The article provides an introduction to radiomics, a field that focuses on extracting quantitative metrics, or radiomic features, from medical images. These features capture tissue and lesion characteristics such as heterogeneity and shape, which can be used alone or in combination with other data for clinical problem-solving. The authors outline the basic radiomics workflow, including feature calculation and selection, dimensionality reduction, and data processing. They discuss potential clinical applications in nuclear medicine, such as predicting treatment response and survival using PET radiomics. The limitations of radiomics, including sensitivity to acquisition parameter variations and common pitfalls, are also covered. The article emphasizes the importance of standardized image acquisition and reconstruction protocols to ensure the reliability and reproducibility of radiomic features. Additionally, it highlights the use of machine learning techniques to improve the accuracy and reliability of radiomic predictions.The article provides an introduction to radiomics, a field that focuses on extracting quantitative metrics, or radiomic features, from medical images. These features capture tissue and lesion characteristics such as heterogeneity and shape, which can be used alone or in combination with other data for clinical problem-solving. The authors outline the basic radiomics workflow, including feature calculation and selection, dimensionality reduction, and data processing. They discuss potential clinical applications in nuclear medicine, such as predicting treatment response and survival using PET radiomics. The limitations of radiomics, including sensitivity to acquisition parameter variations and common pitfalls, are also covered. The article emphasizes the importance of standardized image acquisition and reconstruction protocols to ensure the reliability and reproducibility of radiomic features. Additionally, it highlights the use of machine learning techniques to improve the accuracy and reliability of radiomic predictions.