Prognostic value of genetic alterations and 18F-FDG PET/CT imaging features in diffuse large B cell lymphoma.
Up to one-third of patients with diffuse large B-cell lymphoma (DLBCL) do not respond adequately to standard first-line R-CHOP therapy, making early identification of high-risk patients critical for exploring alternative treatment strategies.
This study investigated whether information already available at diagnosis—18F-FDG PET/CT imaging, clinical variables and genomic alterations—could be integrated to predict complete response to first-line treatment. Importantly, all lesions were analyzed together to capture whole-body tumor burden and disease dissemination, rather than characterizing individual lesions in isolation.
The combined model integrating clinical, radiomic and genomic features achieved the best predictive performance, with an AUC of 0.904, 90% balanced accuracy, 100% sensitivity and 80% specificity. Adding genomic information improved prediction compared with models based on clinical and imaging data alone.
Among genomic alterations, BCL6 amplification emerged as the strongest predictor, being associated with a lower probability of response. Meanwhile, radiomic features reflecting lesion distribution and metabolic heterogeneity provided predictive information beyond conventional PET parameters such as SUVmax, metabolic tumor volume and total lesion glycolysis.
The study highlights the potential of multimodal precision oncology, combining molecular profiling with quantitative information extracted from routine PET/CT to improve early treatment-response prediction in DLBCL and support more personalized therapeutic strategies.
https://www.mdpi.com/2072-6694/15/16/4163
Ferrer-Lores B, Lozano J, Fuster-Matanzo A, Mayorga-Ruiz I, Moreno-Ruiz P, Bellvís F, Teruel AB, Saus A, Ortiz A, Villamón-Ribate E, Serrano-Alcalá A, Piñana JL, Sopena P, Dosdá R, Solano C, Alberich-Bayarri Á, Terol MJ. Prognostic value of genetic alterations and 18F-FDG PET/CT imaging features in diffuse large B cell lymphoma. Am J Cancer Res. 2023 Feb 15;13(2):509-525