Radiomics is the extraction of multidimensional imaging features, which when correlated with genomics, is termed radiogenomics. However, radiogenomic biological validation is not sufficiently described in the literature. We seek to establish causality between differential gene expression status and MRI-extracted radiomic-features in glioblastoma. Radiogenomic predictions and validation were done using the Cancer Genome Atlas and Repository of Molecular Brain Neoplasia Data glioblastoma patients ( = 93) and orthotopic xenografts (OX; = 40). Tumor phenotypes were segmented, and radiomic-features extracted using the developed radiome-sequencing pipeline. Patients and animals were dichotomized on the basis of Periostin ( expression levels. RNA and protein levels confirmed RNAi-mediated knockdown in OX. Total RNA of tumor cells isolated from mouse brains (knockdown and control) was used for microarray-based expression profiling. Radiomic-features were utilized to predict expression status in patient, mouse, and interspecies. Our robust pipeline consists of segmentation, radiomic-feature extraction, feature normalization/selection, and predictive modeling. The combination of skull stripping, brain-tissue focused normalization, and patient-specific normalization are unique to this study, providing comparable cross-platform, cross-institution radiomic features. expression status was not associated with qualitative or volumetric MRI parameters. Radiomic features significantly predicted expression status in patients (AUC: 76.56%; sensitivity/specificity: 73.91/78.26%) and OX (AUC: 92.26%; sensitivity/specificity: 92.86%/91.67%). Furthermore, radiomic features in OX were significantly associated with patients with similar expression levels (AUC: 93.36%; sensitivity/specificity: 82.61%/95.74%; = 02.021E-15). We determined causality between radiomic texture features and expression levels in a preclinical model with clinical validation. Our biologically validated radiomic pipeline also showed the potential application for human-mouse matched coclinical trials.

Background Recurrent pediatric medulloblastoma and ependymoma have a grim prognosis. We report a first-in-human, phase I study of intraventricular infusions of ex vivo expanded autologous natural killer (NK) cells in these tumors, with correlative studies. Methods Twelve patients were enrolled, 9 received protocol therapy up to 3 infusions weekly, in escalating doses from 3 × 106 to 3 × 108 NK cells/m2/infusion, for up to 3 cycles. Cerebrospinal fluid (CSF) was obtained for cellular profile, persistence, and phenotypic analysis of NK cells. Radiomic characterization on pretreatment MRI scans was performed in 7 patients, to develop a non-invasive imaging-based signature. Results Primary objectives of NK cell harvest, expansion, release, and safety of 112 intraventricular infusions of NK cells were achieved in all 9 patients. There were no dose-limiting toxicities. All patients showed progressive disease (PD), except 1 patient showed stable disease for one month at end of study follow-up. Another patient had transient radiographic response of the intraventricular tumor after 5 infusions of NK cell before progressing to PD. At higher dose levels, NK cells increased in the CSF during treatment with repetitive infusions (mean 11.6-fold). Frequent infusions of NK cells resulted in CSF pleocytosis. Radiomic signatures were profiled in 7 patients, evaluating ability to predict upfront radiographic changes, although they did not attain statistical significance. Conclusions This study demonstrated feasibility of production and safety of intraventricular infusions of autologous NK cells. These findings support further investigation of locoregional NK cell infusions in children with brain malignancies.

e15623 Background: The utilization of computed tomography (CT) has virtually replaced the need for tissue diagnosis in hepatocellular carcinoma (HCC). Imaging features (e.g. size, shape and vascularity) have been associated with patient survival. However, the full potential of CT in HCC diagnosis may not be reached, as high-throughput computing allows for extraction of quantitative features that are not part of radiologists’ lexicon. The purpose of this study was to investigate the ability of radiomic analysis to successfully identify specific doxorubicin chemoresistant genes on CT images of treatment-naïve hepatocellular carcinoma (HCC). Methods: We identified 27 treatment-naïve patients with a single HCC tumor from The Cancer Genome Atlas (TCGA) whom had gene expression profiles. Baseline CT images were obtained from The Cancer Imaging Archive (TCIA). 3D Slicer software was used for manual tumor segmentation and final segmented images were reviewed by a board-certified radiologist. Following tumor segmentation, texture analysis was performed on MATLAB environment. A total of 310 rotation invariant texture features, which measure tumor heterogeneity, were obtained (first-order histogram and grey level co-occurrence matrix). The mRMR method was used to select the most relevant radiomic features. ROC analysis and LOOCV were used to assess the performance of five specific genes known to confer doxorubicin chemoresistance (TP53, TOP2A, CTNNB1, CDKN2A and AKT1). Results: Radiomic analysis identified TP53 (AUC = 86.61%, Specificity = 92.31%, Sensitivity = 92.9%), TOP2A (AUC = 78.0%, Specificity = 69%, Sensitivity = 85.7%), CTNNB1 (AUC = 86.8%, Specificity = 92.3%, Sensitivity = 85.7%), CDKN2A (AUC = 76.9%, Specificity = 76.9%, Sensitivity = 78.6%) and AKT1 (AUC = 72.5%, Specificity = 69.2%, Sensitivity = 85.7%) in treatment-naïve HCC CT studies. Conclusions: The identification of specific genes that confer chemoresistance to doxorubicin can be reliably ascertained via the use of radiomic analysis. This study may help tailor future treatment paradigms via the ability to categorize HCC tumors on genetic level and identify tumors which may not have a favorable response to doxorubicin based therapies.

2015 Background: Treatment-related imaging changes are often difficult to distinguish from true tumor progression. Treatment-related changes or pseudoprogression (PsP) subsequently subside or stabilize without any further treatment, whereas progressive tumor requires a more aggressive approach in patient management. Pseudoprogression can mimic true progression radiographically and may potentially alter the physician’s judgment about the residual disease. Hence, it can predispose a patient to overtreatment or be categorized as a non-responder and exclude him from the clinical trials. This study aims at assessing the potential of radiomics to discriminate PsP from progressive disease (PD) in glioblastoma (GBM) patients. Methods: We retrospectively evaluated 304 GBM patients with new or increased enhancement on conventional MRI after treatment, of which it was uncertain for PsP versus PD. 149 patients had the histopathological evidence of PD and 27 of PsP. Remaining 128 patients were categorized into PD and PsP based on RANO criteria performed by a board-certified radiologist. Volumetrics using 3D slicer 4.3.1 and radiomics texture analysis were performed of the enhancing lesion(s) in question. Results: Using the MRMR feature selection method, we identified 100 significant features that were used to build a SVM model. Five texture features (E, CS, SA, MP, CP) were found to be most predictive of pseudoprogression. On Leave One Out Cross-Validation (LOOCV), sensitivity, specificity and accuracy were 97%, 72%, and 90%, respectively. Conclusions: 3D radiomic texture features of conventional MRI successfully discriminated pseudoprogression from true progression in a large cohort of GBM patients.

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.