Integrative, multimodal analysis of glioblastoma using TCGA molecular data, pathology images, and clinical outcomes

Biomarkers of Tumor Heterogeneity in Glioblastoma Multiforme Cohort of TCGA

Tumor Whole Slide Images (WSI) are often heterogeneous, which hinders the discovery of biomarkers in the presence of confounding clinical factors. In this study, we present a pipeline for identifying biomarkers from the Glioblastoma Multiforme (GBM) cohort of WSIs from TCGA archive. The GBM cohort endures many technical artifacts while the discovery of GBM biomarkers is challenged because "age" is the single most confounding factor for predicting outcomes. The proposed approach relies on interpretable features (e.g., nuclear morphometric indices), effective similarity metrics for heterogeneity analysis, and robust statistics for identifying biomarkers. The pipeline first removes artifacts (e.g., pen marks) and partitions each WSI into patches for nuclear segmentation via an extended U-Net for subsequent quantitative representation. Given the variations in fixation and staining that can artificially modulate hematoxylin optical density (HOD), we extended Navab's Lab method to normalize images and reduce the impact of batch effects. The heterogeneity of each WSI is then represented either as probability density functions (PDF) per patient or as the composition of a dictionary predicted from the entire cohort of WSIs. For PDF- or dictionary-based methods, morphometric subtypes are constructed based on distances computed from optimal transport and linkage analysis or consensus clustering with Euclidean distances, respectively. For each inferred subtype, Kaplan-Meier and/or the Cox regression model are used to regress the survival time. Since age is the single most important confounder for predicting survival in GBM and there is an observed violation of the proportionality assumption in the Cox model, we use both age and age-squared coupled with the Likelihood ratio test and forest plots for evaluating competing statistics. Next, the PDF- and dictionary-based methods are combined to identify biomarkers that are predictive of survival. The combined model has the advantage of integrating global (e.g., cohort scale) and local (e.g., patient scale) attributes of morphometric heterogeneity, coupled with robust statistics, to reveal stable biomarkers. The results indicate that, after normalization of the GBM cohort, mean HOD, eccentricity, and cellularity are predictive of survival. Finally, we also stratified the GBM cohort as a function of EGFR expression and published genomic subtypes to reveal genomic-dependent morphometric biomarkers.

An integrative web-based software tool for multi-dimensional pathology whole-slide image analytics

Objective.In the era of precision medicine, human tumor atlas-oriented studies have been significantly facilitated by high-resolution, multi-modal tissue based microscopic pathology image analytics. To better support such tissue-based investigations, we have developed Digital Pathology Laboratory (DPLab), a publicly available web-based platform, to assist biomedical research groups, non-technical end users, and clinicians for pathology whole-slide image visualization, annotation, analysis, and sharing via web browsers.Approach.A major advancement of this work is the easy-to-follow methods to reconstruct three-dimension (3D) tissue image volumes by registering two-dimension (2D) whole-slide pathology images of serial tissue sections stained by hematoxylin and eosin (H&E), and immunohistochemistry (IHC). The integration of these serial slides stained by different methods provides cellular phenotype and pathophysiologic states in the context of a 3D tissue micro-environment. DPLab is hosted on a publicly accessible server and connected to a backend computational cluster for intensive image analysis computations, with results visualized, downloaded, and shared via a web interface.Main results.Equipped with an analysis toolbox of numerous image processing algorithms, DPLab supports continued integration of community-contributed algorithms and presents an effective solution to improve the accessibility and dissemination of image analysis algorithms by research communities.Significance.DPLab represents the first step in making next generation tissue investigation tools widely available to the research community, enabling and facilitating discovery of clinically relevant disease mechanisms in a digital 3D tissue space.

DeePROG: Deep Attention-Based Model for Diseased Gene Prognosis by Fusing Multi-Omics Data

An in-depth exploration of gene prognosis using different methodologies aids in understanding various biological regulations of genes in disease pathobiology and molecular functions. Interpreting gene functions at biological and molecular levels remains a daunting yet crucial task in domains such as drug design, personalized medicine, and next-generation diagnostics. Recent advancements in omics technologies have produced diverse heterogeneous genomic datasets like micro-array gene expression, miRNA expression, DNA sequence, 3D structures, which are significant resources for understanding the gene functions. In this paper, we propose a novel self-attention based deep multi-modal model, named DeePROG, for the prognosis of disease affected genes based on heterogeneous omics data. We use three NCBI datasets covering three modalities, namely gene expression profile, the underlying DNA sequence, and the 3D protein structures. To extract useful features from each modality, we develop several context-specific deep learning models. Besides, we develop three attention-based deep bi-modal architectures along with DeePROG to leverage the prognosis of the underlying biomedical data. We assess the performance of the models' in terms of computational assessment of function annotation (CAFA2) metrics. Moreover, we analyze the results in terms of receiver operating characteristics (ROC) curve in high-class imbalance data setting and perform statistical significance tests in terms of Welch's t-test. Experiment results show that DeePROG significantly outperforms baseline models across in terms of performance metrics. The source code and all preprocessed datasets used in this study are available at https://github.com/duttaprat/DeePROG.

Deep learning features encode interpretable morphologies within histological images

Convolutional neural networks (CNNs) are revolutionizing digital pathology by enabling machine learning-based classification of a variety of phenotypes from hematoxylin and eosin (H&E) whole slide images (WSIs), but the interpretation of CNNs remains difficult. Most studies have considered interpretability in a post hoc fashion, e.g. by presenting example regions with strongly predicted class labels. However, such an approach does not explain the biological features that contribute to correct predictions. To address this problem, here we investigate the interpretability of H&E-derived CNN features (the feature weights in the final layer of a transfer-learning-based architecture). While many studies have incorporated CNN features into predictive models, there has been little empirical study of their properties. We show such features can be construed as abstract morphological genes (“mones”) with strong independent associations to biological phenotypes. Many mones are specific to individual cancer types, while others are found in multiple cancers especially from related tissue types. We also observe that mone-mone correlations are strong and robustly preserved across related cancers. Importantly, linear mone-based classifiers can very accurately separate 38 distinct classes (19 tumor types and their adjacent normals, AUC = \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$97.1\% \pm 2.8\%$$\end{document}97.1%±2.8% for each class prediction), and linear classifiers are also highly effective for universal tumor detection (AUC = \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$99.2\% \pm 0.12\%$$\end{document}99.2%±0.12%). This linearity provides evidence that individual mones or correlated mone clusters may be associated with interpretable histopathological features or other patient characteristics. In particular, the statistical similarity of mones to gene expression values allows integrative mone analysis via expression-based bioinformatics approaches. We observe strong correlations between individual mones and individual gene expression values, notably mones associated with collagen gene expression in ovarian cancer. Mone-expression comparisons also indicate that immunoglobulin expression can be identified using mones in colon adenocarcinoma and that immune activity can be identified across multiple cancer types, and we verify these findings by expert histopathological review. Our work demonstrates that mones provide a morphological H&E decomposition that can be effectively associated with diverse phenotypes, analogous to the interpretability of transcription via gene expression values. Our work also demonstrates mones can be interpreted without using a classifier as a proxy.

