Usefulness of FDG-PET/CT-Based Radiomics for the Characterization and Genetic Orientation of Pheochromocytomas Before Surgery

International audienceSimple Summary: Around 40% of patients with pheochromocytomas (PHEO) carry a germline mutation. Early germline mutation identification is important for accurate treatment and follow-up in affected patients. The aim of our retrospective study was to assess the potential added value of FDG-PET/CT radiomics for the characterization of PHEO and their genetic orientation prior to surgery and genetic testing. We confirmed in an homogeneous population of 52 PHEO (49 patients) the usual avidity of these tumors for FDG (92%) and the impact of germline mutation on their phenotypic presentations with higher SUVmax observed in Cluster-1-related genes. Radiomics biomarkers provided valuable additional and independent information for discriminating genetically determined PHEO (Cluster-1 or Cluster-2-related genes) as well as sporadic forms. FDG-PET/CT is then useful for preoperative detection of PHEO, and when combined with texture features, provides evidences for a genetic predisposition. Abstract: Purpose: To assess the potential added value of FDG-PET/CT radiomics for the characterization of pheochromocytomas (PHEO) and their genetic orientation prior to surgery and genetic testing. Methods: This retrospective monocentric study, included 49 patients (52 tumors) that underwent both FDG-PET/CT and MIBG scan before surgery. A germline mutation was secondarily identified in 13 patients in one of the genes related to Cluster 1 (n = 4) or Cluster 2 (n = 9). No mutation was identified in 32 patients and 4 did not have genetic testing. Correlation between several PET-based biomarkers, including SUVmax, metabolic tumor volume (MTV), total lesion glycolysis (TLG) and textural features, and biochemical and genetic features were analyzed. Results: Sensitivity of FDG-PET/CT alone was 92%, and 98% when combined to MIBG. The SUVmax was significantly higher for mutated tumors classified in Cluster 1 than in Cluster 2 (p = 0.002) or for Cancers 2020, 12, 2424 2 of 15 tumors with no identified mutations (p = 0.04). MTV and TLG of the tumors with the most intense uptake discriminated mutated Cluster 2 from sporadic tumors, but not from Cluster 1 tumors. Textural features combined with MTV led to better differentiation between sporadic and mutated tumors (p < 0.05). Conclusion: FDG-PET/CT is useful for preoperative characterization of PHEO, and when combined with radiomics biomarkers, provides evidences for a genetic predisposition