Multifactorial Prognostic Models in Lymphoma: Integrating PET Imaging into Precision Medicine Approaches

Despite therapeutic advances, predicting patient prognosis remains difficult, as traditional indices like the International Prognostic Index (IPI) fail to capture the complexity of tumor biology and treatment response. Functional and molecular imaging, particularly 18F-FDG PET/CT, has transformed disease assessment by enabling quantification of tumor burden, metabolism, and therapeutic response. Quantitative PET-derived metrics such as metabolic tumor volume, total lesion glycolysis, and radiomic features provide valuable prognostic insights when integrated with clinical, histopathological, molecular, and genetic data. The application of AI-driven and machine-learning models facilitates the development of multifactorial prognostic frameworks, supporting precision prognostication and individualized treatment strategies. This research aims to advance and validate such integrative approaches across various lymphoma subtypes, ultimately improving patient management and therapeutic outcomes.This Research Topic aims to showcase the growing importance of PET/CT and advanced imaging metrics in modern prognostic modeling for lymphoma. It will promote the development of multidimensional tools that integrate clinical, radiomic, and molecular data to enhance outcome prediction. By exploring AI and machine learning approaches, it seeks to refine treatment response assessment and support personalized patient care. The initiative also encourages multicenter and translational research to validate integrative prognostic frameworks, while fostering close collaboration among nuclear medicine physicians, hematologists, medical physicists, and bioinformaticians to advance precision medicine in lymphoma management.This Research Topic welcomes a wide range of contributions focused on advancing prognostic and predictive modeling in lymphoma. Submissions may address the development and validation of multifactorial models, the integration of PET/CT parameters—such as SUV metrics, MTV, TLG, and radiomics—with molecular or genetic data, and the use of dynamic or interim PET imaging to monitor early treatment response. Studies employing AI, deep learning, or radiogenomic approaches to link imaging features with molecular alterations are particularly encouraged. Additional topics include comparative analyses of PET-based versus conventional indices, assessment of responses to immunotherapy and targeted therapies, and exploration of the methodological and ethical challenges in multimodal data integration. Topic editors: Luca Guerra, Stephane Chauvie, Stefano Luminari Source: https://www.frontiersin.org/research-topics/76015/multifactorial-prognostic-models-in-lymphoma-integrating-pet-imaging-into-precision-medicine-approaches