Diabetic retinopathy, a common complication of diabetes, is further exacerbated by factors such as hypertension and obesity. This study introduces the Diabetic Retinopathy Compact Convolutional Transformer (DRCCT) model, which combines convolutional and transformer techniques to enhance the classification of retinal images. The DRCCT model achieved an impressive average F1-score of 0.97, reflecting its high accuracy in detecting true positives while minimizing false positives. Over 100 training epochs, the model demonstrated outstanding generalization capabilities, achieving a remarkable training accuracy of 99% and a validation accuracy of 95%. This consistent improvement underscores the model’s robust learning process and its effectiveness in avoiding overfitting. On a newly evaluated dataset, the model attained precision and recall scores of 96.93% and 98.89%, respectively, indicating a well-balanced handling of false positives and false negatives. The model’s ability to classify retinal images into five distinct diabetic retinopathy categories demonstrates its potential to significantly improve automated diagnosis and aid in clinical decision-making.
Background: Coronaviruses, members of the Coronavirinae subfamily in the Coronaviridae family, are enveloped and positive-stranded RNA viruses that infect animals and humans, causing intestinal and respiratory infections. Coronavirus disease 2019 (COVID-19) is caused by a novel coronavirus, named Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). This disease appeared, for the first time (December 2019), in China and has spread quickly worldwide causing a large number of deaths. Considering the global threat, the World Health Organization (WHO) has declared, in March 2020, COVID-19 as a pandemic. Many studies suggest the great effect of the existing vaccines to protect against symptomatic cases of death by the COVID-19 virus. This paper, proposes to compare the main antigenic proteins sequences of the existing vaccines with Spike (S) protein of the SARS-CoV-2 genome. Our choice of S protein is justified by the major role that plays it in the receptor recognition and membrane fusion process based on an intelligent system. Herein, we focus on finding a correlation between S protein and compulsory vaccines in the countries that have a less death number by COVID-19 virus. In this work, we have used a combination of coding methods, signal processing, and bioinformatic techniques with the goal to localize the similar patterns between the S gene of the SARS-Cov-2 genome and 14 investigated vaccines. Results: A total of 8 similar sequences which have a size more than 6 amino acids were identified. Further, these comparisons propose that these segments can be implicated in the immune response against COVID-19, which may explain the wide variation by country in the severity of this viral threat. Conclusions: Our in silico study suggests a possible protective effect of Poliovirus, HIB, Hepatitis B, PCV10, Measles, Mumps, and Rubella (MMR) vaccines against COVID-19.