MRI based radiomic signature to predict treatment response to intraventricular natural killer (NK) cell infusion therapy for recurrent/refractory pediatric brain tumors.

Abstract

e21511 Background: NK cell therapy is a novel immunotherapeutic strategy used in cancer therapy. We conducted first-in-human, loco-regional infusion of autologous ex-vivo expanded NK cell directly into the brain in children with recurrent medulloblastoma (MB) and ependymoma (EP). Radiomics is considered an emerging method to predict treatment response as well as evaluate prognosis and tumor milieu. This is the first study evaluating the ability of radiomics to predict response to intraventricular infusions of NK cell in children with recurrent/refractory posterior fossa malignant brain tumors. Methods: We evaluated 7 patients (5 males: 2 females; mean age 11.8 years) with refractory/recurrent MB or EP (MBs = 3, EPs = 4), who were enrolled on a Phase-1 trial (NCT02271711) and received 3 cycles of intraventricular NK cell infusions. Patients were categorized based on their clinical response into responders (N = 2) and non-responders (N = 5). After semiautomatic segmentation of the tumor, 3,660 radiomic features were extracted from the baseline (before treatment) MRI scan. The least absolute shrinkage and selection operator regression was used for feature selection, and the radiomics signature was built using the unsupervised anomaly detection algorithm. The performance of the radiomics model was assessed using leave-one-out cross-validation. Results: The radiomic signature/model was comprised of 6 radiomic features and demonstrated high discriminatory performance in predicting response to NK cell therapy with an area under the curve, sensitivity, and specificity of 100% ( P = 0.09486). In addition, patients clustered into responders and non-responders using unsupervised hierarchical clustering. Conclusions: To our knowledge, this is the first study to identify the ability of radiomics to predict those who will likely benefit from NK cell therapy. Though this small study did not attain statistical significance, the robust discriminatory results warrant larger prospective studies, evaluating radiomics as a potential tool to identify responders to NK cell therapy at diagnosis.