淋巴瘤是一种高度异质性的血液系统恶性肿瘤，全身各器官可受累，各亚型间临床特点存在很大差异。¹⁸F氟代脱氧葡萄糖（¹⁸F-fluorodeoxyglucose，¹⁸F-FDG）PET/CT是淋巴瘤临床诊断及治疗过程中重要的影像学检查方法，利于高侵袭性淋巴瘤的解剖学定位及代谢特征量化。该法通过比较治疗前后、病灶与血池的代谢变化从而系统评价疾病。但淋巴瘤异质性及¹⁸F-FDG PET/CT鉴别的局限性增加了医师的诊断难度，从而影响患者的临床治疗方案及预后。随着计算机硬件和图像分析技术的进步，基于提取病灶影像学特征进行分析诊断的影像组学技术应运而生。许多研究者投身于淋巴瘤¹⁸F-FDG PET/CT的影像组学研究，通过特征数据与相关临床数据结合建立模型，将图像信息、临床信息、病理及生存期等随访结果有效关联，提高了影像诊断的准确性和效率；同时根据模型预测预后和疗效，有望减少因医师经验差异导致的主观误差，辅助实现精准医疗。该文从诊断和鉴别诊断、预后预测和风险分级、药物疗效预测及影像组学分析算法优化等方面，对近年来¹⁸F-FDG PET/CT影像组学应用于淋巴瘤诊疗及预后评估的研究进展进行全面综述，以期为进一步研究机器学习、开发医学影像分析技术提供思路。

Lymphoma is a highly heterogeneous hematological malignancy that can affect multiple organs throughout the body, exhibiting significant clinical variations among its subtypes. ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET/CT plays a crucial role in the clinical diagnosis and treatment of lymphoma by facilitating anatomical localization and quantification of metabolic characteristics of highly aggressive lymphomas. This imaging examination method enables a comprehensive evaluation by comparing the metabolic changes before and after treatment, as well as the metabolic difference between lesions and blood pools. However, the heterogeneity of lymphoma, coupled with the limitations of ¹⁸F-FDG PET/CT in differentiation, poses challenges for physicians and adversely impacts the clinical treatment plan and prognosis of patients. With the advancement of computer hardware and image analysis technology, radiomics technology, based on the extraction of imaging features of lesions for analysis and diagnosis, has emerged. Numerous researchers have dedicated their efforts to exploring imageomics in lymphoma assessment by using ¹⁸F-FDG PET/CT. By integrating feature data with relevant clinical information, models have been developed to effectively correlate image information, clinical data, pathology, and survival outcomes, thereby enhancing the accuracy and efficiency of imaging diagnosis. Furthermore, the utilization of predictive models for prognosis and treatment efficacy has the potential to mitigate subjective errors arising from disparities in physician experience, thereby contributing to the realization of personalized medicine. This review intends to comprehensively summarize the research progress of ¹⁸F-FDG PET/CT radiomics in the diagnosis, treatment and evaluation of lymphoma in recent years, from the aspects of diagnosis and differential diagnosis, prognosis prediction and risk grading, drug efficacy prediction and radiomics analysis algorithm optimization, so as to provide insights for future research in machine learning and the development of medical imaging analysis techniques.