Efficient classification of COVID-19 CT scans by using q-transform model for feature extraction

• Published in: PeerJ. Computer science 2021-06, Vol.7, p.e553, Article e553
• Main Authors: Al-Azawi, Razi J, Al-Saidi, Nadia M G, Jalab, Hamid A, Kahtan, Hasan, Ibrahim, Rabha W
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Automation; Bioinformatics; Cable television broadcasting industry; Classification; Classifiers; Computed tomography; Computer Vision; Coronaviruses; COVID-19; CT imaging; CT scans; Datasets; Decision trees; Deep learning; Diagnostic imaging; Epidemics; Equalization; Feature extraction; Health aspects; Histograms; Image analysis; Image contrast; Image enhancement; Image resolution; Lungs; Machine learning; Medical imaging; Medical screening; Methods; Physicians; Pneumonia; Preprocessing; q-transform; Radiation; Reduction; Severe acute respiratory syndrome coronavirus 2; Support vector machine; Support vector machines; United States; Wavelet transforms
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.553

The exponential growth in computer technology throughout the past two decades has facilitated the development of advanced image analysis techniques which aid the field of medical imaging. CT is a widely used medical screening method used to obtain high resolution images of the human body. CT has been proven useful in the screening of the virus that is responsible for the COVID-19 pandemic by allowing physicians to rule out suspected infections based on the appearance of the lungs from the CT scan. Based on this, we hereby propose an intelligent yet efficient CT scan-based COVID-19 classification algorithm that is able to discriminate negative from positive cases by evaluating the appearance of lungs. The algorithm is comprised of four main steps: preprocessing, features extraction, features reduction, and classification. In preprocessing, we employ the contrast limited adaptive histogram equalization (CLAHE) to adjust the contrast of the image to enhance the details of the input image. We then apply the q-transform method to extract features from the CT scan. This method measures the grey level intensity of the pixels which reflects the features of the image. In the feature reduction step, we measure the mean, skewness and standard deviation to reduce overhead and improve the efficiency of the algorithm. Finally, "k-nearest neighbor", "decision tree", and "support vector machine" are used as classifiers to classify the cases. The experimental results show accuracy rates of 98%, 98%, and 98.25% for each of the classifiers, respectively. It is therefore concluded that the proposed method is efficient, accurate, and flexible. Overall, we are confident that the proposed algorithm is capable of achieving a high classification accuracy under different scenarios, which makes it suitable for implementation in real-world applications.