This article provides a comprehensive review of the application of artificial intelligence (AI) in multi-modal imaging for cardiovascular diseases. The authors highlight the significant impact of cardiovascular diseases (CVD) on global health and the potential savings in healthcare costs through the adoption of AI technologies. The review covers recent advancements in multi-modal imaging, focusing on registration, segmentation, and fusion techniques. Key methods and models, such as U-Net, multi-variate mixture models, and convolutional auto-encoders, are discussed, along with their performance in various cardiac imaging tasks. The article also explores the use of AI for predictive tasks and diagnostic aids, including risk assessment for ischemic heart disease and quantification of myocardial tissue heterogeneity. Additionally, it discusses the integration of electronic health records with imaging data and the potential of AI in broader healthcare applications. The authors identify limitations, such as the scarcity of open multi-modal datasets and the need for more robust models in real-world clinical settings, and suggest future directions for research.This article provides a comprehensive review of the application of artificial intelligence (AI) in multi-modal imaging for cardiovascular diseases. The authors highlight the significant impact of cardiovascular diseases (CVD) on global health and the potential savings in healthcare costs through the adoption of AI technologies. The review covers recent advancements in multi-modal imaging, focusing on registration, segmentation, and fusion techniques. Key methods and models, such as U-Net, multi-variate mixture models, and convolutional auto-encoders, are discussed, along with their performance in various cardiac imaging tasks. The article also explores the use of AI for predictive tasks and diagnostic aids, including risk assessment for ischemic heart disease and quantification of myocardial tissue heterogeneity. Additionally, it discusses the integration of electronic health records with imaging data and the potential of AI in broader healthcare applications. The authors identify limitations, such as the scarcity of open multi-modal datasets and the need for more robust models in real-world clinical settings, and suggest future directions for research.