Classification of Images of Childhood Pneumonia using Convolutional Neural Networks

A. A. Saraiva, N. M. Fonseca Ferreira, N. M. Fonseca Ferreira, N. M. Fonseca Ferreira, Luciano Lopes de Sousa, Nator Junior C. Costa, José Vigno Moura Sousa, José Vigno Moura Sousa, D. B. S. Santos, Antonio Valente, Antonio Valente, Salviano Soares

2019

Abstract

In this paper we describe a comparative classification of Pneumonia using Convolution Neural Network. The database used was the dataset Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images for Classification made available by (Kermany, 2018) with a total of 5863 images, with 2 classes: normal and pneumonia. To evaluate the generalization capacity of the models, cross-validation of k-fold was used. The classification models proved to be efficient compared to the work of (Kermany et al., 2018) which obtained 92.8 % and the present work had an average accuracy of 95.30 %.

Download


Paper Citation


in Harvard Style

Saraiva A., Ferreira N., Lopes de Sousa L., Junior C. Costa N., Sousa J., B. S. Santos D., Valente A. and Soares S. (2019). Classification of Images of Childhood Pneumonia using Convolutional Neural Networks. In Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2019) - Volume 2: BIOIMAGING; ISBN 978-989-758-353-7, SciTePress, pages 112-119. DOI: 10.5220/0007404301120119


in Bibtex Style

@conference{bioimaging19,
author={A. A. Saraiva and N. M. Fonseca Ferreira and Luciano Lopes de Sousa and Nator Junior C. Junior C. Costa and José Vigno Moura Sousa and D. B. S. B. S. Santos and Antonio Valente and Salviano Soares},
title={Classification of Images of Childhood Pneumonia using Convolutional Neural Networks},
booktitle={Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2019) - Volume 2: BIOIMAGING},
year={2019},
pages={112-119},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007404301120119},
isbn={978-989-758-353-7},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2019) - Volume 2: BIOIMAGING
TI - Classification of Images of Childhood Pneumonia using Convolutional Neural Networks
SN - 978-989-758-353-7
AU - Saraiva A.
AU - Ferreira N.
AU - Lopes de Sousa L.
AU - Junior C. Costa N.
AU - Sousa J.
AU - B. S. Santos D.
AU - Valente A.
AU - Soares S.
PY - 2019
SP - 112
EP - 119
DO - 10.5220/0007404301120119
PB - SciTePress