Classification of COVID-19 from CT chest images using Convolutional Wavelet Neural Network

<p>Analyzing X-rays and computed tomography-scan (CT scan) images using a convolutional neural network (CNN) method is very interesting subject, especially after coronavirus disease 2019 (COVID-19) pandemic. In this paper, study made on 423 patients’ CT scan from Al-Kadhimiya (Madenat Al Emammain Kadhmain) hospital in Baghdad, Iraq, to diagnose if they have COVID or not CNN. The total data being tested has 15000 CT-scan chosen specific way give correct diagnosis. activation function used research the wavelet function, which differs CNN functions. (CWNN) model proposed paper compared with regular that uses other functions (exponential linear unit (ELU), rectified (ReLU), Swish, Leaky ReLU, Sigmoid), result utilizing CWNN gave better results for all performance metrics (accuracy, sensitivity, specificity, precision, F1-score). obtained show prediction accuracies of were 99.97%, 99.9%, 99.04% when filters (rational quadratic poles (RASP1), (RASP2), polynomials windowed (POLYWOG1), superposed logistic (SLOG1)) as respectively. Using algorithm can reduce time required radiologist detect whether patient high accuracy.</p>