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.
CHENG Ran, HU Jiajia, LI Biao. Advances in the application of 18F-FDG PET/CT radiomics for diagnosis, treatment and prognosis prediction of lymphoma. Journal of Shanghai Jiao Tong University (Medical Science)[J], 2023, 43(6): 781-787 doi:10.3969/j.issn.1674-8115.2023.06.016
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,根据病理检查是否可见里-施细胞(Reed-Sternberg cell)主要分为霍奇金淋巴瘤(Hodgkin lymphoma,HL)与非霍奇金淋巴瘤(non-Hodgkin lymphoma,NHL)两大类。据统计,2020年淋巴瘤约占全球新发癌症病例和新增癌症死亡人数的3.2%和2.8%,其中NHL居新发癌症病例数第13位[1],我国NHL发病率呈逐年增加趋势[2-3]。根据免疫表型、分子遗传学特征等,HL和NHL又可进一步细分为多种亚型,各亚型间临床特点存在很大差异。NHL病理类型较HL更复杂,易发生淋巴结外侵犯、复发和亚型转化,预后更差,其亚型弥漫大B细胞淋巴瘤(diffuse large B-cell lymphoma,DLBCL)患者的5年生存率仅为64%[3]。因此,寻找无创、高效的方法辅助诊断和全面评估病灶变化趋势,是展开医学影像研究和完善诊治方法的重点之一。
CHENG Ran completed the literature collection and drafted the review. HU Jiajia and LI Biao were in charge of revision of the manuscript. All the authors have read the last version of paper and consented for submission.
利益冲突声明
所有作者声明不存在利益冲突。
COMPETING INTERESTS
All authors disclose no relevant conflict of interests.
SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-249.
LIU W P, LIU J M, SONG Y Q, et al. Burden of lymphoma in China, 1990—2019: an analysis of the global burden of diseases, injuries, and risk factors study 2019[J]. Aging, 2022, 14(7): 3175-3190.
CHESON B D, FISHER R I, BARRINGTON S F, et al. Recommendations for initial evaluation, staging, and response assessment of Hodgkin and non-Hodgkin lymphoma: the Lugano classification[J]. J Clin Oncol, 2014, 32(27): 3059-3068.
BARRINGTON S F, KLUGE R. FDG PET for therapy monitoring in Hodgkin and non-Hodgkin lymphomas[J]. Eur J Nucl Med Mol Imaging, 2017, 44(Suppl 1): S97-S110.
CHESON B D, MEIGNAN M. Current role of functional imaging in the management of lymphoma[J]. Curr Oncol Rep, 2021, 23(12): 144.
JIANG H, LI A, JI Z Y, et al. Role of radiomics-based baseline PET/CT imaging in lymphoma: diagnosis, prognosis, and response assessment[J]. Mol Imaging Biol, 2022, 24(4): 537-549.
CASALI M, LAURI C, ALTINI C, et al. State of the art of 18F-FDG PET/CT application in inflammation and infection: a guide for image acquisition and interpretation[J]. Clin Transl Imaging, 2021, 9(4): 299-339.
VAN TIMMEREN J E, CESTER D, TANADINI-LANG S, et al. Radiomics in medical imaging-"how-to" guide and critical reflection[J]. Insights Imaging, 2020, 11(1): 91.
VISVIKIS D, CHEZE LE REST C, JAOUEN V, et al. Artificial intelligence, machine (deep) learning and radio(geno)mics: definitions and nuclear medicine imaging applications[J]. Eur J Nucl Med Mol Imaging, 2019, 46(13): 2630-2637.
DE JESUS F M, YIN Y, MANTZOROU-KYRIAKI E, et al. Machine learning in the differentiation of follicular lymphoma from diffuse large B-cell lymphoma with radiomic [18F]FDG PET/CT features[J]. Eur J Nucl Med Mol Imaging, 2022, 49(5): 1535-1543.
AIDE N, TALBOT M, FRUCHART C, et al. Diagnostic and prognostic value of baseline FDG PET/CT skeletal textural features in diffuse large B cell lymphoma[J]. Eur J Nucl Med Mol Imaging, 2018, 45(5): 699-711.
MAYERHOEFER M E, RIEDL C C, KUMAR A, et al. [18F]FDG-PET/CT radiomics for prediction of bone marrow involvement in mantle cell lymphoma: a retrospective study in 97 patients[J]. Cancers, 2020, 12(5): 1138.
KONG Z R, JIANG C D, ZHU R Z, et al. 18F-FDG-PET-based radiomics features to distinguish primary central nervous system lymphoma from glioblastoma[J]. Neuroimage Clin, 2019, 23: 101912.
OU X J, ZHANG J, WANG J, et al. Radiomics based on 18F-FDG PET/CT could differentiate breast carcinoma from breast lymphoma using machine-learning approach: a preliminary study[J]. Cancer Med, 2020, 9(2): 496-506.
ZHU S, XU H, SHEN C Y, et al. Differential diagnostic ability of 18F-FDG PET/CT radiomics features between renal cell carcinoma and renal lymphoma[J]. Q J Nucl Med Mol Imaging, 2021, 65(1): 72-78.
