ABSTRACT

The humankind had faced several pandemic outbreaks, and coronavirus illness (COVID-19) caused by severe, acute respiratory syndrome coronavirus 2, is designated an emergency by the World Health Organization (WHO). Recognition of COVID-19 is a challenging task. The most commonly used methods are X-ray and CT scans images to inspect COVID-19 patients. It requires specialised medical professionals to report each patient’s health manually. It is found that COVID-19 shows considerable similarity to pneumonia lung disease. Thus, knowledge learned from a model to diagnose pneumonia can be translated to identify COVID-19. Transfer learning method offers a drastic performance when compared with results from conventional classification. In this study, Image pre-processing is done to alleviate intensity variations between medical images. These processed images undergo a feature extraction which is accomplished using Q-deformed entropy and deep learning extraction. The feature extraction techniques are employed to remove abnormal markers from images, noise impedance from tissues and lesions. The traits acquired are integrated to differentiate between COVID-19, pneumonia and healthy cases. The primary aim of this model is to produce an image processing tool for medical professionals. The model results to inspect how a healthy or COVID-19 individual outperforms conventional models. The maximum accuracy of the collected data set is 99.68%.

摘要

人类曾面临数次大流行爆发，由严重急性呼吸系统综合症冠状病毒 2 引起的冠状病毒病 (COVID-19) 已被世界卫生组织 (WHO) 指定为紧急情况。识别 COVID-19 是一项具有挑战性的任务。最常用的方法是 X 射线和 CT 扫描图像来检查 COVID-19 患者。它需要专门的医疗专业人员手动报告每位患者的健康状况。发现 COVID-19 与肺炎肺部疾病有相当大的相似性。因此，从诊断肺炎的模型中学到的知识可以转化为识别 COVID-19。与传统分类的结果相比，迁移学习方法提供了显着的性能。在这项研究中，进行图像预处理以减轻医学图像之间的强度变化。这些处理过的图像经过特征提取，这是使用 Q 变形熵和深度学习提取完成的。特征提取技术用于从图像中去除异常标记，从组织和病变中去除噪声阻抗。整合获得的特征以区分 COVID-19、肺炎和健康病例。该模型的主要目的是为医疗专业人员制作图像处理工具。该模型的结果是检查健康或 COVID-19 个体如何优于传统模型。收集到的数据集的最大准确率为99.68%。整合获得的特征以区分 COVID-19、肺炎和健康病例。该模型的主要目的是为医疗专业人员制作图像处理工具。该模型的结果是检查健康或 COVID-19 个体如何优于传统模型。收集到的数据集的最大准确率为99.68%。整合获得的特征以区分 COVID-19、肺炎和健康病例。该模型的主要目的是为医疗专业人员制作图像处理工具。该模型的结果是检查健康或 COVID-19 个体如何优于传统模型。收集到的数据集的最大准确率为99.68%。