Shivali Narang

Associating spatial diversity features of radiologically defined tumor habitats with epidermal growth factor receptor driver status and 12-month survival in glioblastoma: methods and preliminary investigation

Abstract. We analyzed the spatial diversity of tumor habitats, regions with distinctly different intensity characteristics of a tumor, using various measurements of habitat diversity within tumor regions. These features were then used for investigating the association with a 12-month survival status in glioblastoma (GBM) patients and for the identification of epidermal growth factor receptor (EGFR)-driven tumors. T1 postcontrast and T2 fluid attenuated inversion recovery images from 65 GBM patients were analyzed in this study. A total of 36 spatial diversity features were obtained based on pixel abundances within regions of interest. Performance in both the classification tasks was assessed using receiver operating characteristic (ROC) analysis. For association with 12-month overall survival, area under the ROC curve was 0.74 with confidence intervals [0.630 to 0.858]. The sensitivity and specificity at the optimal operating point (threshold=0.5) on the ROC were 0.59 and 0.75, respectively. For the identification of EGFR-driven tumors, the area under the ROC curve (AUC) was 0.85 with confidence intervals [0.750 to 0.945]. The sensitivity and specificity at the optimal operating point (threshold=0.166) on the ROC were 0.76 and 0.83, respectively. Our findings suggest that these spatial habitat diversity features are associated with these clinical characteristics and could be a useful prognostic tool for magnetic resonance imaging studies of patients with GBM.

Spatial habitat features derived from multiparametric magnetic resonance imaging data are associated with molecular subtype and 12-month survival status in glioblastoma multiforme

One of the most common and aggressive malignant brain tumors is Glioblastoma multiforme. Despite the multimodality treatment such as radiation therapy and chemotherapy (temozolomide: TMZ), the median survival rate of glioblastoma patient is less than 15 months. In this study, we investigated the association between measures of spatial diversity derived from spatial point pattern analysis of multiparametric magnetic resonance imaging (MRI) data with molecular status as well as 12-month survival in glioblastoma. We obtained 27 measures of spatial proximity (diversity) via spatial point pattern analysis of multiparametric T1 post-contrast and T2 fluid-attenuated inversion recovery MRI data. These measures were used to predict 12-month survival status (≤12 or >12 months) in 74 glioblastoma patients. Kaplan-Meier with receiver operating characteristic analyses was used to assess the relationship between derived spatial features and 12-month survival status as well as molecular subtype status in patients with glioblastoma. Kaplan-Meier survival analysis revealed that 14 spatial features were capable of stratifying overall survival in a statistically significant manner. For prediction of 12-month survival status based on these diversity indices, sensitivity and specificity were 0.86 and 0.64, respectively. The area under the receiver operating characteristic curve and the accuracy were 0.76 and 0.75, respectively. For prediction of molecular subtype status, proneural subtype shows highest accuracy of 0.93 among all molecular subtypes based on receiver operating characteristic analysis. We find that measures of spatial diversity from point pattern analysis of intensity habitats from T1 post-contrast and T2 fluid-attenuated inversion recovery images are associated with both tumor subtype status and 12-month survival status and may therefore be useful indicators of patient prognosis, in addition to providing potential guidance for molecularly-targeted therapies in Glioblastoma multiforme.

Identification of histological correlates of overall survival in lower grade gliomas using a bag-of-words paradigm: A preliminary analysis based on hematoxylin & eosin stained slides from the lower grade glioma cohort of the cancer genome Atlas

