Mycobacterium tuberculosis recognition with conventional microscopy
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 fo...
| Autor principal: | Costafilho, Cicero F.F. |
|---|---|
| Outros Autores: | Levy, Pamela Campos, Xavier, Clahildek M., Costa, Marly Guimarães Fernandes, Fujimoto, Luciana Botinelly Mendonça, Salem, Júlia Ignez |
| Grau: | Trabalho Apresentado em Evento |
| Idioma: | English |
| Publicado em: |
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
2020
|
| Assuntos: | |
| Acesso em linha: |
https://repositorio.inpa.gov.br/handle/1/20013 |
| id |
oai:repositorio:1-20013 |
|---|---|
| recordtype |
dspace |
| spelling |
oai:repositorio:1-20013 Mycobacterium tuberculosis recognition with conventional microscopy Costafilho, Cicero F.F. Levy, Pamela Campos Xavier, Clahildek M. Costa, Marly Guimarães Fernandes Fujimoto, Luciana Botinelly Mendonça Salem, Júlia Ignez 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 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. 2020-06-16T17:31:43Z 2020-06-16T17:31:43Z 2012 Trabalho Apresentado em Evento https://repositorio.inpa.gov.br/handle/1/20013 10.1109/EMBC.2012.6347426 en Pags. 6263-6268 Restrito Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS |
| institution |
Instituto Nacional de Pesquisas da Amazônia - Repositório Institucional |
| collection |
INPA-RI |
| language |
English |
| topic |
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 |
| spellingShingle |
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 Costafilho, Cicero F.F. Mycobacterium tuberculosis recognition with conventional microscopy |
| topic_facet |
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 |
| description |
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. |
| format |
Trabalho Apresentado em Evento |
| author |
Costafilho, Cicero F.F. |
| author2 |
Levy, Pamela Campos Xavier, Clahildek M. Costa, Marly Guimarães Fernandes Fujimoto, Luciana Botinelly Mendonça Salem, Júlia Ignez |
| author2Str |
Levy, Pamela Campos Xavier, Clahildek M. Costa, Marly Guimarães Fernandes Fujimoto, Luciana Botinelly Mendonça Salem, Júlia Ignez |
| title |
Mycobacterium tuberculosis recognition with conventional microscopy |
| title_short |
Mycobacterium tuberculosis recognition with conventional microscopy |
| title_full |
Mycobacterium tuberculosis recognition with conventional microscopy |
| title_fullStr |
Mycobacterium tuberculosis recognition with conventional microscopy |
| title_full_unstemmed |
Mycobacterium tuberculosis recognition with conventional microscopy |
| title_sort |
mycobacterium tuberculosis recognition with conventional microscopy |
| publisher |
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS |
| publishDate |
2020 |
| url |
https://repositorio.inpa.gov.br/handle/1/20013 |
| _version_ |
1787143947484659712 |
| score |
11.755432 |