Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images.

Momeny, Mohammad; Neshat, Ali Asghar; Hussain, Mohammad Arafat; Kia, Solmaz; Marhamati, Mahmoud; Jahanbakhshi, Ahmad; Hamarneh, Ghassan

Momeny, Mohammad; Neshat, Ali Asghar; Hussain, Mohammad Arafat; Kia, Solmaz; Marhamati, Mahmoud; Jahanbakhshi, Ahmad; Hamarneh, Ghassan.

Afiliação

Momeny M; Department of Computer Engineering, Yazd University, Yazd, Iran. Electronic address: mohamad.momeny@gmail.com.
Neshat AA; Department of Environmental Engineering, Esfarayen Faculty of Medical Science, Esfarayen, Iran. Electronic address: en.neshat@gmail.com.
Hussain MA; School of Computing Science, Simon Fraser University, Burnaby, BC, V5A 1S6, Canada.
Kia S; Department of Engineering Science, Faculty of Advanced Technologies, University of Mohaghegh Ardabili, Namin, Iran.
Marhamati M; Department of Medical-Surgical Nursing, Esfarayen Faculty of Medical Science, Esfarayen, Iran.
Jahanbakhshi A; Department of Biosystems Engineering, University of Mohaghegh Ardabili, Ardabil, Iran.
Hamarneh G; School of Computing Science, Simon Fraser University, Burnaby, BC, V5A 1S6, Canada.

Comput Biol Med ; 136: 104704, 2021 09.

Article em En | MEDLINE | ID: mdl-34352454

Assuntos

COVID-19; Aprendizado Profundo; Teorema de Bayes; Humanos; Radiografia Torácica; SARS-CoV-2; Raios X

Palavras-chave

COVID-19; Classification; Data augmentation; Deep learning; Learning-to-augment; Noise; X-ray images

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Aprendizado Profundo / COVID-19 Tipo de estudo: Diagnostic_studies / Prognostic_studies Limite: Humans Idioma: En Revista: Comput Biol Med Ano de publicação: 2021 Tipo de documento: Article

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google