<div>AbstractPurpose:<p>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.</p>Experimental Design:<p>Radiogenomic predictions and validation were done using the Cancer Genome Atlas and Repository of Molecular Brain Neoplasia Data glioblastoma patients (<i>n</i> = 93) and orthotopic xenografts (OX; <i>n</i> = 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 (<i>POSTN)</i> expression levels. RNA and protein levels confirmed RNAi-mediated <i>POSTN</i> 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 <i>POSTN</i> expression status in patient, mouse, and interspecies.</p>Results:<p>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. <i>POSTN</i> expression status was not associated with qualitative or volumetric MRI parameters. Radiomic features significantly predicted <i>POSTN</i> 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 <i>POSTN</i> expression levels (AUC: 93.36%; sensitivity/specificity: 82.61%/95.74%; <i>P</i> = 02.021E−15).</p>Conclusions:<p>We determined causality between radiomic texture features and <i>POSTN</i> 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.</p></div>
Abstract PURPOSE Multi-parametric MRI based radiomic signatures have highlighted the promise of artificial intelligence (AI) in neuro-oncology. However, inter-institution heterogeneity hinders generalization to data from unseen clinical institutions. To this end, we formulated the ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium for glioblastoma. Here, we seek non-invasive generalizable radiomic signatures from routine clinically-acquired MRI for prognostic stratification of glioblastoma patients. METHODS We identified a retrospective cohort of 606 patients with near/gross total tumor resection ( >90%), from 13 geographically-diverse institutions. All pre-operative structural MRI scans (T1,T1-Gd,T2,T2-FLAIR) were aligned to a common anatomical atlas. An automatic algorithm segmented the whole tumors (WTs) into 3 sub-compartments, i.e., enhancing (ET), necrotic core (NC), and peritumoral T2-FLAIR signal abnormality (ED). The combination of ET+NC defines the tumor core (TC). Quantitative radiomic features were extracted to generate our AI model to stratify patients into short- (< 14mts) and long-survivors ( >14mts). The model trained on 276 patients from a single institution was independently validated on 330 unseen patients from 12 left-out institutions, using the area-under-the-receiver-operating-characteristic-curve (AUC). RESULTS Each feature individually offered certain (limited but reproducible) value for identifying short-survivors: 1) TC closer to lateral ventricles (AUC=0.62); 2) larger ET/brain (AUC=0.61); 3) larger TC/brain (AUC=0.59); 4) larger WT/brain (AUC=0.55); 5) larger ET/WT (AUC=0.59); 6) smaller ED/WT (AUC=0.57); 7) larger ventricle deformations (AUC=0.6). Integrating all features and age, through a multivariate AI model, resulted in higher accuracy (AUC=0.7; 95% C.I.,0.64-0.77). CONCLUSION Prognostic stratification using basic radiomic features is highly reproducible across diverse institutions and patient populations. Multivariate integration yields relatively more accurate and generalizable radiomic signatures, across institutions. Our results offer promise for generalizable non-invasive in vivo signatures of survival prediction in patients with glioblastoma. Extracted features from clinically-acquired imaging, renders these signatures easier for clinical translation. Large-scale evaluation could contribute to improving patient management and treatment planning. *Indicates equal authorship.
Abstract Purpose: 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. Experimental Design: Radiogenomic predictions and validation were done using the Cancer Genome Atlas and Repository of Molecular Brain Neoplasia Data glioblastoma patients (n = 93) and orthotopic xenografts (OX; n = 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 (POSTN) expression levels. RNA and protein levels confirmed RNAi-mediated POSTN 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 POSTN expression status in patient, mouse, and interspecies. Results: 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. POSTN expression status was not associated with qualitative or volumetric MRI parameters. Radiomic features significantly predicted POSTN 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 POSTN expression levels (AUC: 93.36%; sensitivity/specificity: 82.61%/95.74%; P = 02.021E−15). Conclusions: We determined causality between radiomic texture features and POSTN 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.
