Enhancing X-Ray Imaging: CNN and DWT-Based Noise Reduction for Lower Radiation Exposure

In order to identify afflicted persons and stop transmission, there is an urgent need for precise and effective diagnostic techniques due to the fast spread. This study suggests a customised Deep Convolutional Neural Network (DCNN) architecture that is especially optimised for the identification of cases from CT images in order to address this urgent issue. The suggested DCNN architecture has been painstakingly designed to efficiently identify and evaluate minute patterns and characteristics that point to infection in CT scan pictures. The model is developed using a large dataset that includes CT scans from confirmed cases as well as non-cases for comparison, utilising the capabilities of deep learning. The suggested DCNN has remarkable performance in precisely identifying patients from CT scans after much testing and optimisation. The model achieves high sensitivity and specificity by utilising its capacity to learn intricate patterns and representations from vast amounts of data, allowing for accurate and prompt infection detection.