Diagnosis of COVID-۱۹ patients based on chest CT images using image processing algorithms

The rapid diagnosis of the disease often makes the treatment procedure faster and less expensive. In the caseof SARS-COV۲, an infectious disease with a high rate if transmission, diagnosis without the need to see adoctor is of great importance.In this study, we aim to introduce an algorithm with a high performamce based on which we can diagnose apatient based on the chest CT imaging features, and without any need for the suspected patient to see a doctor.Firstly, we enhanced the quality of CT images by using the classic algorithms and the most important filtersfor image processing. Then thr most important CT imaging feature were extracted using a convolutionalneural network. We have used two imaging sets including ۴۲ images from patients and ۴۲ images fromhealthy persons. For each of CT features we assigned a certain weight.Finally, we desgined an algorithm which gets a CT image from an individual as input, and determines whetherthis individual is healthy or patient, by enhancing the quality of the initial image, extracting the relevantimaging features by using a convolutional neural network, and adding the multiplication of each feature andits associated weight.In this study, by examining ۱۲۸۸ photos of healthy people and ۱۳۴۳ photos of sick people, we reached about۹۰% accuracy in diagnosing the disease.