INTEGRATION OF RADIOMICS AND MACHINE LEARNING FOR PREDICTING GLIOMA PROGRESSION: A MULTIMODAL IMAGING AND COMPUTATIONAL APPROACH TO PRECISION NEURO-ONCOLOGY

Abstract

Gliomas represent one of the most aggressive and heterogeneous groups of primary brain tumors, characterized by unpredictable progression patterns and variable clinical outcomes. Accurate prediction of glioma progression remains a major challenge in neuro-oncology, limiting the effectiveness of personalized treatment strategies. Traditional diagnostic approaches, based on conventional imaging and histopathological evaluation, often fail to capture the complex spatial and temporal heterogeneity of tumor biology.