Spatial topology on baseline PET/CT improves risk stratification in disseminated diffuse large B-cell lymphoma: a multicenter study

To evaluate whether spatial topology features (STFs) from baseline 18 F-FDG PET/CT provide prognostic value beyond conventional burden and dissemination metrics in disseminated diffuse large B-cell lymphoma (DLBCL). This multicenter study included 243 patients (training, n = 161; validation, n = 82) with de novo DLBCL (≥ 4 lesions). An AI-assisted, human-in-the-loop pipeline was used to automatically detect lesions and construct 3D spatial networks. Six hierarchical models predicted 2-year progression-free survival, comparing a standard burden model (M3), a topology model (M4), and a fusion model (M5). Performance was assessed via AUC, Brier score, and calibration slope. Clinical utility was analyzed using Decision Curve Analysis (DCA), and biological correlations were tested against molecular subtypes. In the external validation cohort, the clinical baseline model (M0) showed limited efficacy (AUC 0.620). M4 showed similar discrimination to M3 (AUC 0.819 vs. 0.828; p = 0.68), but better specificity (76.4% vs. 67.3%). Integrating topological architecture with volumetric metrics, the fusion model (M5) significantly outperformed M3 (AUC 0.871; p = 0.032) and improved calibration (slope 0.96 vs. 0.65), providing more reliable probability estimates than purely volume-based predictions. A high LCI correlated with the non-GCB subtype ( p < 0.001) and double-expressor status ( p = 0.017). In disseminated DLBCL, spatial topology features function as macroscopic imaging phenotypes that capture internal tumor architecture distinct from absolute volumetric burden. Integrating this spatial dimension improved non-invasive risk stratification, while high LCI correlated with aggressive molecular phenotypes. Not applicable.