Radiomic features predictive of response in hgg-targeting car-t therapy

Abstract SIGNIFICANCE Radiomics may improve precision medicine in CAR-T (Chimeric Antigen Receptor T Cell) therapy patient selection. BACKGROUND High-Grade Glioma (HGG) is a heterogenous primary CNS neoplasm with a high recurrence rate and poor outcomes. Many studies are exploring CAR T cells to combat HGG. Radiomic models have shown value in identifying biomarkers predictive of tumor genetics, response, and patient prognosis. In this study, we explore radiomic features derived from four clinical sequences and volumes of edema and enhancing tumor to predict treatment response to the first three doses of CAR-T therapy. METHODS In this IRB-approved phase 1 clinical trial (IRB 13384), patients underwent surgical resection of the tumor and received CAR-T cell therapy. Of the 82 patients accrued, 59 (20 females, median age = 49) completed three cycles of therapy and had 3T field strength MRI scans with minimal imaging artifacts. T1 weighted pre-contrast, T1 weighted post-contrast, T2 weighted, and T2 FLuid Attenuated Inversion Recovery sequences were used to generate 3D and 2D radiomics features. In total 28,541 radiomic features were generated per patient using the images prior to CAR-T administration. Each patient’s response to treatment after three cycles was determined to be either stable disease (29 patients) or progression. The radiomic feature set dimensionality was reduced using Maximum Relevance Minimum Redundancy. 10-fold cross-validation XGBoost was used to determine radiomic features predictive of treatment response with a randomized grid search for hyperparameter tuning. RESULTS Six radiomic features (four shape-based), had high SHapley Additive exPlanations (SHAP)-based importance feature predictive of RANO response with an AUC >0.73. CONCLUSION Despite the limited study size, such imaging-based radiomic models can serve as a potential basis for optimizing clinical trial design through more precise patient screening and providing potential predictive imaging biomarkers of whether a patient will respond to CAR-T cell therapy in HGGs.