Résumé
This chapter provides an overview of AI in nuclear medicine and hybrid imaging applications. It refers to nuclear medicine with its widest definition, as the medical specialty that uses radioactive tracers (radiopharmaceuticals) to assess bodily functions and to diagnose and treat disease. Hybrid imaging refers to the combination of any imaging modality that uses radioactive tracers, along with any other imaging modality, often one that focuses on anatomy, for simultaneous or sequential imaging such as with computed tomography (CT) in positron emission tomography (PET)/CT, single photon emission computed tomography (SPECT)/CT, or magnetic resonance imaging (MRI) in PET/MR. This chapter considers the use of AI in nuclear medicine to provide novel solutions for both imaging-related tasks such as image acquisition, reconstruction, processing, segmentation, and analysis, and for other related tasks that are important for patient care and the efficient organisation of a department. Finally, AI can be applied in the construction of models to derive diagnosis-specific metrics to aid the clinical decision making and to pursue further optimisation of the diagnostic or therapeutic process, such as automated feature (lesion) detection or predictive internal radiation dosimetry for personalised therapy.