Immunotherapy, particularly immune checkpoint inhibitor therapy, has made remarkable advancements in the treatment of patients with cancer in the last decade. However, not all patients respond to immunotherapy, which is a therapeutic approach associated with high costs and adverse events. As such, there is an unmet need for identifying biomarkers that can accurately predict treatment response. The potential of currently identified biomarkers such as programmed cell death ligand 1 (PD-L1) and tumor mutational burden (TMB) is debated. Recently, noninvasive radiomics approaches have showed promise in predicting response to immunotherapy, further facilitating precision oncology. In this chapter, we establish a general understanding of the utility of radiomics in predicting immunotherapy response in patients with cancer, in a way that medical professionals with limited understanding of computer science can comprehend. We explore various cancers for which this novel approach has been applied and discuss the challenges that need to be addressed in future investigations.