Your browser doesn't support javascript.
loading
Automatic bright-field smear microscopy for diagnosis of pulmonary tuberculosis.
Serrão, Mikaela Kalline Maciel; Costa, Marly Guimarães Fernandes; Fujimoto, Luciana Botinelly Mendonça; Ogusku, Mauricio Morishi; Costa Filho, Cicero Ferreira Fernandes.
Afiliação
  • Serrão MKM; R&D Center in Electronic and Information Technology, Federal University of Amazonas, Manaus, 69067-005, Brazil.
  • Costa MGF; R&D Center in Electronic and Information Technology, Federal University of Amazonas, Manaus, 69067-005, Brazil.
  • Fujimoto LBM; Faculty of Medicine, Federal University of Amazonas, Manaus, 69020-160, Brazil.
  • Ogusku MM; National Institute of Amazonian Research - INPA, 69080-971, Manaus, Brazil.
  • Costa Filho CFF; R&D Center in Electronic and Information Technology, Federal University of Amazonas, Manaus, 69067-005, Brazil. Electronic address: ccosta@ufam.edu.br.
Comput Biol Med ; 172: 108167, 2024 Apr.
Article em En | MEDLINE | ID: mdl-38461699
ABSTRACT
In recent decades, many studies have been published on the use of automatic smear microscopy for diagnosing pulmonary tuberculosis (TB). Most of them deal with a preliminary step of the diagnosis, the bacilli detection, whereas sputum smear microscopy for diagnosis of pulmonary TB comprises detecting and reporting the number of bacilli found in at least 100 microscopic fields, according to the 5 grading scales (negative, scanty, 1+, 2+ and 3+) endorsed by the World Health Organization (WHO). Pulmonary TB diagnosis in bright-field smear microscopy, however, depends upon the attention of a trained and motivated technician, while the automated TB diagnosis requires little or no interpretation by a technician. As far as we know, this work proposes the first automatic method for pulmonary TB diagnosis in bright-field smear microscopy, according to the WHO recommendations. The proposed method comprises a semantic segmentation step, using a deep neural network, followed by a filtering step aiming to reduce the number of false positives (false bacilli) color and shape filtering. In semantic segmentation, different configurations of encoders are evaluated, using depth-wise separable convolution layers and channel attention mechanism. The proposed method was evaluated with a large, robust, and annotated image dataset designed for this purpose, consisting of 250 testing sets, 50 sets for each of the 5 TB diagnostic classes. The following performance metrics were obtained for automatic pulmonary TB diagnosis by smear microscopy mean precision of 0.894, mean recall of 0.896, and mean F1-score of 0.895.
Assuntos
Palavras-chave
Texto completo
Adicionar na Minha BVS
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Tuberculose Pulmonar / Mycobacterium tuberculosis Limite: Humans Idioma: En Revista: Comput Biol Med Ano de publicação: 2024 Tipo de documento: Article País de afiliação: Brasil País de publicação: Estados Unidos
Texto completo
Adicionar na Minha BVS
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Tuberculose Pulmonar / Mycobacterium tuberculosis Limite: Humans Idioma: En Revista: Comput Biol Med Ano de publicação: 2024 Tipo de documento: Article País de afiliação: Brasil País de publicação: Estados Unidos