Due to the conditions in which countries experienced the outbreak of the Coronavirus and our problem in diagnosing the disease, some of them relied on swabs to know if a person was infected, and also their dependence on symptoms such as temperature, rapid heartbeat, pressure, coughing and other symptoms similar to the normal flu, but this method is failure sometimes, therefore it was the best way for early detection and diagnosis of cases of COVID- 19, as well as the accurate segregation of non-COVID-19 patients at cost and in the early stages of the disease, is a major difficulty in the current COVID-19 pandemic. Although widely used in diagnostic centres, radiation-based diagnostic techniques have drawbacks when it comes to disease newness. As a result, deep learning models are commonly used for X-ray interpretation by medical and computational researchers. Deep learning models can identify COVID-19, a critical task for treatment options based on diagnostic data these days. On the other hand, advances in artificial intelligence, machine learning, deep learning, and medical imaging methods enable outstanding performance, especially in detection, classification, and segmentation issues. These advances have allowed clinicians to more accurately monitor the human body, improving diagnosis and non-surgical patient examination. There are a variety of imaging methods that can be used to identify COVID-19, but we choose to use computerized tomography (CT) because it is the most commonly used. In addition, to detect COVID-19, we use a deep learning model based on a Convolutional Neural Network (CNN). Two samples of the tested data were used, where one of these data was collected from Al-Karkh Hospital in Baghdad, which consisted of 40 people, samples were taken according to their critical condition. The system was trained and tested on the basis of this dataset, where we used CNN three times, once to extract the feature and twice for the classification process. The results showed that the accuracy of the system reaches 100% because this system depends on the Bayes rule and it is not possible error.

In this century, lung cancer is undoubtedly one of the major serious health problems, and one of the leading causes of death for women and men worldwide. Despite advances in treating lung cancer with unprecedented products of pharmaceutical and technological advances, mortality and morbidity rates remain a major challenge for oncologists and cancer biologists. Thus, there is an urgent need to provide early, accurate, and effective diagnostic techniques to improve the survival rate and reduce morbidity and mortality related to lung cancer patients. Therefore, in this paper, an effective lung cancer screening technique is proposed for the early detection of risk factors for lung cancer. In this proposed technique, the powerful acceleration feature Speeded up robust feature (SURF) was used to extract the features. One of the machine learning methods was used to detect cancer by relying on the k nearest neighbor (KNN ) method, where the experimental results show an effective way to discover SURF features and tumor detection by relying on neighborhoods and calculating the distance using KNN. As a result, a high system sensitivity performance success rate of 96% and a system accuracy of 99% has been achieved.