Evaluating Convolutional Neural Networks for COVID-19 classification in chest X-ray images

TL;DR

This work assesses the effectiveness of four pre-trained CNNs (AlexNet, VGG-11, SqueezeNet, DenseNet-121) for binary COVID-19 detection in chest X-ray images using shallow fine-tuning and data augmentation. By applying stratified ten-fold cross-validation, the study demonstrates high cross-validated accuracy (>97%, with SqueezeNet at 99.20%) despite a small positive class. The results indicate that transfer learning with minimal fine-tuning and augmentation can yield robust discrimination between COVID-19 and non-COVID pneumonia, outperforming several prior reports on the same dataset. The findings suggest practical potential for fast, low-cost screening and point to future directions including larger datasets, hyperparameter optimization, and ensemble methods.

Abstract

Coronavirus Disease 2019 (COVID-19) pandemic rapidly spread globally, impacting the lives of billions of people. The effective screening of infected patients is a critical step to struggle with COVID-19, and treating the patients avoiding this quickly disease spread. The need for automated and scalable methods has increased due to the unavailability of accurate automated toolkits. Recent researches using chest X-ray images suggest they include relevant information about the COVID-19 virus. Hence, applying machine learning techniques combined with radiological imaging promises to identify this disease accurately. It is straightforward to collect these images once it is spreadly shared and analyzed in the world. This paper presents a method for automatic COVID-19 detection using chest Xray images through four convolutional neural networks, namely: AlexNet, VGG-11, SqueezeNet, and DenseNet-121. This method had been providing accurate diagnostics for positive or negative COVID-19 classification. We validate our experiments using a ten-fold cross-validation procedure over the training and test sets. Our findings include the shallow fine-tuning and data augmentation strategies that can assist in dealing with the low number of positive COVID-19 images publicly available. The accuracy for all CNNs is higher than 97.00%, and the SqueezeNet model achieved the best result with 99.20%.

Figures (3)

• Figure 1: Steps of proposed method.
• Figure 2: Examples of image instance for each class.
• Figure 3: 10-fold average values of the performance measures for each CNN model. 1) AlexNet; 2) VGG-11; 3) SqueezeNet; and 4) DenseNet-121.