Recent advances in artificial intelligence have already made their way into multiple fields of medicine. The ability of state-of-the-art AI methods to analyse and generate images makes radiology an area where substantial impact is particularly likely. However, with the promise of AI-enabled methods that improve efficiency, accuracy, or reproducibility also come the environmental costs associated with computationally intensive algorithms. This chapter provides an introduction to basic concepts in modern AI, with particular emphasis on their application in radiology. It starts with the basics of Artificial Neural Networks, progresses with more advanced architectures such as Convolutional Neural Networks and Transformers, and explains the principles of generative AI methods and their main applications in radiology. Finally, it discusses the carbon footprint of AI in radiology, outlining future developments to ensure the alignment of AI developments with net zero healthcare.