Radiomics is a method for extracting large amounts of quantitative image features from medical images, aiming to improve the analysis of tumour heterogeneity. This approach uses advanced feature analysis to provide more information than traditional methods, potentially enhancing treatment planning and monitoring. The field has evolved with innovations in medical imaging hardware, imaging agents, standardized protocols, and analysis techniques. These advancements allow for quantitative imaging, which requires automated and reproducible analysis methods to extract more information from image-based features. The Radiomics workflow involves acquiring high-quality, standardized images, segmenting the tumour region, extracting quantitative features such as intensity distribution, texture, shape, and spatial relationships, and then analyzing these features to predict treatment outcomes or gene expression. The hypothesis is that quantitative analysis of medical images can provide insights into genomic and proteomic patterns, potentially revealing prognostic information. Studies have shown that imaging features can correlate with biological processes, such as protein expression and tumour metabolism, and that these features may predict treatment response. Radiomics is linked to the concept of radio-genomics, which suggests that imaging features are related to gene signatures. Research indicates that tumours with greater genomic heterogeneity may have worse prognoses, and that imaging can capture this heterogeneity. Examples include studies showing that imaging features can predict outcomes in various cancers, such as ovarian and lung cancer. These findings support the Radiomics hypothesis that imaging features can provide valuable information for treatment decisions. The field requires further validation in multi-centric settings and in the laboratory to confirm the relationship between imaging features and gene expression. The QuIC-ConCePT consortium aims to experimentally confirm this hypothesis by studying more patients and tumour types. Overall, radiomics holds promise for improving the understanding and treatment of cancer by leveraging the potential of non-invasive imaging to capture tumour heterogeneity.Radiomics is a method for extracting large amounts of quantitative image features from medical images, aiming to improve the analysis of tumour heterogeneity. This approach uses advanced feature analysis to provide more information than traditional methods, potentially enhancing treatment planning and monitoring. The field has evolved with innovations in medical imaging hardware, imaging agents, standardized protocols, and analysis techniques. These advancements allow for quantitative imaging, which requires automated and reproducible analysis methods to extract more information from image-based features. The Radiomics workflow involves acquiring high-quality, standardized images, segmenting the tumour region, extracting quantitative features such as intensity distribution, texture, shape, and spatial relationships, and then analyzing these features to predict treatment outcomes or gene expression. The hypothesis is that quantitative analysis of medical images can provide insights into genomic and proteomic patterns, potentially revealing prognostic information. Studies have shown that imaging features can correlate with biological processes, such as protein expression and tumour metabolism, and that these features may predict treatment response. Radiomics is linked to the concept of radio-genomics, which suggests that imaging features are related to gene signatures. Research indicates that tumours with greater genomic heterogeneity may have worse prognoses, and that imaging can capture this heterogeneity. Examples include studies showing that imaging features can predict outcomes in various cancers, such as ovarian and lung cancer. These findings support the Radiomics hypothesis that imaging features can provide valuable information for treatment decisions. The field requires further validation in multi-centric settings and in the laboratory to confirm the relationship between imaging features and gene expression. The QuIC-ConCePT consortium aims to experimentally confirm this hypothesis by studying more patients and tumour types. Overall, radiomics holds promise for improving the understanding and treatment of cancer by leveraging the potential of non-invasive imaging to capture tumour heterogeneity.