Tumor Cell Invasion in Glioblastoma

Glioblastoma (GBM) is a particularly devastating tumor with a median survival of about 16 months. Recent research has revealed novel insights into the outstanding heterogeneity of this type of brain cancer. However, all GBM subtypes share the hallmark feature of aggressive invasion into the surrounding tissue. Invasive glioblastoma cells escape surgery and focal therapies and thus represent a major obstacle for curative therapy. This review aims to provide a comprehensive understanding of glioma invasion mechanisms with respect to tumor-cell-intrinsic properties as well as cues provided by the microenvironment. We discuss genetic programs that may influence the dissemination and plasticity of GBM cells as well as their different invasion patterns. We also review how tumor cells shape their microenvironment and how, vice versa, components of the extracellular matrix and factors from non-neoplastic cells influence tumor cell motility. We further discuss different research platforms for modeling invasion. Finally, we highlight the importance of accounting for the complex interplay between tumor cell invasion and treatment resistance in glioblastoma when considering new therapeutic approaches.

Segmentation and Classification in Digital Pathology for Glioma Research: Challenges and Deep Learning Approaches

Biomedical imaging Is an important source of information in cancer research. Characterizations of cancer morphology at onset, progression, and in response to treatment provide complementary information to that gleaned from genomics and clinical data. Accurate extraction and classification of both visual and latent image features Is an increasingly complex challenge due to the increased complexity and resolution of biomedical image data. In this paper, we present four deep learning-based image analysis methods from the Computational Precision Medicine (CPM) satellite event of the 21st International Medical Image Computing and Computer Assisted Intervention (MICCAI 2018) conference. One method Is a segmentation method designed to segment nuclei in whole slide tissue images (WSIs) of adult diffuse glioma cases. It achieved a Dice similarity coefficient of 0.868 with the CPM challenge datasets. Three methods are classification methods developed to categorize adult diffuse glioma cases into oligodendroglioma and astrocytoma classes using radiographic and histologic image data. These methods achieved accuracy values of 0.75, 0.80, and 0.90, measured as the ratio of the number of correct classifications to the number of total cases, with the challenge datasets. The evaluations of the four methods indicate that (1) carefully constructed deep learning algorithms are able to produce high accuracy in the analysis of biomedical image data and (2) the combination of radiographic with histologic image information improves classification performance.

Histo-genomics: digital pathology at the forefront of precision medicine

The toughest challenge OMICs face is that they provide extremely high molecular resolution but poor spatial information. Understanding the cellular/histological context of the overwhelming genetic data is critical for a full understanding of the clinical behavior of a malignant tumor. Digital pathology can add an extra layer of information to help visualize in a spatial and microenvironmental context the molecular information of cancer. Thus, histo-genomics provide a unique chance for data integration. In the era of a precision medicine, a four-dimensional (4D) (temporal/spatial) analysis of cancer aided by digital pathology can be a critical step to understand the evolution/progression of different cancers and consequently tailor individual treatment plans. For instance, the integration of molecular biomarkers expression into a three-dimensional (3D) image of a digitally scanned tumor can offer a better understanding of its subtype, behavior, host immune response and prognosis. Using advanced digital image analysis, a larger spectrum of parameters can be analyzed as potential predictors of clinical behavior. Correlation between morphological features and host immune response can be also performed with therapeutic implications. Radio-histomics, or the interface of radiological images and histology is another emerging exciting field which encompasses the integration of radiological imaging with digital pathological images, genomics, and clinical data to portray a more holistic approach to understating and treating disease. These advances in digital slide scanning are not without technical challenges, which will be addressed carefully in this review with quick peek at its future.

PANOPLY: Omics-Guided Drug Prioritization Method Tailored to an Individual Patient

PURPOSE

The majority of patients with cancer receive treatments that are minimally informed by omics data. We propose a precision medicine computational framework, PANOPLY (Precision Cancer Genomic Report: Single Sample Inventory), to identify and prioritize drug targets and cancer therapy regimens.

MATERIALS AND METHODS

The PANOPLY approach integrates clinical data with germline and somatic features obtained from multiomics platforms and applies machine learning and network analysis approaches in the context of the individual patient and matched controls. The PANOPLY workflow uses the following four steps: selection of matched controls to the patient of interest; identification of patient-specific genomic events; identification of suitable drugs using the driver-gene network and random forest analyses; and provision of an integrated multiomics case report of the patient with prioritization of anticancer drugs.

RESULTS

The PANOPLY workflow can be executed on a stand-alone virtual machine and is also available for download as an R package. We applied the method to an institutional breast cancer neoadjuvant chemotherapy study that collected clinical and genomic data as well as patient-derived xenografts to investigate the prioritization offered by PANOPLY. In a chemotherapy-resistant patient-derived xenograft model, we found that that the prioritized drug, olaparib, was more effective than placebo in treating the tumor ( P < .05). We also applied PANOPLY to in-house and publicly accessible multiomics tumor data sets with therapeutic response or survival data available.

CONCLUSION

PANOPLY shows promise as a means to prioritize drugs on the basis of clinical and multiomics data for an individual patient with cancer. Additional studies are needed to confirm this approach.

Targeting Oncogenic BRAF: Past, Present, and Future

Identifying recurrent somatic genetic alterations of, and dependency on, the kinase BRAF has enabled a "precision medicine" paradigm to diagnose and treat BRAF-driven tumors. Although targeted kinase inhibitors against BRAF are effective in a subset of mutant BRAF tumors, resistance to the therapy inevitably emerges. In this review, we discuss BRAF biology, both in wild-type and mutant settings. We discuss the predominant BRAF mutations and we outline therapeutic strategies to block mutant BRAF and cancer growth. We highlight common mechanistic themes that underpin different classes of resistance mechanisms against BRAF-targeted therapies and discuss tumor heterogeneity and co-occurring molecular alterations as a potential source of therapy resistance. We outline promising therapy approaches to overcome these barriers to the long-term control of BRAF-driven tumors and emphasize how an extensive understanding of these themes can offer more pre-emptive, improved therapeutic strategies.

Augmentation of Physician Assessments with Multi-Omics Enhances Predictability of Drug Response: A Case Study of Major Depressive Disorder

This work proposes a "learning-augmented clinical assessment" workflow to sequentially augment physician assessments of patients' symptoms and their socio-demographic measures with heterogeneous biological measures to accurately predict treatment outcomes using machine learning. Across many psychiatric illnesses, ranging from major depressive disorder to schizophrenia, symptom severity assessments are subjective and do not include biological measures, making predictability in eventual treatment outcomes a challenge. Using data from the Mayo Clinic PGRN-AMPS SSRI trial as a case study, this work demonstrates a significant improvement in the prediction accuracy for antidepressant treatment outcomes in patients with major depressive disorder from 35% to 80% individualized by patient, compared to using only a physician's assessment as the predictors. This improvement is achieved through an iterative overlay of biological measures, starting with metabolites (blood measures modulated by drug action) associated with symptom severity, and then adding in genes associated with metabolomic concentrations. Hence, therapeutic efficacy for a new patient can be assessed prior to treatment, using prediction models that take as inputs, selected biological measures and physician's assessments of depression severity. Of broader significance extending beyond psychiatry, the approach presented in this work can potentially be applied to predicting treatment outcomes for other medical conditions, such as migraine headaches or rheumatoid arthritis, for which patients are treated according to subject-reported assessments of symptom severity.