SIBILLE L, SEIFERT R, AVRAMOVIC N, et al. 18F-FDG PET/CT uptake classification in lymphoma and lung cancer by using deep convolutional neural networks[J]. Radiology, 2020, 294(2): 445-452.
LOVINFOSSE P, FERREIRA M, WITHOFS N, et al. Distinction of lymphoma from sarcoidosis on 18F-FDG PET/CT: evaluation of radiomics-feature-guided machine learning versus human reader performance[J]. J Nucl Med, 2022, 63(12): 1933-1940.
FROOD R, CLARK M, BURTON C, et al. Utility of pre-treatment FDG PET/CT-derived machine learning models for outcome prediction in classical Hodgkin lymphoma[J]. Eur Radiol, 2022, 32(10): 7237-7247.
AKHTARI M, MILGROM S A, PINNIX C C, et al. Reclassifying patients with early-stage Hodgkin lymphoma based on functional radiographic markers at presentation[J]. Blood, 2018, 131(1): 84-94.
LUE K H, WU Y F, LIU S H, et al. Prognostic value of pretreatment radiomic features of 18F-FDG PET in patients with Hodgkin lymphoma[J]. Clin Nucl Med, 2019, 44(10): e559-e565.
MAYERHOEFER M E, RIEDL C C, KUMAR A, et al. Radiomic features of glucose metabolism enable prediction of outcome in mantle cell lymphoma[J]. Eur J Nucl Med Mol Imaging, 2019, 46(13): 2760-2769.
LISSON C S, LISSON C G, MEZGER M F, et al. Deep neural networks and machine learning radiomics modelling for prediction of relapse in mantle cell lymphoma[J]. Cancers, 2022, 14(8): 2008.
WANG H X, ZHAO S N, LI L, et al. Development and validation of an 18F-FDG PET radiomic model for prognosis prediction in patients with nasal-type extranodal natural killer/T cell lymphoma[J]. Eur Radiol, 2020, 30(10): 5578-5587.
PARVEZ A, TAU N, HUSSEY D, et al. 18F-FDG PET/CT metabolic tumor parameters and radiomics features in aggressive non-Hodgkin's lymphoma as predictors of treatment outcome and survival[J]. Ann Nucl Med, 2018, 32(6): 410-416.
AIDE N, FRUCHART C, NGANOA C, et al. Baseline 18F-FDG PET radiomic features as predictors of 2-year event-free survival in diffuse large B cell lymphomas treated with immunochemotherapy[J]. Eur Radiol, 2020, 30(8): 4623-4632.
JIANG C, LI A, TENG Y, et al. Optimal PET-based radiomic signature construction based on the cross-combination method for predicting the survival of patients with diffuse large B-cell lymphoma[J]. Eur J Nucl Med Mol Imaging, 2022, 49(8): 2902-2916.
JIANG C, HUANG X J, LI A, et al. Radiomics signature from [18F]FDG PET images for prognosis predication of primary gastrointestinal diffuse large B cell lymphoma[J]. Eur Radiol, 2022, 32(8): 5730-5741.
EERTINK J J, VAN DE BRUG T, WIEGERS S E, et al. 18F-FDG PET baseline radiomics features improve the prediction of treatment outcome in diffuse large B-cell lymphoma[J]. Eur J Nucl Med Mol Imaging, 2022, 49(3): 932-942.
FROOD R, CLARK M, BURTON C, et al. Discovery of pre-treatment FDG PET/CT-derived radiomics-based models for predicting outcome in diffuse large B-cell lymphoma[J]. Cancers, 2022, 14(7): 1711.
ZHANG X H, CHEN L, JIANG H, et al. A novel analytic approach for outcome prediction in diffuse large B-cell lymphoma by [18F]FDG PET/CT[J]. Eur J Nucl Med Mol Imaging, 2022, 49(4): 1298-1310.
COTTEREAU A S, NIOCHE C, DIRAND A S, et al. 18F-FDG PET dissemination features in diffuse large B-cell lymphoma are predictive of outcome[J]. J Nucl Med, 2020, 61(1): 40-45.
EERTINK J J, ZWEZERIJNEN G J C, CYSOUW M C F, et al. Comparing lesion and feature selections to predict progression in newly diagnosed DLBCL patients with FDG PET/CT radiomics features[J]. Eur J Nucl Med Mol Imaging, 2022, 49(13): 4642-4651.
JIMENEZ J E, DAI D, XU G F, et al. Lesion-based radiomics signature in pretherapy 18F-FDG PET predicts treatment response to ibrutinib in lymphoma[J]. Clin Nucl Med, 2022, 47(3): 209-218.
HU X B, GUO R, CHEN J N, et al. Coarse-to-fine adversarial networks and zone-based uncertainty analysis for NK/T-cell lymphoma segmentation in CT/PET images[J]. IEEE J Biomed Health Inform, 2020, 24(9): 2599-2608.
GUO R, HU X B, SONG H M, et al. Weakly supervised deep learning for determining the prognostic value of 18F-FDG PET/CT in extranodal natural killer/T cell lymphoma, nasal type[J]. Eur J Nucl Med Mol Imaging, 2021, 48(10): 3151-3161.