The world health organization states that the coronavirus epidemic has created a daily threat to the global healthcare system. After numerous deaths around the world, the pandemic unlocked a new threat making people ready for something which is similar and unpredictable. There were many challenges including the shortage of medical staff, beds, diagnosis centres, and intensive care units. Correct detection of disease is also crucial in surviving the pandemic. So, with a growing need for accurate and rapid diagnosis, there are many alternatives that are derived to identify the disease with the help of Radiology and Computed Tomography (CT) scans. This paper proposes a deep-learning-based approach for the detection of COVID-19 from X-ray and CT-scan images and is based on Predefined CNN architectures such as DenseNet201 and ResNet152, which are fine-tuned to classify images as COVID-19 positive or negative. The results obtained demonstrate that the proposed methods achieve high accuracy in detecting COVID-19 cases from X-ray and CT scan images. Hence, this project can be used as a valuable tool for frontline healthcare workers and public health officials to fight against the COVID-19 pandemic.