Artificial Intelligence (AI) has become a powerful tool in modern healthcare, particularly in the field of medical image analysis. This research paper focuses exclusively on AI-driven techniques for multi-disease diagnosis using medical imaging, without relying on cloud computing infrastructure. Advanced deep learning models, especially Convolutional Neural Networks (CNNs), are used to analyze X-ray, CT scan, and MRI images to detect diseases such as COVID-19, brain tumors, and lung cancer. By using locally trained and deployed AI models, the system ensures faster response times, improved data privacy, and reduced dependency on internet connectivity. Experimental results from a simulated case study show that the proposed AI-based system achieves an accuracy of 91.6% in classifying multiple diseases. This paper discusses system architecture, dataset preparation, model design, performance evaluation, challenges, ethical considerations, and future scope, highlighting the potential of AI to transform medical diagnostics.