Over the past few decades, imaging has become a crucial part of medical decision-making. Techniques such as computed tomography (CT), magnetic resonance imaging (MRI), X-ray radiography, and positron emission tomography (PET) have given physicians increasing amounts of two-dimensional anatomical information, which influences triaging, treatment, intervention, and clinical outcomes. This has created a need for a streamlined method to process and quantify large amounts of imaging data. The process of acquiring these datasets, converting or processing them into a mineable format, extracting relevant features, and performing analysis through machine learning is known as radiomics (Scapicchio et al. Radiol Med 126:1296–1311, 2021). Radiomics has most rapidly grown in the field of oncology due to its improved spatiotemporal resolution, high-throughput comprehensive characterization of heterogeneous tumors, and its ability to capture genomic, cellular, and metabolic signatures on a spectrum (Parekh and Jacobs Expert Rev Precis Med Drug Dev 4:59–72, 2019). Applications of radiomics have been varied, including prediction and measure of treatment response, tumor staging, and genetic characterization to move toward personalized medicine (Ding et al. Front Oncol 11:689802, 2021). This chapter summarizes the principles of quantitative imaging and details and overview of clinical applications.