A combined diffusion tensor imaging and Ki-67 labeling index study for evaluating the extent of tumor infiltration using the F98 rat glioma model

Diffusion tensor imaging (DTI) has been proven to be a sophisticated and useful tool for the delineation of tumors. In the present study, we investigated the predictive role of DTI compared to other magnetic resonance imaging (MRI) techniques in combination with Ki-67 labeling index in defining tumor cell infiltration in the peritumoral regions of F98 glioma-bearing rats. A total of 29 tumor-bearing Fischer rats underwent T2-weighted imaging, contrast-enhanced T1-weighted imaging, and DTI of their brain using a 7.0-T MRI scanner. The fractional anisotropy (FA) ratios were correlated to the Ki-67 labeling index using the Spearman correlation analysis. A receiver operating characteristic curve (ROC) analysis was established to evaluate parameters with sensitivity and specificity in order to identify the threshold values for predicting tumor infiltration. Significant correlations were observed between the FA ratios and Ki-67 labeling index (r = - 0.865, p < 0.001). The ROC analysis demonstrated that the apparent diffusion coefficient (ADC) and FA ratios could predict 50% of the proliferating cells in the regions of interest (ROI), with a sensitivity of 88.1 and 81.3%, and a specificity of 86.2 and 90.2%, respectively (p < 0.001). Meanwhile, the two ratios could also predict 10% of the proliferating cells in the ROI, with a sensitivity of 82.5 and 94.9%, and a specificity of 100 and 88.9%, respectively (p < 0.001). The present study demonstrated that the FA ratios are closely correlated with the Ki-67 labeling index. Furthermore, both ADC and FA ratios, derived from DTI, were useful for quantitatively predicting the Ki-67 labeling of glioma cells.

Integrative radiogenomic analysis for multicentric radiophenotype in glioblastoma

We postulated that multicentric glioblastoma (GBM) represents more invasiveness form than solitary GBM and has their own genomic characteristics. From May 2004 to June 2010 we retrospectively identified 51 treatment-naïve GBM patients with available clinical information from the Samsung Medical Center data registry. Multicentricity of the tumor was defined as the presence of multiple foci on the T1 contrast enhancement of MR images or having high signal for multiple lesions without contiguity of each other on the FLAIR image. Kaplan-Meier survival analysis demonstrated that multicentric GBM had worse prognosis than solitary GBM (median, 16.03 vs. 20.57 months, p < 0.05). Copy number variation (CNV) analysis revealed there was an increase in 11 regions, and a decrease in 17 regions, in the multicentric GBM. Gene expression profiling identified 738 genes to be increased and 623 genes to be decreased in the multicentric radiophenotype (p < 0.001). Integration of the CNV and expression datasets identified twelve representative genes: CPM, LANCL2, LAMP1, GAS6, DCUN1D2, CDK4, AGAP2, TSPAN33, PDLIM1, CLDN12, and GTPBP10 having high correlation across CNV, gene expression and patient outcome. Network and enrichment analyses showed that the multicentric tumor had elevated fibrotic signaling pathways compared with a more proliferative and mitogenic signal in the solitary tumors. Noninvasive radiological imaging together with integrative radiogenomic analysis can provide an important tool in helping to advance personalized therapy for the more clinically aggressive subset of GBM.

Adaptive Multiview Nonnegative Matrix Factorization Algorithm for Integration of Multimodal Biomedical Data

The amounts and types of available multimodal tumor data are rapidly increasing, and their integration is critical for fully understanding the underlying cancer biology and personalizing treatment. However, the development of methods for effectively integrating multimodal data in a principled manner is lagging behind our ability to generate the data. In this article, we introduce an extension to a multiview nonnegative matrix factorization algorithm (NNMF) for dimensionality reduction and integration of heterogeneous data types and compare the predictive modeling performance of the method on unimodal and multimodal data. We also present a comparative evaluation of our novel multiview approach and current data integration methods. Our work provides an efficient method to extend an existing dimensionality reduction method. We report rigorous evaluation of the method on large-scale quantitative protein and phosphoprotein tumor data from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) acquired using state-of-the-art liquid chromatography mass spectrometry. Exome sequencing and RNA-Seq data were also available from The Cancer Genome Atlas for the same tumors. For unimodal data, in case of breast cancer, transcript levels were most predictive of estrogen and progesterone receptor status and copy number variation of human epidermal growth factor receptor 2 status. For ovarian and colon cancers, phosphoprotein and protein levels were most predictive of tumor grade and stage and residual tumor, respectively. When multiview NNMF was applied to multimodal data to predict outcomes, the improvement in performance is not overall statistically significant beyond unimodal data, suggesting that proteomics data may contain more predictive information regarding tumor phenotypes than transcript levels, probably due to the fact that proteins are the functional gene products and therefore a more direct measurement of the functional state of the tumor. Here, we have applied our proposed approach to multimodal molecular data for tumors, but it is generally applicable to dimensionality reduction and joint analysis of any type of multimodal data.

Development of a Framework for Large Scale Three-Dimensional Pathology and Biomarker Imaging and Spatial Analytics

With the rapid advancement in large-throughput scanning technologies, digital pathology has emerged as platform with promise for diagnostic approaches, but also for high-throughput quantitative data extraction and analysis for translational research. Digital pathology and biomarker images are rich sources of information on tissue architecture, cell diversity and morphology, and molecular pathway activation. However, the understanding of disease in three-dimension (3D) has been hampered by their traditional two-dimension (2D) representations on histologic slides. In this paper, we propose a scalable image processing framework to quantitatively investigate 3D phenotypic and cell-specific molecular features from digital pathology and biomarker images in information- lossless 3D tissue space. We also develop a generalized 3D spatial data management framework with multi-level parallelism and provide a sustainable infrastructure for rapid spatial queries through scalable and efficient spatial data processing. The developed framework can facilitate biomedical research by efficiently processing large-scale, 3D pathology and in-situ biomarker imaging data.

Identification of "BRAF-Positive" Cases Based on Whole-Slide Image Analysis

A key requirement for precision medicine is the accurate identification of patients that would respond to a specific treatment or those that represent a high-risk group, and a plethora of molecular biomarkers have been proposed for this purpose during the last decade. Their application in clinical settings, however, is not always straightforward due to relatively high costs of some tests, limited availability of the biological material and time, and procedural constraints. Hence, there is an increasing interest in constructing tissue-based surrogate biomarkers that could be applied with minimal overhead directly to histopathology images and which could be used for guiding the selection of eventual further molecular tests. In the context of colorectal cancer, we present a method for constructing a surrogate biomarker that is able to predict with high accuracy whether a sample belongs to the “BRAF-positive” group, a high-risk group comprising V600E BRAF mutants and BRAF-mutant-like tumors. Our model is trained to mimic the predictions of a 64-gene signature, the current definition of BRAF-positive group, thus effectively identifying histopathology image features that can be linked to a molecular score. Since the only required input is the routine histopathology image, the model can easily be integrated in the diagnostic workflow.

