Abstract
Background: The aim of this study was to evaluate the performance of an automated COVID-19 detection method based on a transfer learning technique that makes use of chest computed tomography (CT) images. Method: In this study, we used a publicly available multiclass CT scan dataset containing 4171 CT scans of 210 different patients. In particular, we extracted features from the CT images using a set of convolutional neural networks (CNNs) that had been pretrained on the ImageNet dataset as feature extractors, and we then selected a subset of these features using the Information Gain filter. The resulting feature vectors were then used to train a set of k Nearest Neighbors classifiers with 10-fold cross validation to assess the classification performance of the features that had been extracted by each CNN. Finally, a majority voting approach was used to classify each image into two different classes: COVID-19 and NO COVID-19. Results: A total of 414 images of the test set (10% of the complete dataset) were correctly classified, and only 4 were misclassified, yielding a final classification accuracy of 99.04%. Conclusions: The high performance that was achieved by the method could make it feasible option that could be used to assist radiologists in COVID-19 diagnosis through the use of CT images.
Highlights
In March 2020, the new coronavirus (COVID-19) pandemic was declared by the WorldHealth Organization (WHO)
All of these approaches use artificial intelligence (AI) techniques, those that are derived from machine learning (ML), which are considered to be a prominent tool for the prediction and diagnosis of numerous diseases [15]
Soares et al [28] proposed an eXplainable Deep Learning approach that used a dataset that contained 2482 computed tomography (CT) scans in total, 1252 CT scans that were positive for SARS-CoV-2 infection, and 1230 CT scans for patients who were not infected with SARS-CoV-2, achieving an F1 score of 97.31%
Summary
In March 2020, the new coronavirus (COVID-19) pandemic was declared by the WorldHealth Organization (WHO). It has been demonstrated that the interpretation of CT images for COVID-19 diagnosis that have been made by radiologists do not have high sensitivity [14] For these reasons, novel approaches have been proposed in order to find automated methods to detect COVID-19 in CT images. Loddo et al [29] presented a method in which they first compared different architectures on a public and extended reference dataset to find the most suitable one, and proposed a patient-oriented investigation to determine which network had the best performance They evaluated their robustness in a real-world scenario, which was represented by cross-dataset experiments. Conclusions: The high performance that was achieved by the method could make it feasible option that could be used to assist radiologists in COVID-19 diagnosis through the use of CT images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
