Open AccessDetection of COVID-19 and Other Pneumonia Cases Using Convolutional Neural Networks and X-ray Images
Author(s) -
Carlos Eduardo Belman-López
Publication year - 2021
Publication title -
ingeniería e investigación/ingeniería e investigación
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.204
H-Index - 12
eISSN - 2248-8723
pISSN - 0120-5609
DOI - 10.15446/ing.investig.v42n1.90289
Subject(s) - hyperparameter , convolutional neural network , overfitting , computer science , binary classification , deep learning , artificial intelligence , machine learning , covid-19 , artificial neural network , pattern recognition (psychology) , medicine , disease , pathology , infectious disease (medical specialty) , support vector machine
Given that it is fundamental to detect positive COVID-19 cases and treat affected patients quickly to mitigate the impact of the virus, X-ray images have been subjected to research regarding COVID-19, together with deep learning models, eliminating disadvantages such as the scarcity of RT-PCR test kits, their elevated costs, and the long wait for results. The contribution of this paper is to present new models for detecting COVID-19 and other cases of pneumonia using chest X-ray images and convolutional neural networks, thus providing accurate diagnostics in binary and 4-classes classification scenarios. Classification accuracy was improved, and overfitting was prevented by following 2 actions: (1) increasing the data set size while the classification scenarios were balanced; and (2) adding regularization techniques and performing hyperparameter optimization. Additionally, the network capacity and size in the models were reduced as much as possible, making the final models a perfect option to be deployed locally on devices with limited capacities and without the need for Internet access. The impact of key hyperparameters was tested using modern deep learning packages. The final models obtained a classification accuracy of 99,17 and 94,03% for the binary and categorical scenarios, respectively, achieving superior performance compared to other studies in the literature, and requiring a significantly lower number of parameters. The models can also be placed on a digital platform to provide instantaneous diagnostics and surpass the shortage of experts and radiologists.