Automatic detection of COVID-19 infection using chest X-ray images through transfer learning

Abstract

The new coronavirus (COVID-19), declared by the World Health Organization as a pandemic, has infected more than 1 million people and killed more than 50 thousand. An infection caused by COVID-19 can develop into pneumonia, which can be detected by a chest X-ray exam and should be treated appropriately. In this work, we propose an automatic detection method for COVID-19 infection based on chest X-ray images. The datasets constructed for this study are composed of 194 X-ray images of patients diagnosed with coronavirus and 194 X-ray images of healthy patients. Since few images of patients with COVID-19 are publicly available, we apply the concept of transfer learning for this task. We use different architectures of convolutional neural networks (CNNs) trained on ImageNet, and adapt them to behave as feature extractors for the X-ray images. Then, the CNNs are combined with consolidated machine learning methods, such as k-Nearest Neighbor, Bayes, Random Forest, multilayer perceptron (MLP), and support vector machine (SVM). The results show that, for one of the datasets, the extractor-classifier pair with the best performance is the MobileNet architecture with the SVM classifier using a linear kernel, which achieves an accuracy and an F1-Score of 98.5%. For the other dataset, the best pair is DenseNet201 with MLP, achieving an accuracy and an F1-Score of 95.6%. Thus, the proposed approach demonstrates efficiency in detecting COVID-19 in X-ray images.

RETRACTED ARTICLE: Simple hemogram to support the decision-making of COVID-19 diagnosis using clusters analysis with self-organizing maps neural network

“…( 2020 ); Ohata et al. ( 2020 )). Furthermore, other reports utilized supervised machine learning applications for image recognition and diagnosis in health sciences (Omara et al.…”

Convolutional Neural Network Model to Detect COVID-19 Patients Utilizing Chest X-ray Images

“…Most of the works were focused on high sensitivity, i.e. how the classifiers can identify COVID-19 positive cases frequently (Karar et al, 2020; Karthik et al, 2020; Khan et al, 2020; Ismael & Şengür, 2021; Ohata et al, 2021). But, nowadays the community transmission is a great issue to prevent the spread of COVID-19 and the growth of false negative rates are accelerated, which is a great concern.…”

“…Karthik et al (2020) proposed a customized CNN with distinctive filter learning module that shows 97.94% accuracy and 96.90% F1-score for predicting four classes respectively. Ohata et al (2021) proposed an automatic detection model where MobileNet with the SVM (linear kernel) provides 98.5% accuracy and an F1-score and DenseNet201 with MLP shows 95.6% accuracy and an F1-score for COVID-19 infection based on chest X-ray images. Moura et al (2020) investigated 1616 chest X-ray images using DenseNet161 where it shows 79.89% accuracy to classify normal, pathological and COVID-19 patients.…”

An effective classification framework for brain-computer interface system design based on combining of fNIRS and EEG signals

“…It creates a linear combination that gives the most significant mean differences according to the classes entered. In this classifier, a primary scoring function is defined, and the coefficients that will maximize this score are sought ( Arican & Polat, 2019 ; Filho et al, 2014 ; Parah et al, 2020 ; Ohata et al, 2021 ).…”