International Conference on Computer and Knowledge Engineering

Home / 11th International Conference on Computer and Knowledge Engineering

Deep Learning Feature Extraction for COVID-19 Detection Algorithm using Computerized Tomography Scan

Authors :

Maisarah Mohd Sufian¹ Ervin Gubin Moung² Chong Joon Hou³ Ali Farzamnia⁴

1- Faculty of Computing and Informatics Universiti Malaysia Sabah 2- Faculty of Computing and Informatics Universiti Malaysia Sabah 3- Faculty of Computing and Informatics Universiti Malaysia Sabah 4- universiti malaysia sabah

Keywords :

deep learning, COVID-19, computerized tomography, neural network, feature extraction

Abstract :

COVID-19 is a new virus that has infected over three million people worldwide and still infecting, and currently, there is no vaccine and no treatment. The most used method for detecting infected persons is reverse transcriptase-polymerase chain reaction (RT-PCR). However, there is an acute scarcity of RT-PCR test kits worldwide. Therefore, computerized Tomography (CT) scans have been used widely in hospitals to diagnose respiratory illness, among others. Many studies have been carried out where CT scan is used for COVID-19 detection. Due to its nature in the extraction of image attributes, deep learning (DL) was considered a powerful method for improving the accuracy of COVID-19 diagnosis with CT scans. This research compared the performance of the three most popular DL models, (i) Custom CNN, (ii) Resnet-50, and (iii) VGG-16, in the classification of COVID-19 positive and COVID-19 negative patients. The convolutional base of each model is used to obtain features of all images from the SARS-CoV-2 CT-scan dataset. In addition, 10-folds cross-validation is used to evaluate the performance and effectiveness of DL models. VGG-16 gives the best performance in specificity and accuracy with 97% and 92.5% among the three DL models, respectively. Custom CNN outperformed in sensitivity with 90%.v