A Comparison of Deep Learning Models for Detecting COVID-19 in Chest X-ray Images.

Peláez, Enrique; Serrano, Ricardo; Murillo, Geancarlo; Cárdenas, Washington

Peláez, Enrique; Serrano, Ricardo; Murillo, Geancarlo; Cárdenas, Washington.

Afiliação

Peláez E; Escuela Superior Politécnica del Litoral - ESPOL University, Electrical and Computer Engineering, Guayaquil, Ecuador.
Serrano R; Escuela Superior Politécnica del Litoral - ESPOL University, Electrical and Computer Engineering, Guayaquil, Ecuador.
Murillo G; Escuela Superior Politécnica del Litoral - ESPOL University, Electrical and Computer Engineering, Guayaquil, Ecuador.
Cárdenas W; Escuela Superior Politécnica del Litoral - ESPOL University, Life Science, Guayaquil, Ecuador.

IFAC Pap OnLine ; 54(15): 358-363, 2021.

Article em En | MEDLINE | ID: mdl-38620947

ABSTRACT

ABSTRACT

COVID-19 has spread around the world rapidly causing a pandemic. In this research, a set of Deep Learning architectures, for diagnosing the presence or not of the disease have been designed and compared; such as, a CNN with 4 incremental convolutional blocks; a VGG-19 architecture; an Inception network; and, a compact CNN model known as MobileNet. For the analysis and comparison, transfer learning techniques were used in forty-five different experiments. All four models were designed to perform binary classification, reaching an accuracy above 95%. A set of different scores were implemented to compare the performance of all models, showing that the VGG-19 and Inception configurations performed the best.

Palavras-chave

COVID-19; Convolutional Neural Network; Machine Learning; Transfer Learning; X-Ray Image Analysis

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Revista: IFAC Pap OnLine Ano de publicação: 2021 Tipo de documento: Article País de afiliação: Equador País de publicação: Holanda

Texto completo

Adicionar na Minha BVS

Imprimir

XML

PubMed Links

Buscar no Google