A different perspective on the diagnosis of COVID-19 disease with the developed quadstar local binary pattern method

Abstract

The COVID-19 disease is one of the most severe health disasters encountered in the world recently. COVID-19 disease is a highly fatal disease that spreads quickly through the respiratory tract. The most accurate method for diagnosing COVID-19 disease is Reverse Transcription Polymerase Chain Reaction (RT-PCR). Although this method gives more precise results, it is extremely costly in terms of cost and processing time. To overcome this issue, many studies are being carried out, particularly on diagnosis via lung images. Deep learning, artificial intelligence, and machine learning methods are applied in image enhancement studies, and powerful results are obtained. Within the scope of this study, texture analysis methods, which are part of the image enhancement methods, are examined. Among these methods, the local binary pattern (LBP) method has a special place. Due to the extremely high success rate of the LBP method, many successful derivative methods have been derived from this method. The paper includes the developed quadstar local binary pattern (QS-LBP) method derived from the standard LBP method. Moreover, machine learning (ML) algorithms are used to process the features extracted from two different models using the QS-LBP method. Extremely high analysis values have been obtained from the hybrid method consisting of the developed models and ML methods, accuracy is 99.21%, kappa is 96.2%, ROC area is 99.8%, F-measure is 99.6 %, precision is 99.5%, and finally recall is 99.8%, respectively. Using the hybrid technique suggested in the paper, diagnosing COVID-19 disease in lung images has been carried out exceedingly successfully. © The Author(s) 2025.