Whole Slide Imaging for Analytical Anatomic Pathology and Telepathology: Practical Applications Today, Promises, and Perils

Whole slide imaging (WSI) offers a convenient, tractable platform for measuring features of routine and special-stain histology or in immunohistochemistry staining by using digital image analysis (IA). We now routinely use IA for quantitative and qualitative analysis of theranostic markers such as human epidermal growth factor 2 (HER2/neu), estrogen and progesterone receptors, and Ki-67. Quantitative IA requires extensive validation, however, and may not always be the best approach, with pancreatic neuroendocrine tumors being one example in which a semiautomated approach may be preferable for patient care. We find that IA has great utility for objective assessment of gastrointestinal tract dysplasia, microvessel density in hepatocellular carcinoma, hepatic fibrosis and steatosis, renal fibrosis, and general quality analysis/quality control, although the applications of these to daily practice are still in development. Collaborations with bioinformatics specialists have explored novel applications to gliomas, including in silico approaches for mining histologic data and correlating with molecular and radiologic findings. We and many others are using WSI for rapid, remote-access slide reviews (telepathology), though technical factors currently limit its utility for routine, high-volume diagnostics. In our experience, the greatest current practical impact of WSI lies in facilitating long-term storage and retrieval of images while obviating the need to keep slides on site. Once the existing barriers of capital cost, validation, operator training, software design, and storage/back-up concerns are overcome, these technologies appear destined to be a cornerstone of precision medicine and personalized patient care, and to become a routine part of pathology practice.

Genome-wide analysis of gynecologic cancer: The Cancer Genome Atlas in ovarian and endometrial cancer

Cancer typically develops due to genetic abnormalities, but a single gene abnormality cannot completely account for the onset of cancer. The Cancer Genome Atlas (CGA) project was conducted for the cross-sectional genome-wide analysis of numerous genetic abnormalities in various types of cancer. This approach has facilitated the identification of novel AT-rich interaction domain 1A gene mutations in ovarian clear cell carcinoma, frequent tumor protein 53 (TP53) gene mutations in high-grade ovarian serous carcinoma, and Kirsten rat sarcoma and B-rapidly accelerated fibrosarcoma proto-oncogene, serine/threonine kinase gene mutations in low-grade ovarian serous carcinoma. Genome-wide analysis of endometrial cancers has led to the establishment of four subgroups: Polymerase ultramutated, microsatellite instability hypermutated, genome copy-number low and genome copy-number high. These results may facilitate the improvement of the prediction of patient prognosis and therapeutic sensitivity in various types of gynecologic cancer. The enhanced use of currently available therapeutic agents and the development of novel drugs may be facilitated by the novel classification of ovarian cancer based on TP53 mutations, the efficacy of poly (ADP-ribose) polymerase inhibitors for tumors with breast cancer 1/2 mutations and the effect of phosphoinositide-3-kinase (PI3K)/mammalian target of rapamycin inhibitors for tumors with mutations in the PI3K/protein kinase B signaling pathway. Important results have been revealed by genome-wide analyses; however, the pathogenic underlying mechanisms of gynecologic cancer will require further studies and multilateral evaluation using epigenetic, transcriptomic and proteomic analyses, in addition to genomic analysis.

Network inference from multimodal data: A review of approaches from infectious disease transmission

Networks inference problems are commonly found in multiple biomedical subfields such as genomics, metagenomics, neuroscience, and epidemiology. Networks are useful for representing a wide range of complex interactions ranging from those between molecular biomarkers, neurons, and microbial communities, to those found in human or animal populations. Recent technological advances have resulted in an increasing amount of healthcare data in multiple modalities, increasing the preponderance of network inference problems. Multi-domain data can now be used to improve the robustness and reliability of recovered networks from unimodal data. For infectious diseases in particular, there is a body of knowledge that has been focused on combining multiple pieces of linked information. Combining or analyzing disparate modalities in concert has demonstrated greater insight into disease transmission than could be obtained from any single modality in isolation. This has been particularly helpful in understanding incidence and transmission at early stages of infections that have pandemic potential. Novel pieces of linked information in the form of spatial, temporal, and other covariates including high-throughput sequence data, clinical visits, social network information, pharmaceutical prescriptions, and clinical symptoms (reported as free-text data) also encourage further investigation of these methods. The purpose of this review is to provide an in-depth analysis of multimodal infectious disease transmission network inference methods with a specific focus on Bayesian inference. We focus on analytical Bayesian inference-based methods as this enables recovering multiple parameters simultaneously, for example, not just the disease transmission network, but also parameters of epidemic dynamics. Our review studies their assumptions, key inference parameters and limitations, and ultimately provides insights about improving future network inference methods in multiple applications.

Sample Level Enrichment Analysis of KEGG Pathways Identifies Clinically Relevant Subtypes of Glioblastoma

Background: Glioblastoma is the most lethal primary brain tumor in adults. Aberrant signal transduction pathways, associated with the progression of glioblastoma, have been identified recently and may offer a potential gene therapy strategy. Methods and Findings: We first used the sample level enrichment analysis to transfer gene expression profile of TCGA dataset into pathway enrichment z-score matrix. Then, we classified glioblastoma into five subtypes (Cluster A to Cluster E) by the consensus clustering and silhouette analysis. Principle component analysis showed the five subtype could be separated by first three principle components. Integrative omics data showed that mesenchymal subtype was rich in Cluster A, neural subtype was centered in Cluster D and proneural subtype was gathered in Cluster E, while Cluster E showed a high percentage of G-CIMP subtype. Additionally, according to analyze the overall survival and progression free survival of each subtype by Kaplan-Merie analysis and Cox hazard proportion model, we identified Cluster D and Cluster E received a better prognosis. Conclusions: We report a clinically relevant classification of glioblastoma based on sample level KEGG pathway enrichment profile and this novel classification system provided new insights into the heterogeneity of glioblastoma, and may be used as an important clinical tool to predict the prognosis.

Towards the identification of tissue-based proxy biomarkers

Accurate patient population stratification is a key requirement for a personalized medicine and more precise biomarkers are expected to be obtained by better exploiting the available data. We introduce a novel computational framework that exploits both the information from gene expression data and histopathology images for constructing a tissue-based biomarker, which can be used for identifying a high-risk patient population. Its utility is demonstrated in the context of colorectal cancer data and we show that the resulting biomarker can be used as a proxy for a prognostic gene expression signature. These results are important for both the computational discovery of new biomarkers and clinical practice, as they demonstrate a possible approach for multimodal biomedical data mining and since the new tissue-based biomarker could easily be implemented in the routine pathology practice.

Joint analysis of histopathology image features and gene expression in breast cancer

Background

Genomics and proteomics are nowadays the dominant techniques for novel biomarker discovery. However, histopathology images contain a wealth of information related to the tumor histology, morphology and tumor-host interactions that is not accessible through these techniques. Thus, integrating the histopathology images in the biomarker discovery workflow could potentially lead to the identification of new image-based biomarkers and the refinement or even replacement of the existing genomic and proteomic signatures. However, extracting meaningful and robust image features to be mined jointly with genomic (and clinical, etc.) data represents a real challenge due to the complexity of the images.

