to the neural network, and Eklof &Ringertz’s Atlas data are used as training source. The results of the classification stage reached a rate of 95% of accuracy when applying the Eklof &Ringertz’s simplified method, excluding one of the ossification center

ASSUNTO(S)

extract features extração de características bone age artificial neural networks image processing redes neurais artificiais processamento de imagem idade óssea

Documentos Relacionados