Over time, the emergence of respiratory viruses has placed humanity in a context of uncertainty and fear, often accentuated by the urgency of the response. This enormous number of cases has led the medical community to take a greater interest in this kind of disease. So far, this pandemic has affected more than 200 countries, with more than 591 million coronavirus pneumonia cases and more than 6.4 million deaths directly linked to this coronavirus, officially counted on 19 August 2022. In less than a year, it has plunged humanity into an unprecedented crisis that has spared no area of life. In this context, it is mentioned that the respiratory virus SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus-2) became a major pandemic because of its easy spread in the air and contact with contaminated objects and people. The world was gripped by the COVID-19 pandemic over the first half of 2020, it’s spread had severe and damaging sociological impacts and led to a significant slowdown in economic activities. The results of the classification are promising and will certainly improve the diagnosis and decision making of lung diseases that keep appearing over time. This work implements an accurate computer-aided system for the analysis of radiographic and CT medical images. The results provided robust and consistent features to this system for pneumonia detection with predictive accuracy according to the three classes mentioned above for both imaging modalities: radiography at 99.81% and CT at 99.88%. In terms of accuracy, the proposed model is compared with recent pneumonia detection techniques. In this paper, a deep learning architecture based on EfficientNetB7, known as the most advanced architecture among convolutional networks, has been constructed for classification of medical X-ray and CT images of lungs into three classes namely: common pneumonia, coronavirus pneumonia and normal cases. This has encouraged the use of modern artificial intelligence techniques such as deep learning. Although lung imaging techniques have many advantages for disease diagnosis, the interpretation of medial lung images has always been a major problem for physicians and radiologists due to diagnostic errors. They require accurate and rapid diagnosis. The identification and characterization of lung diseases is one of the most interesting research topics in recent years.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |