Badie, Behnam

Abstract BACKGROUND Conventional magnetic resonance imaging (MR) guides patient care in GBM. However, there is mounting awareness that MR enhancement is non-specific reflecting either tumor progression or non-tumoral inflammatory changes. Histological evaluation of GBM is held as the gold standard for disease assessment. However, the invasiveness of this methodology and the sample sparsity limit its usefulness. Methods to infer histological underpinnings of MRI are needed to improve clinical care. METHODS A transfer learning mixed effects model based on T1Gd and FLAIR MR voxel based image features trained and cross-validated to predict FPKM values of CD68, CASP3, CD8A and IL13RA2. Training data included RNAseq from 38 image-localized biopsies from 15 newly-diagnosed GBM patients. These models were then applied to two independent patients, chosen based on therapy and the quality of image registration, at three different time points, just prior to receiving IL13RA2 targeted CAR-T therapy for rGBM, after 2 cycles and after 4 cycles, resulting in a voxel-based prediction of the relative expression levels of these genes. RESULTS Cross-validation of the proposed machine learning models demonstrated a Pearson Correlation coefficient between predicted and observed FPKM values of 0.89 (CD68), 0.92 (CASP3), 0.93 (CD8A), and 0.88 (IL13RA2). When the models were applied to the two CAR-T patients, CD68-modeled expression levels were seen to increase throughout therapy for one patient, while remaining stable for the other. Survival from first CAR-T infusion was, respectively, 412 and 83 days suggesting that the increased CD68 was indicative of therapeutic effectivity. Further, the spatial activity predictions were consistent with expected therapeutic action as the correlation coefficient between CASP3 and the product of IL13R2 and CD8A expression was 0.81, suggesting the T-cells targeting IL13RA2 were inducing cell death. CONCLUSIONS Preliminary results with our model highlights the potential of spatially resolved radiomic maps to provide insight into regional therapeutic effectivity.

Abstract INTRODUCTION Immunotherapy with engineered CAR T cells is a promising new therapy for glioblastoma, for which predictive and prognostic biomarkers are needed to inform effective intervention. Recently, our group analyzed standard-of-care (SOC) MRI images of long-term and short-term glioblastoma survivors and identified six intratumoral “habitats” of which “Habitat 6” was correlated with survival at diagnosis in high-grade glioma. Based on the MRI characteristics of “Habitat 6”, viz. high enhancement and high edema, we hypothesized that it could be a marker of tumor immune infiltrates. We are studying longitudinal changes in tumor “habitat” composition on MRIs of subjects with recurrent high-grade glioma treated with CAR T cells engineered to target IL13Ra2. METHODS MRI scans of the brain were acquired in 6 subjects at 3.0 T at baseline and various times before and after initiation of CAR T cell therapy. FLAIR, T1W and T1W-CE MRI images were registered to T2W images and six intratumoral “habitats” were computed as per our recently published methodology. The six habitats generated at the end of the tumor segmentation process were: “Habitat 1” (low FLAIR, low enhancement), “Habitat 2” (high FLAIR, low enhancement), “Habitat 3” (low FLAIR, medium enhancement), “Habitat 4” (high FLAIR, medium enhancement), “Habitat 5” (low FLAIR, high enhancement), and “Habitat 6” (high FLAIR, high enhancement). RESULTS Analysis of temporal changes in the six “habitats” shows an initial increase in both “Habitat 4” and “Habitat 6” following CAR T cell therapy initiation. Subjects with higher absolute volumes of “Habitat 6” at the baseline (pre-treatment) showed longer overall survival. Overall survival is a function of absolute “Habitat 6” volume at baseline, its direction of change immediately post-therapy, the duration of any increase in “Habitat 6” post-treatment, and the “Habitat 6” to “Habitat 4” ratio. Additional subjects are being evaluated to further understand these preliminary observations.