Radiomic Phenotype-Informed Patient-Level Aggregation of Multiple Lesions: Application to PET Prognostic Modeling in NET and DLBCL

Purpose: To develop and validate a multilesion hierarchical radiomic phenotyping and aggregation framework for positron emission tomography (PET) imaging that captures intertumor heterogeneity and improves prognostic modeling in metastatic cancers. Methods: This retrospective study included 81 neuroendocrine tumor (NET) patients imaged with 68Ga-DOTATATE or 68Ga-DOTATOC PET/CT and 76 diffuse large B-cell lymphoma (DLBCL) patients imaged with 18F-FDG PET/CT. Lesion-level radiomic features were extracted using PyRadiomics v3.0.1 and harmonized using ComBat. Unsupervised consensus clustering identified radiomic phenotypes, which were aggregated at four levels: body-level (B), phenotype-specific body-level (BP), organ-level (O), and phenotype-specific organ-level (OP). Nested cross-validation models predicted overall survival (OS), time to progression (TTP), and binary progression, comparing phenotype-agnostic and phenotype-informed aggregation, with and without clinical features, against single-lesion approaches and clinical baselines. Results: Phenotype discovery identified 4 NET and 8 DLBCL radiomic phenotypes, driven mainly by gray-level co-occurrence matrix and gray-level size-zone matrix texture features. Hierarchical aggregation yielded numerically favorable performance relative to single-lesion approaches across end points. B+BP was the performance-favorable representation for survival in both cohorts. Clinical+Aggregated models achieved the highest C-indices for NET OS (0.72 vs 0.65), NET TTP (0.67 vs 0.64), DLBCL OS (0.66 vs 0.62), and DLBCL TTP (0.66 vs 0.58) compared with clinical-only models. Clinical-only models were weakest for binary progression. For DLBCL progression, the richest Clinical+Aggregated representation (B+BP+O+OP) performed best (ROC-AUC = 0.77, MCC = 0.43), whereas NET progression was most stable with phenotype-agnostic body-level aggregation (ROC-AUC = 0.72, MCC = 0.34). Conclusion: Phenotype-informed aggregation of PET radiomics provides a structured approach for incorporating interlesion heterogeneity into patient-level prognostic modeling and showed promising performance relative to conventional single-lesion representations.