Radiomics is a quantitative approach to medical imaging that enhances clinical data through advanced mathematical analysis. This review aims to provide a practical guide to radiomics analysis and discuss its current limitations. The workflow includes image segmentation, image processing, feature extraction, and dimension reduction. Image segmentation can be manual, semi-automated, or fully automated, with deep learning algorithms being the most promising for reducing observer bias. Image processing involves homogenizing images, and various software platforms support this step. Feature extraction quantifies characteristics of grey levels within the region of interest (ROI) or volume of interest (VOI). Dimension reduction and feature selection are crucial for generating valid and generalizable results, and several methods are available. Despite its potential, radiomics faces challenges such as lack of standardization, insufficient reporting, and limited open-source data. Recent guidelines aim to improve the quality of future studies, emphasizing the importance of transparency. Future improvements should focus on integrating radiomics into clinical workflows and addressing legal and regulatory issues.Radiomics is a quantitative approach to medical imaging that enhances clinical data through advanced mathematical analysis. This review aims to provide a practical guide to radiomics analysis and discuss its current limitations. The workflow includes image segmentation, image processing, feature extraction, and dimension reduction. Image segmentation can be manual, semi-automated, or fully automated, with deep learning algorithms being the most promising for reducing observer bias. Image processing involves homogenizing images, and various software platforms support this step. Feature extraction quantifies characteristics of grey levels within the region of interest (ROI) or volume of interest (VOI). Dimension reduction and feature selection are crucial for generating valid and generalizable results, and several methods are available. Despite its potential, radiomics faces challenges such as lack of standardization, insufficient reporting, and limited open-source data. Recent guidelines aim to improve the quality of future studies, emphasizing the importance of transparency. Future improvements should focus on integrating radiomics into clinical workflows and addressing legal and regulatory issues.