The COVID-19 pandemic highlighted the urgent need for fast, accurate, and scalable diagnostic systems capable of supporting healthcare professionals in detecting infections at early stages. Traditional diagnostic methods such as Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, while considered the gold standard, often suffer from delays, limited availability, and false-negative results, especially during peak infection periods. Medical imaging techniques, including chest X-rays and computed tomography (CT) scans, emerged as complementary diagnostic tools for identifying lung abnormalities associated with COVID-19. In recent years, Artificial Intelligence (AI) has demonstrated significant potential in enhancing the analysis of medical images for rapid and automated disease detection. AI-based models, particularly deep learning architectures such as Convolutional Neural Networks (CNNs), enable automated feature extraction and classification of COVID-19-related patterns in imaging data with high accuracy and efficiency. This research explores AI-driven approaches for COVID-19 detection using medical imaging technologies, focusing on model architectures, dataset utilization, preprocessing techniques, and diagnostic performance evaluation. The study also investigates hybrid AI models, transfer learning approaches, and ensemble methods that improve detection accuracy. Furthermore, it evaluates the benefits, limitations, and challenges associated with deploying AI systems in clinical environments. The findings indicate that AI-based imaging solutions can significantly enhance early diagnosis, reduce workload on healthcare systems, and improve patient outcomes, while also highlighting concerns related to data quality, model interpretability, and clinical validation requirements.