Abstract Pseudoprogression (PsP) is a diagnostic clinical dilemma in cancer. In this study, we retrospectively analyse glioblastoma patients, and using their dynamic susceptibility contrast and dynamic contrast-enhanced perfusion MRI images we build a classifier using radiomic features obtained from both Ktrans and rCBV maps coupled with support vector machines. We achieve an accuracy of 90.82% (area under the curve (AUC) = 89.10%, sensitivity = 91.36%, 67 specificity = 88.24%, p = 0.017) in differentiating between pseudoprogression (PsP) and progressive disease (PD). The diagnostic performances of the models built using radiomic features from Ktrans and rCBV separately were equally high (Ktrans: AUC = 94%, 69 p = 0.012; rCBV: AUC = 89.8%, p = 0.004). Thus, this MR perfusion-based radiomic model demonstrates high accuracy, sensitivity and specificity in discriminating PsP from PD, thus provides a reliable alternative for noninvasive identification of PsP versus PD at the time of clinical/radiologic question. This study also illustrates the successful application of radiomic analysis as an advanced processing step on different MR perfusion maps.
Abstract PURPOSE Clinical care and outcome in Glioblastoma (GBM) remains challenging due to the tumor's invasive grwoth. To establish personalized treatment options in GBM, discovery of genetic mechanisms essential for the tumor's invasion is needed. We have previously described radiogenomic approaches to diagnose gene networks non invasively by analyzing genomic data from TCGA. The purpose of the current reseach is to identify a genetic network that drives GBM invasion and can be targeted specifically. METHOD AND MATERIALS Using Kaplan-Meier statistics, the data of the two independent databases TCGA and REMBRANDT were used to validate the genetic netowork's impact on clinical outcome. The genes’ staus was assessed in a panel of human glioma stem cells (GSCs) and conventional proneural, classical and mesenchymal GBM cell lines using RT-PCR. Differentiation potential (Tuj1+ve, S100A+ve, and GFAP+ve), self-renewal (limiting dilution assays), invasion (Boyden chamber) and proliferation (BrdU) were assessed. Gain (lentiviral vectors) and loss (SMARTchoice Inducible shRNA) of function experiments were performed. Orthotopic xenograft models (nude mice) were used to characterize the genes impact in vivo. Potential FDA approved therapeutics were identified using connectivity map. RESULTS Texture analysis based on radiogenomics significantly predicted the genes responsible for invasion of GBM in a non-invasive manner. Invasion in both, in vitro and in vivo was significantly decreased upun downregulation of this gene network. Transcriptome micro-array analysis showed that an upregulation of the described genes results in class switching from proneural to mesenchymal sub-types. Cmap derived therapeutics could significantly inhibit the gene network's activitiy and hence invasion. CONCLUSION The describend genes could be essential drivers of molecular subtypes and invasion in GBM. The therapeutics defined with cmap offer a targetted therapy to adress these key features of GBM pathogenesis. Noninvasive radiogenomics-based identification of tumor subgroups and potential treatment approaches can significantly contribute to personalized therapy. CLINICAL RELEVANCE/APPLICATION The described gene network seems to be key for GBM pathogenesis. Noninvasive, radiogenomics-based subgroup identification and specific novel treatment approaches can significanty contribution to personalized GBM therapy. Citation Format: Rivka R. Colen, Markus Luedi, Sanjay K. Singh, Islam Hassan, Joy Gumin, Erik P. Sulman, Frederick F. Lang, Pascal O. Zinn. Radiogenomics defines key genomic network driving GBM invasion. [abstract]. In: Proceedings of the 107th Annual Meeting of the American Association for Cancer Research; 2016 Apr 16-20; New Orleans, LA. Philadelphia (PA): AACR; Cancer Res 2016;76(14 Suppl):Abstract nr 1505.