Results

We developed a framework for integrating the histopathology images in the biomarker discovery workflow based on the bag-of-features approach – a method that has the advantage of being assumption-free and data-driven. The images were reduced to a set of salient patterns and additional measurements of their spatial distribution, with the resulting features being directly used in a standard biomarker discovery application. We demonstrated this framework in a search for prognostic biomarkers in breast cancer which resulted in the identification of several prognostic image features and a promising multimodal (imaging and genomic) prognostic signature. The source code for the image analysis procedures is freely available.

Conclusions

The framework proposed allows for a joint analysis of images and gene expression data. Its application to a set of breast cancer cases resulted in image-based and combined (image and genomic) prognostic scores for relapse-free survival.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1072-z) contains supplementary material, which is available to authorized users.

Claudin-7 indirectly regulates the integrin/FAK signaling pathway in human colon cancer tissue

The claudin family of proteins is integral to the structure and function of tight junctions. The role of claudin-7 (Cldn-7, CLDN7) in regulating the integrin/focal adhesion kinase (FAK)/ERK signaling pathway remains poorly understood. Therefore, we investigated differences in gene expression, primarily focusing on CLDN7 and integrin/FAK/ERK signaling pathway genes, between colon cancer and adjacent normal tissues. Quantitative real-time reverse transcription-PCR and immunohistochemistry were utilized to verify the results of mRNA and protein expression, respectively. In silico analysis was used to predict co-regulation between Cldn-7 and integrin/FAK/ERK signaling pathway components, and the STRING database was used to analyze protein-protein interaction pairs among these proteins. Meta-analysis of expression microarrays in The Cancer Genome Atlas (TCGA) database was used to identify significant correlations between Cldn-7 and components of predicted genes in the integrin/FAK/ERK signaling pathway. Our results showed marked cancer stage-specific decreases in the protein expression of Cldn-7, Gelsolin, MAPK1 and MAPK3 in colon cancer samples, and the observed changes for all proteins except Cldn-7 were in agreement with changes in the corresponding mRNA levels. Cldn-7 might indirectly regulate MAPK3 via KRT8 due to KRT8 co-expression with MAPK3 or CLDN7. Our bioinformatics methods supported the hypothesis that Cldn-7 does not directly regulate any genes in the integrin/FAK/ERK signaling pathway. These factors may participate in a common network that regulates cancer progression in which the MAPK pathway serves as the central node.

A Framework for 3D Vessel Analysis using Whole Slide Images of Liver Tissue Sections

Three-dimensional (3D) high resolution microscopic images have high potential for improving the understanding of both normal and disease processes where structural changes or spatial relationship of disease features are significant. In this paper, we develop a complete framework applicable to 3D pathology analytical imaging, with an application to whole slide images of sequential liver slices for 3D vessel structure analysis. The analysis workflow consists of image registration, segmentation, vessel cross-section association, interpolation, and volumetric rendering. To identify biologically-meaningful correspondence across adjacent slides, we formulate a similarity function for four association cases. The optimal solution is then obtained by constrained Integer Programming. We quantitatively and qualitatively compare our vessel reconstruction results with human annotations. Validation results indicate a satisfactory concordance as measured both by region-based and distance-based metrics. These results demonstrate a promising 3D vessel analysis framework for whole slide images of liver tissue sections.

Scalable analysis of Big pathology image data cohorts using efficient methods and high-performance computing strategies

BACKGROUND

We describe a suite of tools and methods that form a core set of capabilities for researchers and clinical investigators to evaluate multiple analytical pipelines and quantify sensitivity and variability of the results while conducting large-scale studies in investigative pathology and oncology. The overarching objective of the current investigation is to address the challenges of large data sizes and high computational demands.

RESULTS

The proposed tools and methods take advantage of state-of-the-art parallel machines and efficient content-based image searching strategies. The content based image retrieval (CBIR) algorithms can quickly detect and retrieve image patches similar to a query patch using a hierarchical analysis approach. The analysis component based on high performance computing can carry out consensus clustering on 500,000 data points using a large shared memory system.

CONCLUSIONS

Our work demonstrates efficient CBIR algorithms and high performance computing can be leveraged for efficient analysis of large microscopy images to meet the challenges of clinically salient applications in pathology. These technologies enable researchers and clinical investigators to make more effective use of the rich informational content contained within digitized microscopy specimens.

Radiological features combined with IDH1 status for predicting the survival outcome of glioblastoma patients

BACKGROUND

Radiological characteristics may reflect the biological features of brain tumors and may be associated with genetic alterations that occur in tumorigenesis. This study aimed to investigate the relationship between radiological features and IDH1 status as well as their predictive value for survival of glioblastoma patients.

METHODS

The clinical information and MR images of 280 patients with histologically confirmed glioblastoma were retrospectively reviewed. The radiological characteristics of tumors were examined on MR images, and the IDH1 status was determined using DNA sequencing for all cases. The Kaplan-Meier method and Cox regression model were used to identify prognostic factors for progression-free and overall survival.

RESULTS

The IDH1 mutation was associated with longer progression-free survival (P = .022; hazard ratio, 0.602) and overall survival (P = .018; hazard ratio, 0.554). In patients with the IDH1 mutation, tumor contrast enhancement and peritumoral edema indicated worse progression-free survival (P = .015 and P = .024, respectively) and worse overall survival (P = .024 and P = .032, respectively). For tumors with contrast enhancement, multifocal contrast enhancement of the tumor lesion was associated with poor progression-free survival (P = .002) and poor overall survival (P = .010) in patients with wild-type IDH1 tumors.

CONCLUSIONS

Combining the radiological features and IDH1 status of a tumor allows more accurate prediction of survival outcomes in glioblastoma patients. The complementary roles of genetic changes and radiological features of tumors should be considered in future studies.

Efficient exploration of pan-cancer networks by generalized covariance selection and interactive web content

Statistical network modeling techniques are increasingly important tools to analyze cancer genomics data. However, current tools and resources are not designed to work across multiple diagnoses and technical platforms, thus limiting their applicability to comprehensive pan-cancer datasets such as The Cancer Genome Atlas (TCGA). To address this, we describe a new data driven modeling method, based on generalized Sparse Inverse Covariance Selection (SICS). The method integrates genetic, epigenetic and transcriptional data from multiple cancers, to define links that are present in multiple cancers, a subset of cancers, or a single cancer. It is shown to be statistically robust and effective at detecting direct pathway links in data from TCGA. To facilitate interpretation of the results, we introduce a publicly accessible tool (cancerlandscapes.org), in which the derived networks are explored as interactive web content, linked to several pathway and pharmacological databases. To evaluate the performance of the method, we constructed a model for eight TCGA cancers, using data from 3900 patients. The model rediscovered known mechanisms and contained interesting predictions. Possible applications include prediction of regulatory relationships, comparison of network modules across multiple forms of cancer and identification of drug targets.

