Assessment of early metabolic progression in melanoma patients under immunotherapy: an 18F-FDG PET/CT study

Background The usage of immune checkpoint inhibitors (ICIs) is the standard practice for the treatment of metastatic melanoma. However, a significant amount of patients show no response to immunotherapy, while issues on its reliable response interpretation exist. Aim of this study was to investigate the phenomenon of early disease progression in 2-deoxy-2-(F-18)fluoro-D-glucose (F-18-FDG) positron emission tomography/computed tomography (PET/CT) in melanoma patients treated with ICIs. Methods Thirty-one patients under ICIs serially monitored with F-18-FDG PET/CT were enrolled. All patients exhibited progressive metabolic disease (PMD) after two ICIs' cycles according to the European Organization for Research and Treatment of Cancer (EORTC) criteria, and were characterized as unconfirmed PMD (uPMD). They were further followed with at least one PET/CT for either confirmation of PMD (cPMD) or demonstration of pseudoprogression remission. Patients were also evaluated with the PET Response Evaluation Criteria for Immunotherapy (PERCIMT). Moreover, in an attempt to investigate immune activation, the spleen to liver ratios (SLRmean, SLRmax) of F-18-FDG uptake were measured. Results Median follow up was 69.7 months [64.6-NA]. According to EORTC, 26/31 patients with uPMD eventually showed cPMD (83.9%) and 5/31 patients showed pseudoprogression (16.1%). Patients with cPMD (n = 26) had a median OS of 10.9 months [8.5-NA], while those with pseudoprogression (n = 5) did not reach a median OS [40.9-NA]. Respectively, after application of PERCIMT, 2/5 patients of the pseudoprogression group were correctly classified as non-PMD, reducing the uPMD cohort to 29 patients; eventually, 26/29 patients demonstrated cPMD (89.7%) and 3/29 pseudoprogression (10.3%). One further patient with pseudoprogression exhibited transient, sarcoid-like, mediastinal/hilar lymphadenopathy, a known immune-related adverse event (irAE). Finally, patients eventually showing cPMD exhibited a significantly higher SLRmean than those showing pseudoprogression after two ICIs' cycles (p = 0.038). Conclusion PET/CT, performed already after administration of two ICIs' cycles, can identify the majority of non-responders in melanoma immunotherapy. In order to tackle however, the non-negligible phenomenon of pseudoprogression, another follow-up PET/CT, the usage of novel response criteria and vigilance over emergence of radiological irAEs are recommended. Moreover, the investigation of spleen glucose metabolism may offer further prognostic information in melanoma patients under ICIs.