COVID19 Chest X-Ray Classification with Simple Convolutional Neural Network

Conference proceedings article

Authors/Editors

Strategic Research Themes

Publication Details

Author list: Li, Chenqi; Wang, Maggie; Wu, Grace; Rana, Khadija; Charoenkitkarn, Nipon; Chan, Jonathan;

Publisher: Hindawi

Publication year: 2020

Start page: 97

End page: 100

Number of pages: 4

ISBN: 9781450388238

ISSN: 0146-9428

eISSN: 1745-4557

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85097280524&doi=10.1145%2f3429210.3429216&partnerID=40&md5=8cc128d18696e5c4983f9de451f8bac5

Languages: English-Great Britain (EN-GB)

View on publisher site

Abstract

COVID-19 outbreak calls for the urgent need of quick, accurate, and accessible methods for detection. Convolutional neural networks applied to chest X-ray images is a promising solution; however, X-ray device configurations vary and data quality across different datasets are inconsistent. This leads to overfitting on a particular set of training data. This paper aims to explore methods to mitigate overfitting. © 2020 ACM.

Keywords

Chest X-ray, Keras, Overfitting, TensorFlow