Current perspectives concerning the multimodal therapy in Glioblastoma

GBM (Glioblastoma) is the most common, malignant type of primary brain tumor. It has a dismal prognosis, with an average life expectancy of less than 15 months. A better understanding of the tumor biology of GBM has been achieved in the past decade and set up new directions in the multimodal therapy by targeting the molecular paths involved in tumor initiation and progression. Invasion is a hallmark of GBM, and targeting the complex invasive mechanism of the tumor is mandatory in order to achieve a satisfactory result in GBM therapy. The goal of this review is to describe the tumor biology and key features of GBM and to provide an up-to-date overview of the current identified molecular alterations involved both in tumorigenesis and tumor progression.

Crowdsourcing image annotation for nucleus detection and segmentation in computational pathology: evaluating experts, automated methods, and the crowd

The development of tools in computational pathology to assist physicians and biomedical scientists in the diagnosis of disease requires access to high-quality annotated images for algorithm learning and evaluation. Generating high-quality expert-derived annotations is time-consuming and expensive. We explore the use of crowdsourcing for rapidly obtaining annotations for two core tasks in com- putational pathology: nucleus detection and nucleus segmentation. We designed and implemented crowdsourcing experiments using the CrowdFlower platform, which provides access to a large set of labor channel partners that accesses and manages millions of contributors worldwide. We obtained annotations from four types of annotators and compared concordance across these groups. We obtained: crowdsourced annotations for nucleus detection and segmentation on a total of 810 images; annotations using automated methods on 810 images; annotations from research fellows for detection and segmentation on 477 and 455 images, respectively; and expert pathologist-derived annotations for detection and segmentation on 80 and 63 images, respectively. For the crowdsourced annotations, we evaluated performance across a range of contributor skill levels (1, 2, or 3). The crowdsourced annotations (4,860 images in total) were completed in only a fraction of the time and cost required for obtaining annotations using traditional methods. For the nucleus detection task, the research fellow-derived annotations showed the strongest concordance with the expert pathologist- derived annotations (F-M =93.68%), followed by the crowd-sourced contributor levels 1,2, and 3 and the automated method, which showed relatively similar performance (F-M = 87.84%, 88.49%, 87.26%, and 86.99%, respectively). For the nucleus segmentation task, the crowdsourced contributor level 3-derived annotations, research fellow-derived annotations, and automated method showed the strongest concordance with the expert pathologist-derived annotations (F-M = 66.41%, 65.93%, and 65.36%, respectively), followed by the contributor levels 2 and 1 (60.89% and 60.87%, respectively). When the research fellows were used as a gold-standard for the segmentation task, all three con- tributor levels of the crowdsourced annotations significantly outperformed the automated method (F-M = 62.21%, 62.47%, and 65.15% vs. 51.92%). Aggregating multiple annotations from the crowd to obtain a consensus annotation resulted in the strongest performance for the crowd-sourced segmentation. For both detection and segmentation, crowd-sourced performance is strongest with small images (400 × 400 pixels) and degrades significantly with the use of larger images (600 × 600 and 800 × 800 pixels). We conclude that crowdsourcing to non-experts can be used for large-scale labeling microtasks in computational pathology and offers a new approach for the rapid generation of labeled images for algorithm development and evaluation.

Glioblastoma: imaging genomic mapping reveals sex-specific oncogenic associations of cell death

PURPOSE

To identify the molecular profiles of cell death as defined by necrosis volumes at magnetic resonance (MR) imaging and uncover sex-specific molecular signatures potentially driving oncogenesis and cell death in glioblastoma (GBM).

MATERIALS AND METHODS

This retrospective study was HIPAA compliant and had institutional review board approval, with waiver of the need to obtain informed consent. The molecular profiles for 99 patients (30 female patients, 69 male patients) were identified from the Cancer Genome Atlas, and quantitative MR imaging data were obtained from the Cancer Imaging Archive. Volumes of necrosis at MR imaging were extracted. Differential gene expression profiles were obtained in those patients (including male and female patients separately) with high versus low MR imaging volumes of tumor necrosis. Ingenuity Pathway Analysis was used for messenger RNA-microRNA interaction analysis. A histopathologic data set (n = 368; 144 female patients, 224 male patients) was used to validate the MR imaging findings by assessing the amount of cell death. A connectivity map was used to identify therapeutic agents potentially targeting sex-specific cell death in GBM.

RESULTS

Female patients showed significantly lower volumes of necrosis at MR imaging than male patients (6821 vs 11 050 mm(3), P = .03). Female patients, unlike male patients, with high volumes of necrosis at imaging had significantly shorter survival (6.5 vs 14.5 months, P = .01). Transcription factor analysis suggested that cell death in female patients with GBM is associated with MYC, while that in male patients is associated with TP53 activity. Additionally, a group of therapeutic agents that can potentially be tested to target cell death in a sex-specific manner was identified.

CONCLUSION

The results of this study suggest that cell death in GBM may be driven by sex-specific molecular pathways.

Molecular heterogeneity of glioblastoma and its clinical relevance

Glioblastoma is the most common intracranial malignancy and constitutes about 50 % of all gliomas. Both inter-tumor and intra-tumor histological heterogeneity had been recognized by the early 1980-ies. Recent works using novel molecular platforms provided molecular definitions of these tumors. Based on comprehensive genomic sequence analyses, The Cancer Genome Atlas Research Network (TCGA) cataloged somatic mutations and recurrent copy number alterations in glioblastoma. Robust transcriptome and epigenome studies also revealed inter-tumor heterogeneity. Integration and cluster analyses of multi-dimensional genomic data lead to a new classification of glioblastoma tumors into subtypes with distinct biological features and clinical correlates. However, multiple observations also revealed tumor area-specific patterns of genomic imbalance. In addition, genetic alterations have been identified that were common to all areas analyzed and other alterations that were area specific. Analyses of intra-tumor transcriptome variations revealed that in more than half of the examined cases, fragments from the same tumor mass could be classified into at least two different glioblastoma molecular subgroups. Intra-tumor heterogeneity of molecular genetic profiles in glioblastoma may explain the difficulties encountered in the validation of oncologic biomarkers, and contribute to a biased selection of patients for single target therapies, treatment failure or drug resistance. In this paper, we summarize the currently available literature concerning inter- and intra-tumor molecular heterogeneity of glioblastomas, and call attention to the importance of this topic in relation to the growing efforts in routine molecular diagnostics and personalized therapy.

Content-based histopathology image retrieval using CometCloud

Background

The development of digital imaging technology is creating extraordinary levels of accuracy that provide support for improved reliability in different aspects of the image analysis, such as content-based image retrieval, image segmentation, and classification. This has dramatically increased the volume and rate at which data are generated. Together these facts make querying and sharing non-trivial and render centralized solutions unfeasible. Moreover, in many cases this data is often distributed and must be shared across multiple institutions requiring decentralized solutions. In this context, a new generation of data/information driven applications must be developed to take advantage of the national advanced cyber-infrastructure (ACI) which enable investigators to seamlessly and securely interact with information/data which is distributed across geographically disparate resources. This paper presents the development and evaluation of a novel content-based image retrieval (CBIR) framework. The methods were tested extensively using both peripheral blood smears and renal glomeruli specimens. The datasets and performance were evaluated by two pathologists to determine the concordance.

