Alzheimer's disease(AD)is a common chronic neurodegenerative disorder.PET,a non-invasive molecular imaging technique,plays a significant role in diagnosing AD by revealing characteristic pathological changes.Meanwhile,radiomics technology can extract a vast amount of information that is difficult to recognize by the naked eye,and provides an objective and quantitative method for analyzing PET image features of AD patients.This article introduces the general steps of radiomics and common tools for PET image analysis applied in the assessment of AD.It also reviews the current research status of radiomics based on PET imaging in the diagnosis and prognosis prediction of AD,focusing on amyloid β,tau proteins and cerebral glucose metabolism.Furthermore,the article discusses future challenges in this field.