Optimizing Workflows for Fast and Reliable Metabolic Tumor Volume Measurements in Diffuse Large B Cell Lymphoma

This pilot study aimed to determine interobserver reliability and ease of use of three workflows for measuring metabolic tumor volume (MTV) and total lesion glycolysis (TLG) in diffuse large B cell lymphoma (DLBCL). Twelve baseline [18F]FDG PET/CT scans from DLBCL patients with wide variation in number and size of involved organs and lymph nodes were selected from the international PETRA consortium database. Three observers analyzed scans using three workflows. Workflow A: user-defined selection of individual lesions followed by four automated segmentations (41%SUVmax, A50%SUVpeak, SUV≥2.5, SUV≥4.0). For each lesion, observers indicated their “preferred segmentation.” Individually selected lesions were summed to yield total MTV and TLG. Workflow B: fully automated preselection of [18F]FDG-avid structures (SUV≥4.0 and volume≥3ml), followed by removing non-tumor regions with single mouse clicks. Workflow C: preselected volumes based on Workflow B modified by manually adding lesions or removing physiological uptake, subsequently checked by experienced nuclear medicine physicians. Workflow C was performed 3 months later to avoid recall bias from the initial Workflow B analysis. Interobserver reliability was expressed as intraclass correlation coefficients (ICC). Highest interobserver reliability in Workflow A was found for SUV≥2.5 and SUV≥4.0 methods (ICCs for MTV 0.96 and 0.94, respectively). SUV≥4.0 and A50%Peak were most and SUV≥2.5 was the least preferred segmentation method. Workflow B had an excellent interobserver reliability (ICC = 1.00) for MTV and TLG. Workflow C reduced the ICC for MTV and TLG to 0.92 and 0.97, respectively. Mean workflow analysis time per scan was 29, 7, and 22 min for A, B, and C, respectively. Improved interobserver reliability and ease of use occurred using fully automated preselection (using SUV≥4.0 and volume≥3ml, Workflow B) compared with individual lesion selection by observers (Workflow A). Subsequent manual modification was necessary for some patients but reduced interobserver reliability which may need to be balanced against potential improvement on prognostic accuracy.