Background: Glioma, the most common primary brain neoplasm, describes a heterogeneous tumor of multiple histologic subtypes and cellular origins. At clinical presentation, gliomas are graded according to the World Health Organization guidelines (WHO), which reflect the malignant characteristics of the tumor based on histopathological and molecular features. Lower grade diffuse gliomas (LGGs) (WHO Grade II–III) have fewer malignant characteristics than high-grade gliomas (WHO Grade IV), and a better clinical prognosis, however, accurate discrimination of overall survival (OS) remains a challenge. In this study, we aimed to identify tissue-derived image features using a machine learning approach to predict OS in a mixed histology and grade cohort of lower grade glioma patients. To achieve this aim, we used H and E stained slides from the public LGG cohort of The Cancer Genome Atlas (TCGA) to create a machine learned dictionary of “image-derived visual words” associated with OS. We then evaluated the combined efficacy of using these visual words in predicting short versus long OS by training a generalized machine learning model. Finally, we mapped these predictive visual words back to molecular signaling cascades to infer potential drivers of the machine learned survival-associated phenotypes. Methods: We analyzed digitized histological sections downloaded from the LGG cohort of TCGA using a bag-of-words approach. This method identified a diverse set of histological patterns that were further correlated with OS, histology, and molecular signaling activity using Cox regression, analysis of variance, and Spearman correlation, respectively. A support vector machine (SVM) model was constructed to discriminate patients into short and long OS groups dichotomized at 24-month. Results: This method identified disease-relevant phenotypes associated with OS, some of which are correlated with disease-associated molecular pathways. From these image-derived phenotypes, a generalized SVM model which could discriminate 24-month OS (area under the curve, 0.76) was obtained. Conclusion: Here, we demonstrated one potential strategy to incorporate image features derived from H and E stained slides into predictive models of OS. In addition, we showed how these image-derived phenotypic characteristics correlate with molecular signaling activity underlying the etiology or behavior of LGG.

Tumor image-derived texture features are associated with CD3 T-cell infiltration status in glioblastoma

This study analyzed magnetic resonance imaging (MRI) scans of Glioblastoma (GB) patients to develop an imaging-derived predictive model for assessing the extent of intratumoral CD3 T-cell infiltration. Pre-surgical T1-weighted post-contrast and T2-weighted Fluid-Attenuated-Inversion-Recovery (FLAIR) MRI scans, with corresponding mRNA expression of CD3D/E/G were obtained through The Cancer Genome Atlas (TCGA) for 79 GB patients. The tumor region was contoured and 86 image-derived features were extracted across the T1-post contrast and FLAIR images. Six imaging features—kurtosis, contrast, small zone size emphasis, low gray level zone size emphasis, high gray level zone size emphasis, small zone high gray level emphasis—were found associated with CD3 activity and used to build a predictive model for CD3 infiltration in an independent data set of 69 GB patients (using a 50-50 split for training and testing). For the training set, the image-based prediction model for CD3 infiltration achieved accuracy of 97.1% and area under the curve (AUC) of 0.993. For the test set, the model achieved accuracy of 76.5% and AUC of 0.847. This suggests a relationship between image-derived textural features and CD3 T-cell infiltration enabling the non-invasive inference of intratumoral CD3 T-cell infiltration in GB patients, with potential value for the radiological assessment of response to immune therapeutics.

Spatial habitats from multiparametric MR imaging are associated with signaling pathway activities and survival in glioblastoma

Glioblastoma (GBM) show significant inter- and intra-tumoral heterogeneity, impacting response to treatment and overall survival time of 12-15 months. To study glioblastoma phenotypic heterogeneity, multi-parametric magnetic resonance images (MRI) of 85 glioblastoma patients from The Cancer Genome Atlas were analyzed to characterize tumor-derived spatial habitats for their relationship with outcome (overall survival) and to identify their molecular correlates (i.e., determine associated tumor signaling pathways correlated with imaging-derived habitat measurements). Tumor sub-regions based on four sequences (fluid attenuated inversion recovery, T1-weighted, post-contrast T1-weighted, and T2-weighted) were defined by automated segmentation. From relative intensity of pixels in the 3-dimensional tumor region, “imaging habitats” were identified and analyzed for their association to clinical and genetic data using survival modeling and Dirichlet regression, respectively. Sixteen distinct tumor sub-regions (“spatial imaging habitats”) were derived, and those associated with overall survival (denoted “relevant” habitats) in glioblastoma patients were identified. Dirichlet regression implicated each relevant habitat with unique pathway alterations. Relevant habitats also had some pathways and cellular processes in common, including phosphorylation of STAT-1 and natural killer cell activity, consistent with cancer hallmarks. This work revealed clinical relevance of MRI-derived spatial habitats and their relationship with oncogenic molecular mechanisms in patients with GBM. Characterizing the associations between imaging-derived phenotypic measurements with the genomic and molecular characteristics of tumors can enable insights into tumor biology, further enabling the practice of personalized cancer treatment. The analytical framework and workflow demonstrated in this study are inherently scalable to multiple MR sequences.

