The Impact of Segmentation Method and Target Lesion Selection on Radiomic Analysis of 18F-FDG PET Images in Diffuse Large B-Cell Lymphoma

Abstract

Radiomic analysis of 18F[FDG] PET/CT images might identify predictive imaging biomarkers, however, the reproducibility of this quantitative approach might depend on the methodology adopted for image analysis. This retrospective study investigates the impact of PET segmentation method and the selection of different target lesions on the radiomic analysis of baseline 18F[FDG] PET/CT images in a population of newly diagnosed diffuse large B-cell lymphoma (DLBCL) patients. The whole tumor burden was segmented on PET images applying six methods: (1) 2.5 standardized uptake value (SUV) threshold; (2) 25% maximum SUV (SUVmax) threshold; (3) 42% SUVmax threshold; (4) 1.3∙liver uptake threshold; (5) intersection among 1, 2, 4; and (6) intersection among 1, 3, 4. For each method, total metabolic tumor volume (TMTV) and whole-body total lesion glycolysis (WTLG) were assessed, and their association with survival outcomes (progression-free survival PFS and overall survival OS) was investigated. Methods 1 and 2 provided stronger associations and were selected for the next steps. Radiomic analysis was then performed on two target lesions for each patient: the one with the highest SUV and the largest one. Fifty-three radiomic features were extracted, and radiomic scores to predict PFS and OS were obtained. Two proportional-hazard regression Cox models for PFS and OS were developed: (1) univariate radiomic models based on radiomic score; and (2) multivariable clinical–radiomic model including radiomic score and clinical/diagnostic parameters (IPI score, SUVmax, TMTV, WTLG, lesion volume). The models were created in the four scenarios obtained by varying the segmentation method and/or the target lesion; the models’ performances were compared (C-index). In all scenarios, the radiomic score was significantly associated with PFS and OS both at univariate and multivariable analysis (p < 0.001), in the latter case in association with the IPI score. When comparing the models’ performances in the four scenarios, the C-indexes agreed within the confidence interval. C-index ranges were 0.79–0.81 and 0.80–0.83 for PFS radiomic and clinical–radiomic models; 0.82–0.87 and 0.83–0.90 for OS radiomic and clinical–radiomic models. In conclusion, the selection of either between two PET segmentation methods and two target lesions for radiomic analysis did not significantly affect the performance of the prognostic models built on radiomic and clinical data of DLBCL patients. These results prompt further investigation of the proposed methodology on a validation dataset.

[18F]‐FDG PET radiomic model as prognostic biomarker in diffuse large B‐cell lymphoma

“…Notably, ANOVA did not identify significant influence, probably due to imaging procedure standardization in our center. In addition, to test and support the robustness of the methodology, a preliminary analysis was performed to select the most reliable PET segmentation method, including a sensitivity analysis to assess the differences in model performance when changing segmentation method or when considering different target lesions 22 . Since no significant difference was found among the tested methodologies, the results obtained with only one segmentation method and target lesion were included in this study.…”

“…Quantitative PET images analysis was performed with LifeX 6.32 package 21 . A pilot study was performed 22 comparing six different segmentation methods among those most widely used in the literature for lymphoma, 23 to select the most suitable method for the subsequent radiomic analysis. The main points of this study are summarized in the Supplementary Materials (Pilot study on Pet segmentation paragraph).…”

“…In addition, to test and support the robustness of the methodology, a preliminary analysis was performed to select the most reliable PET segmentation method, including a sensitivity analysis to assess the differences in model performance when changing segmentation method or when considering different target lesions. 22 Since no significant difference was found among the tested methodologies, the results obtained with only one segmentation method and target lesion were included in this study. The generalizability of the models needs to be confirmed with external validation on independent populations, also with the inclusion of novel parameters appearing promising for their prognostic role in recent studies.…”