M. G. Argenziano

This paper develops BioNet, a biologically-informed deep learning model, to predict intratumoral heterogeneity in post-treatment glioblastoma using MRI and biopsy data, showing improved performance over existing methods.

The paper identifies a metabolic vulnerability in specific glioma cell states that can be targeted with GPX4 inhibitors to induce ferroptosis.

This study shows 5-ALA labeling is not specific to transformed glioma cells but can label untransformed cells directly or via PpIX from surrounding tumor cells.