Results

The CBIR algorithms that were developed can reliably retrieve the candidate image patches exhibiting intensity and morphological characteristics that are most similar to a given query image. The methods described in this paper are able to reliably discriminate among subtle staining differences and spatial pattern distributions. By integrating a newly developed dual-similarity relevance feedback module into the CBIR framework, the CBIR results were improved substantially. By aggregating the computational power of high performance computing (HPC) and cloud resources, we demonstrated that the method can be successfully executed in minutes on the Cloud compared to weeks using standard computers.

Conclusions

In this paper, we present a set of newly developed CBIR algorithms and validate them using two different pathology applications, which are regularly evaluated in the practice of pathology. Comparative experimental results demonstrate excellent performance throughout the course of a set of systematic studies. Additionally, we present and evaluate a framework to enable the execution of these algorithms across distributed resources. We show how parallel searching of content-wise similar images in the dataset significantly reduces the overall computational time to ensure the practical utility of the proposed CBIR algorithms.

Joint sparse coding based spatial pyramid matching for classification of color medical image

Although color medical images are important in clinical practice, they are usually converted to grayscale for further processing in pattern recognition, resulting in loss of rich color information. The sparse coding based linear spatial pyramid matching (ScSPM) and its variants are popular for grayscale image classification, but cannot extract color information. In this paper, we propose a joint sparse coding based SPM (JScSPM) method for the classification of color medical images. A joint dictionary can represent both the color information in each color channel and the correlation between channels. Consequently, the joint sparse codes calculated from a joint dictionary can carry color information, and therefore this method can easily transform a feature descriptor originally designed for grayscale images to a color descriptor. A color hepatocellular carcinoma histological image dataset was used to evaluate the performance of the proposed JScSPM algorithm. Experimental results show that JScSPM provides significant improvements as compared with the majority voting based ScSPM and the original ScSPM for color medical image classification.

Information content and analysis methods for multi-modal high-throughput biomedical data

The spectrum of modern molecular high-throughput assaying includes diverse technologies such as microarray gene expression, miRNA expression, proteomics, DNA methylation, among many others. Now that these technologies have matured and become increasingly accessible, the next frontier is to collect "multi-modal" data for the same set of subjects and conduct integrative, multi-level analyses. While multi-modal data does contain distinct biological information that can be useful for answering complex biology questions, its value for predicting clinical phenotypes and contributions of each type of input remain unknown. We obtained 47 datasets/predictive tasks that in total span over 9 data modalities and executed analytic experiments for predicting various clinical phenotypes and outcomes. First, we analyzed each modality separately using uni-modal approaches based on several state-of-the-art supervised classification and feature selection methods. Then, we applied integrative multi-modal classification techniques. We have found that gene expression is the most predictively informative modality. Other modalities such as protein expression, miRNA expression, and DNA methylation also provide highly predictive results, which are often statistically comparable but not superior to gene expression data. Integrative multi-modal analyses generally do not increase predictive signal compared to gene expression data.

Key determinants of short-term and long-term glioblastoma survival: a 14-year retrospective study of patients from the Hermelin Brain Tumor Center at Henry Ford Hospital

OBJECTIVE

Glioblastoma (GBM) is a heterogeneous neoplasm with a small percentage of long-term survivors. Despite aggressive surgical resection and advances in radiotherapy and chemotherapy, the median survival for patients with GBM is 12-14 months. Factors associated with a favorable prognosis include young age, high performance status, gross resection >98%, non-eloquent tumor location and O6-methylguanine methyltransferase (MGMT) promoter methylation. We retrospectively analyzed the relationship of clinical, epidemiologic, genetic and molecular characteristics with survival in patients with GBM.

METHODS

This retrospective analysis of overall survival looked at the outcomes of 480 patients diagnosed with GBM over 14 years at a single institution. Multivariate analysis was performed examining multiple patient characteristics.

RESULTS

Median survival time improved from 11.8 months in patients diagnosed from 1995 to 1999 to 15.9 months in those diagnosed from 2005 to 2008. Factors associated with survivor groups were age, KPS, tumor resection, treatment received and early progression. 18 cancer-related genes were upregulated in short-term survivors and five genes were downregulated in short-term survivors.

CONCLUSIONS

Epidemiologic, clinical, and molecular characteristics all contribute to GBM prognosis. Identifying factors associated with survival is important for treatment strategies as well as research for novel therapeutics and technologies. This study demonstrated improved survival for patients over time as well as significant differences among survivor groups.

High-Performance Computational Analysis of Glioblastoma Pathology Images with Database Support Identifies Molecular and Survival Correlates

In this paper, we present a novel framework for microscopic image analysis of nuclei, data management, and high performance computation to support translational research involving nuclear morphometry features, molecular data, and clinical outcomes. Our image analysis pipeline consists of nuclei segmentation and feature computation facilitated by high performance computing with coordinated execution in multi-core CPUs and Graphical Processor Units (GPUs). All data derived from image analysis are managed in a spatial relational database supporting highly efficient scientific queries. We applied our image analysis workflow to 159 glioblastomas (GBM) from The Cancer Genome Atlas dataset. With integrative studies, we found statistics of four specific nuclear features were significantly associated with patient survival. Additionally, we correlated nuclear features with molecular data and found interesting results that support pathologic domain knowledge. We found that Proneural subtype GBMs had the smallest mean of nuclear Eccentricity and the largest mean of nuclear Extent, and MinorAxisLength. We also found gene expressions of stem cell marker MYC and cell proliferation maker MKI67 were correlated with nuclear features. To complement and inform pathologists of relevant diagnostic features, we queried the most representative nuclear instances from each patient population based on genetic and transcriptional classes. Our results demonstrate that specific nuclear features carry prognostic significance and associations with transcriptional and genetic classes, highlighting the potential of high throughput pathology image analysis as a complementary approach to human-based review and translational research.

Machine-based morphologic analysis of glioblastoma using whole-slide pathology images uncovers clinically relevant molecular correlates

Pathologic review of tumor morphology in histologic sections is the traditional method for cancer classification and grading, yet human review has limitations that can result in low reproducibility and inter-observer agreement. Computerized image analysis can partially overcome these shortcomings due to its capacity to quantitatively and reproducibly measure histologic structures on a large-scale. In this paper, we present an end-to-end image analysis and data integration pipeline for large-scale morphologic analysis of pathology images and demonstrate the ability to correlate phenotypic groups with molecular data and clinical outcomes. We demonstrate our method in the context of glioblastoma (GBM), with specific focus on the degree of the oligodendroglioma component. Over 200 million nuclei in digitized pathology slides from 117 GBMs in the Cancer Genome Atlas were quantitatively analyzed, followed by multiplatform correlation of nuclear features with molecular and clinical data. For each nucleus, a Nuclear Score (NS) was calculated based on the degree of oligodendroglioma appearance, using a regression model trained from the optimal feature set. Using the frequencies of neoplastic nuclei in low and high NS intervals, we were able to cluster patients into three well-separated disease groups that contained low, medium, or high Oligodendroglioma Component (OC). We showed that machine-based classification of GBMs with high oligodendroglioma component uncovered a set of tumors with strong associations with PDGFRA amplification, proneural transcriptional class, and expression of the oligodendrocyte signature genes MBP, HOXD1, PLP1, MOBP and PDGFRA. Quantitative morphologic features within the GBMs that correlated most strongly with oligodendrocyte gene expression were high nuclear circularity and low eccentricity. These findings highlight the potential of high throughput morphologic analysis to complement and inform human-based pathologic review.

