Idioma:

Automated diagnosis of intestinal parasites: A new hybrid approach and its benefits

Osaku, D. ; Cuba, C.F. ; Suzuki, C.T.N. ; Gomes, J.F. ; Falcão, A.X.

Computers in biology and medicine, 2020-08, Vol.123, p.103917-103917, Article 103917 [Periódico revisado por pares]

United States: Elsevier Ltd

Texto completo disponível

Citações Citado por

Enviar para

Título:
Automated diagnosis of intestinal parasites: A new hybrid approach and its benefits
Autor: Osaku, D. ; Cuba, C.F. ; Suzuki, C.T.N. ; Gomes, J.F. ; Falcão, A.X.
Assuntos: Artificial neural networks ; Automated diagnosis of intestinal parasites ; Automation ; Classification ; Clinical decision making ; Complex systems ; Cysts ; Decision making ; Deep neural networks ; Diagnosis ; Eggs ; Error analysis ; Feature extraction ; Hybrid systems ; Image classification ; Intestinal parasites ; Intestine ; Larvae ; Light microscopy ; Medical diagnosis ; Medical imaging ; Microscopy ; Microscopy image analysis ; Neural networks ; Optical microscopy ; Parasites ; Protozoa ; Reclassification ; Support vector machines
É parte de: Computers in biology and medicine, 2020-08, Vol.123, p.103917-103917, Article 103917
Notas: ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Descrição: Intestinal parasites are responsible for several diseases in human beings. In order to eliminate the error-prone visual analysis of optical microscopy slides, we have investigated automated, fast, and low-cost systems for the diagnosis of human intestinal parasites. In this work, we present a hybrid approach that combines the opinion of two decision-making systems with complementary properties: (DS1) a simpler system based on very fast handcrafted image feature extraction and support vector machine classification and (DS2) a more complex system based on a deep neural network, Vgg-16, for image feature extraction and classification. DS1 is much faster than DS2, but it is less accurate than DS2. Fortunately, the errors of DS1 are not the same of DS2. During training, we use a validation set to learn the probabilities of misclassification by DS1 on each class based on its confidence values. When DS1 quickly classifies all images from a microscopy slide, the method selects a number of images with higher chances of misclassification for characterization and reclassification by DS2. Our hybrid system can improve the overall effectiveness without compromising efficiency, being suitable for the clinical routine — a strategy that might be suitable for other real applications. As demonstrated on large datasets, the proposed system can achieve, on average, 94.9%, 87.8%, and 92.5% of Cohen’s Kappa on helminth eggs, helminth larvae, and protozoa cysts, respectively. •A hybrid decision-making system that improves effectiveness without compromising efficiency.•It combines a faster and less accurate decision system DS1 with DS2, a slower and more accurate one.•A method that selects images with higher chances of errors by DS1 for analysis by DS2.•A viable solution towards the automated diagnosis of intestinal parasites.
Editor: United States: Elsevier Ltd
Idioma: Inglês

Links

View this record in MEDLINE/PubMed

Voltar para lista de resultados

Anterior Resultado 5 Avançar Ir para próxima página

Realização: Logos de Redes Sociais:

Automated diagnosis of intestinal parasites: A new hybrid approach and its benefits

Osaku, D. ; Cuba, C.F. ; Suzuki, C.T.N. ; Gomes, J.F. ; Falcão, A.X.

United States: Elsevier Ltd

Buscando em bases de dados remotas. Favor aguardar.