Lymphoma, encompassing a wide spectrum of immune system malignancies, presents significant complexities in its early detection, management, and prognosis assessment since it can mimic post-infectious/inflammatory diseases. The heterogeneous nature of lymphoma makes it challenging to definitively pinpoint valuable biomarkers for predicting tumor biology and selecting the most effective treatment strategies. Although molecular imaging modalities, such as positron emission tomography/computed tomography (PET/CT), specifically ¹⁸F-FDG PET/CT, hold significant importance in the diagnosis of lymphoma, prognostication, and assessment of treatment response, they still face significant challenges. Over the past few years, radiomics and artificial intelligence (AI) have surfaced as valuable tools for detecting subtle features within medical images that may not be easily discerned by visual assessment. The rapid expansion of AI and its application in medicine/radiomics is opening up new opportunities in the nuclear medicine field. Radiomics and AI capabilities seem to hold promise across various clinical scenarios related to lymphoma. Nevertheless, the need for more extensive prospective trials is evident to substantiate their reliability and standardize their applications. This review aims to provide a comprehensive perspective on the current literature regarding the application of AI and radiomics applied/extracted on/from ¹⁸F-FDG PET/CT in the management of lymphoma patients.

Objective: Develop and evaluate a patient-level framework for discriminating Hodgkin lymphoma (HL) from non-Hodgkin lymphoma (NHL) on baseline ¹⁸ F-FDG PET by aggregating radiomic descriptors from a variable number of involved lymph nodes in a multi-center setting. Approach: Each patient was modeled as an unordered set of lesion-level PET radiomic feature vectors. PET images were converted to standardized uptake values (SUV), resampled to a uniform voxel spacing of 2 × 2 × 2 mm3, and radiomic features were extracted using PyRadiomics from the original SUV images with a fixed bin width of 0.25 SUV units, following definitions consistent with the Image Biomarker Standardisation Initiative (IBSI). A total of 107 first-order, texture, and shape features were extracted per lesion and optionally augmented with demographic variables and normalized node center-of-mass coordinates after rigid registration to a common reference space. We compared statistical pooled tabular baselines with learnable set-based aggregation models, including Transformer, Deep Sets, multiple instance learning, Set Transformer, and a graph-based model. Models were trained using five-fold cross-validation on Center 1 (151 patients; 85 HL, 66 NHL) and evaluated on an independent external Center 2 cohort (80 patients; 36 HL, 44 NHL) under direct transfer and unsupervised test-time adaptation (TTA). Main results: Combining radiomics with demographic and spatial features consistently improved discrimination. On Center 1, the best-performing deep aggregation models achieved ROC-AUC (mean ± std) up to 0.91 ± 0.05 and accuracy up to 0.84 ± 0.07. External evaluation on Center 2 revealed a measurable domain shift, with reduced performance under direct transfer. Unsupervised TTA, particularly TENT, improved cross-center generalization for deep aggregation models; for example, the Transformer improved from ROC-AUC 0.81 ± 0.05 and F1-score 0.60 ± 0.23 to ROC-AUC 0.87 ± 0.01 and F1-score 0.75 ± 0.01. Feature attribution analysis indicated that both demographic and radiomic descriptors contributed to the predictions. Significance: These results show that multi-nodal PET radiomics combined with demographic and spatial dissemination cues is a promising strategy for patient-level HL versus NHL prediction. The findings also highlight the importance of robustness considerations in multi-center PET radiomics and suggest that test-time adaptation may help mitigate cross-center variability.