Cancer Digital Slide Archive: an informatics resource to support integrated in silico analysis of TCGA pathology data

BACKGROUND

The integration and visualization of multimodal datasets is a common challenge in biomedical informatics. Several recent studies of The Cancer Genome Atlas (TCGA) data have illustrated important relationships between morphology observed in whole-slide images, outcome, and genetic events. The pairing of genomics and rich clinical descriptions with whole-slide imaging provided by TCGA presents a unique opportunity to perform these correlative studies. However, better tools are needed to integrate the vast and disparate data types.

OBJECTIVE

To build an integrated web-based platform supporting whole-slide pathology image visualization and data integration.

MATERIALS AND METHODS

All images and genomic data were directly obtained from the TCGA and National Cancer Institute (NCI) websites.

RESULTS

The Cancer Digital Slide Archive (CDSA) produced is accessible to the public (http://cancer.digitalslidearchive.net) and currently hosts more than 20,000 whole-slide images from 22 cancer types.

DISCUSSION

The capabilities of CDSA are demonstrated using TCGA datasets to integrate pathology imaging with associated clinical, genomic and MRI measurements in glioblastomas and can be extended to other tumor types. CDSA also allows URL-based sharing of whole-slide images, and has preliminary support for directly sharing regions of interest and other annotations. Images can also be selected on the basis of other metadata, such as mutational profile, patient age, and other relevant characteristics.

CONCLUSIONS

With the increasing availability of whole-slide scanners, analysis of digitized pathology images will become increasingly important in linking morphologic observations with genomic and clinical endpoints.

A high-performance spatial database based approach for pathology imaging algorithm evaluation

BACKGROUND

Algorithm evaluation provides a means to characterize variability across image analysis algorithms, validate algorithms by comparison with human annotations, combine results from multiple algorithms for performance improvement, and facilitate algorithm sensitivity studies. The sizes of images and image analysis results in pathology image analysis pose significant challenges in algorithm evaluation. We present an efficient parallel spatial database approach to model, normalize, manage, and query large volumes of analytical image result data. This provides an efficient platform for algorithm evaluation. Our experiments with a set of brain tumor images demonstrate the application, scalability, and effectiveness of the platform.

CONTEXT

The paper describes an approach and platform for evaluation of pathology image analysis algorithms. The platform facilitates algorithm evaluation through a high-performance database built on the Pathology Analytic Imaging Standards (PAIS) data model.

AIMS

(1) Develop a framework to support algorithm evaluation by modeling and managing analytical results and human annotations from pathology images; (2) Create a robust data normalization tool for converting, validating, and fixing spatial data from algorithm or human annotations; (3) Develop a set of queries to support data sampling and result comparisons; (4) Achieve high performance computation capacity via a parallel data management infrastructure, parallel data loading and spatial indexing optimizations in this infrastructure.

MATERIALS AND METHODS

WE HAVE CONSIDERED TWO SCENARIOS FOR ALGORITHM EVALUATION: (1) algorithm comparison where multiple result sets from different methods are compared and consolidated; and (2) algorithm validation where algorithm results are compared with human annotations. We have developed a spatial normalization toolkit to validate and normalize spatial boundaries produced by image analysis algorithms or human annotations. The validated data were formatted based on the PAIS data model and loaded into a spatial database. To support efficient data loading, we have implemented a parallel data loading tool that takes advantage of multi-core CPUs to accelerate data injection. The spatial database manages both geometric shapes and image features or classifications, and enables spatial sampling, result comparison, and result aggregation through expressive structured query language (SQL) queries with spatial extensions. To provide scalable and efficient query support, we have employed a shared nothing parallel database architecture, which distributes data homogenously across multiple database partitions to take advantage of parallel computation power and implements spatial indexing to achieve high I/O throughput.

RESULTS

Our work proposes a high performance, parallel spatial database platform for algorithm validation and comparison. This platform was evaluated by storing, managing, and comparing analysis results from a set of brain tumor whole slide images. The tools we develop are open source and available to download.

CONCLUSIONS

Pathology image algorithm validation and comparison are essential to iterative algorithm development and refinement. One critical component is the support for queries involving spatial predicates and comparisons. In our work, we develop an efficient data model and parallel database approach to model, normalize, manage and query large volumes of analytical image result data. Our experiments demonstrate that the data partitioning strategy and the grid-based indexing result in good data distribution across database nodes and reduce I/O overhead in spatial join queries through parallel retrieval of relevant data and quick subsetting of datasets. The set of tools in the framework provide a full pipeline to normalize, load, manage and query analytical results for algorithm evaluation.

Towards Building a High Performance Spatial Query System for Large Scale Medical Imaging Data

Support of high performance queries on large volumes of scientific spatial data is becoming increasingly important in many applications. This growth is driven by not only geospatial problems in numerous fields, but also emerging scientific applications that are increasingly data- and compute-intensive. For example, digital pathology imaging has become an emerging field during the past decade, where examination of high resolution images of human tissue specimens enables more effective diagnosis, prediction and treatment of diseases. Systematic analysis of large-scale pathology images generates tremendous amounts of spatially derived quantifications of micro-anatomic objects, such as nuclei, blood vessels, and tissue regions. Analytical pathology imaging provides high potential to support image based computer aided diagnosis. One major requirement for this is effective querying of such enormous amount of data with fast response, which is faced with two major challenges: the "big data" challenge and the high computation complexity. In this paper, we present our work towards building a high performance spatial query system for querying massive spatial data on MapReduce. Our framework takes an on demand index building approach for processing spatial queries and a partition-merge approach for building parallel spatial query pipelines, which fits nicely with the computing model of MapReduce. We demonstrate our framework on supporting multi-way spatial joins for algorithm evaluation and nearest neighbor queries for microanatomic objects. To reduce query response time, we propose cost based query optimization to mitigate the effect of data skew. Our experiments show that the framework can efficiently support complex analytical spatial queries on MapReduce.

Biological Interpretation of Morphological Patterns in Histopathological Whole-Slide Images

We propose a framework for studying visual morphological patterns across histopathological whole-slide images (WSIs). Image representation is an important component of computer-aided decision support systems for histopathological cancer diagnosis. Such systems extract hundreds of quantitative image features from digitized tissue biopsy slides and produce models for prediction. The performance of these models depends on the identification of informative features for selection of appropriate regions-of-interest (ROIs) from heterogeneous WSIs and for development of models. However, identification of informative features is hindered by the semantic gap between human interpretation of visual morphological patterns and quantitative image features. We address this challenge by using data mining and information visualization tools to study spatial patterns formed by features extracted from sub-sections of WSIs. Using ovarian serous cystadenocarcinoma (OvCa) WSIs provided by the cancer genome atlas (TCGA), we show that (1) individual and (2) multivariate image features correspond to biologically relevant ROIs, and (3) supervised image feature selection can map histopathology domain knowledge to quantitative image features.