Radiogenomics and Histomics in Glioblastoma: The Promise of Linking Image-Derived Phenotype with Genomic Information

Intra-tumor heterogeneity is the fundamental challenge in finding a cure for late-stage cancers. Physical biopsies do not sufficiently cover the diversity of molecular phenotypes within the tumor. Treatments are only effective on a subset of vulnerable tumor cells due to the prevalence of tumor stem-like cells. GBM tumors exemplify these general properties of late-stage cancers, with heterogeneous molecular profiles, histology, and radiology. Radiomics aims to characterize disease phenotypes from radiology scans in order to provide an alternative view of tumor heterogeneity, enabling models built from retrospective analysis of radiology scan data, and their integration with clinical data and molecular profiles. Computational histology (histomics) follows a workflow analogous to that of radiomics, with pre-processing, segmentation, feature extraction and analytics. The goal of histomics is to compute cellular morphometry and heterogeneity features from histology datasets. Genomic traits can potentially be inferred from histologic features by analysis of large, linked pathology-genomic data sets. There is also an active investigation of computer vision and machine learning applications to classify gliomas using radiology and histology images. The potential of radiomics, radiogenomics and histomics studies is to advance personalized cancer treatment by enabling interpretation of biological mechanisms underlying imaging phenotypes. These efforts aim to make personalized therapies more accessible. Results from preliminary imaging could direct administration of precision assays to guide treatment, measure treatment response and identify targetable genetic alterations from image-derived phenotype data, across biological scale. Radiomics and histomics promises to revolutionize the practice of personalized medicine, by providing an important complement to molecular strategies.

DEMARCATE: Density-based magnetic resonance image clustering for assessing tumor heterogeneity in cancer

Tumor heterogeneity is a crucial area of cancer research wherein inter- and intra-tumor differences are investigated to assess and monitor disease development and progression, especially in cancer. The proliferation of imaging and linked genomic data has enabled us to evaluate tumor heterogeneity on multiple levels. In this work, we examine magnetic resonance imaging (MRI) in patients with brain cancer to assess image-based tumor heterogeneity. Standard approaches to this problem use scalar summary measures (e.g., intensity-based histogram statistics) that do not adequately capture the complete and finer scale information in the voxel-level data. In this paper, we introduce a novel technique, DEMARCATE (DEnsity-based MAgnetic Resonance image Clustering for Assessing Tumor hEterogeneity) to explore the entire tumor heterogeneity density profiles (THDPs) obtained from the full tumor voxel space. THDPs are smoothed representations of the probability density function of the tumor images. We develop tools for analyzing such objects under the Fisher–Rao Riemannian framework that allows us to construct metrics for THDP comparisons across patients, which can be used in conjunction with standard clustering approaches. Our analyses of The Cancer Genome Atlas (TCGA) based Glioblastoma dataset reveal two significant clusters of patients with marked differences in tumor morphology, genomic characteristics and prognostic clinical outcomes. In addition, we see enrichment of image-based clusters with known molecular subtypes of glioblastoma multiforme, which further validates our representation of tumor heterogeneity and subsequent clustering techniques.

NCO-11TUMOR VOLUMETRIC AND TEXTURAL FEATURE PREDICTORS OF NEUROCOGNITIVE IMPAIRMENT IN PATIENTS WITH TEMPORAL LOBE GLIOMA

BACKGROUND: To determine whether computationally derived image-based textural and volumetric tumor features can predict cognitive impairment in patients with temporal lobe glioma. METHODS: Treatment naive patients with glioma (n = 69; 64% glioblastoma; 74% left temporal) completed neurocognitive testing [WAIS-III Digit Span (DS); Controlled Oral Word Association (COWA); HVLT-R Total Recall; Trail Making Test A & B (TMT)]. Demographically adjusted scores that were at or below 0.74). Volumetric and textural tumor features appear predictive of neurocognitive impairment in patients with glioma, with inclusion of textural indices conveying at least marginal improvement in classification accuracy.