The hallmarks of cancer were introduced by Hanahan and Weinberg as a conceptual organizing framework to distil the complexity of tumours. This concept of cancer hallmarks has become an enduring theme in cancer research. Moreover, an increasing number of therapeutic strategies are being aimed at targeting these hallmarks. However, translating them into the clinic requires technologies to monitor their effectiveness and biomarkers that can stratify patients for the choice of specific therapies. Tumour heterogeneity and the ability of tumour cells to rapidly mutate and develop evasion strategies makes the development of non-invasive imaging capabilities to interrogate these hallmarks as biomarkers and monitor them longitudinally and quantitatively particularly important. This Review presents a holistic discussion of non-invasive diagnostic imaging capabilities related to the hallmarks of cancer; some hallmarks can be assessed with imaging probes that directly target biomolecules, whereas others can be interrogated indirectly by imaging pathophysiological processes. Additionally, visualizing the hallmarks of cancer can be addressed with artificial intelligence-assisted, multiparametric image analysis (for example, radiomics, radiogenomics and deep learning). The approaches discussed have been evaluated in a translational context, and some of them already have a substantial role in clinical practice, for example, to guide treatment strategies, including surgical resections, radiotherapy and molecularly targeted chemo-, immuno- and radiopharmaceutical therapies.