Artificial intelligence has become a transformative force in medical imaging, enabling breakthroughs in disease detection, treatment planning, and accurate diagnosis. This chapter serves as an introduction to machine learning (ML) and deep learning (DL) models, with a focus on those most relevant to medical imaging applications. We begin by highlighting fundamental concepts, including supervised and unsupervised learning, outlining a typical ML workflow, discussing concepts such as supervised and unsupervised learning, and introducing the main concepts behind deep learning. Key architectures such as multilayer perceptrons (MLPs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and the autoencoder are also discussed. The chapter also highlights classic CNN designs and advanced architectures, including U-Net, generative adversarial networks (GANs), and transformers, while also addressing emerging trends such as domain adaptation, foundation models, and generative techniques. An introduction to radiomic analysis is also offered, including feature selection and analysis, alongside key factors impacting it. Finally, the chapter underscores the importance of explainability, uncertainty quantification, and robustness, ensuring that AI tools can be trusted in clinical settings. With a balance of theory and practical examples, this chapter serves as an essential guide for understanding the rapidly evolving landscape of AI in medical imaging.