Use este identificador para citar ou linkar para este item:
https://repositorio.inpa.gov.br/handle/1/20013
Título: | Mycobacterium tuberculosis recognition with conventional microscopy |
Autor: | Costafilho, Cicero F.F. Levy, Pamela Campos Xavier, Clahildek M. Costa, Marly Guimarães Fernandes Fujimoto, Luciana Botinelly Mendonça Salem, Júlia Ignez |
Palavras-chave: | Color Characteristics Color Ratios Color Space Geometric Characteristics Mycobacterium Tuberculosis Noise Filtering Pixel Classification Bacilli Bacteriology Color Feedforward Neural Networks Tubes (components) Pixels Classification Human Isolation And Purification Methodology Microbiology Microscopy Mycobacterium Tuberculosis Reproducibility Sensitivity And Specificity Sputum Humans Microscopy Mycobacterium Tuberculosis Reproducibility Of Results Sensitivity And Specificity Sputum |
Data do documento: | 2012 |
Editor: | Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS |
É parte de: | Pags. 6263-6268 |
Abstract: | This paper presents a new method for segmentation of tuberculosis bacillus in conventional sputum smear microscopy. The method comprises three main steps. In the first step, a scalar selection are made for characteristics from the following color spaces: RGB, HSI, YCbCr and Lab. The features used for pixel classification in the segmentation step were the components and subtraction of components of these color spaces. In the second step, a feedforward neural network pixel classifier, using selected characteristics as inputs, is applied to segment pixels that belong to bacilli from the background. In third step geometric characteristics, especially the eccentricity, and a new proposed color characteristic, the color ratio, are used to noise filtering. The best sensitivity achieved in bacilli detection was 91.5%. © 2012 IEEE. |
DOI: | 10.1109/EMBC.2012.6347426 |
Aparece nas coleções: | Trabalhos Apresentados em Evento |
Arquivos associados a este item:
Não existem arquivos associados a este item.
Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.