Integrative, Multimodal Analysis of Glioblastoma Using TCGA Molecular Data, Pathology Images, and Clinical Outcomes

Abstract

Multi-modal, multi-scale data synthesis is becoming increasingly critical for successful translational biomedical research. In this paper, we present a large-scale investigative initiative on glioblastoma, a high-grade brain tumor, with complementary data types using in silico approaches. We integrate and analyze data from The Cancer Genome Atlas Project on glioblastoma that includes novel nuclear phenotypic data derived from microscopic slides, genotypic signatures described by transcriptional class and genetic alterations, and clinical outcomes defined by response to therapy and patient survival. Our preliminary results demonstrate numerous clinically and biologically significant correlations across multiple data types, revealing the power of in silico multi-modal data integration for cancer research.

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

“…Image features and quantitative measures obtained from segmentation and classification can be used in downstream analyses that integrate information from clinical and molecular data and develop predictive and correlative models. Studies have shown the value of image analysis and image features in research, and an increasing number of research projects have developed image analysis methods to efficiently, accurately, and reliably convert raw image data into rich information and new knowledge (Gurcan et al, 2009;Foran et al, 2011;Kong et al, 2011;Kothari et al, 2012Kothari et al, , 2013Lambin et al, 2012;Gillies, 2013;Cheng et al, 2016;Coroller et al, 2016;Gao et al, 2016;Ishikawa et al, 2016;Madabhushi and Lee, 2016;Manivannan et al, 2016;Xing and Yang, 2016;Al-Milaji et al, 2017;Bakas et al, 2017c;Lehrer et al, 2017;Chang et al, 2018aChang et al, , 2019Fabelo et al, 2018;Hu et al, 2018;Khosravi et al, 2018;Lee et al, 2018;Mobadersany et al, 2018;Peikari et al, 2018;Saltz et al, 2018;Yonekura et al, 2018;Zhou et al, 2018). Recent work on biomedical image analysis focused on the development and application of machine learning methods, in particular, deep learning models.…”

“…Radiomics deals with the extraction, analysis, and interpretation of large sets of visual and sub-visual image features for organ-level quantification and classification of tumors (Lambin et al, 2012;Gillies, 2013;Aerts et al, 2014;Parmar et al, 2015;Gillies et al, 2016;Zwanenburg et al, 2016). The histopathologic examination of tissue, on the other hand, reveals the effects of cancer onset and progression at the sub-cellular level (Gurcan et al, 2009;Foran et al, 2011;Kong et al, 2011;Kothari et al, 2013;Griffin and Treanor, 2017;Yonekura et al, 2018). Histopathology has been used as a primary source of information for cancer diagnosis and prognosis.…”

Detecting the potential cancer association or metastasis by multi-omics data analysis

“…However, characterizing somatic mutations and their functional consequences in tumor tissues remains a challenge. With the rapid technological advances in acquiring data from diverse platforms in cancer research, numerous large scale datasets have become available, providing high resolution views and multi-faceted descriptions of biological systems (Kong et al, 2011). Accordingly, multilevel -omics data integration approaches will help researchers to uncover further systemic information about cancer associations and metastasis.…”

A framework for 3D vessel analysis using whole slide images of liver tissue sections

“…With the rapid and significant advances in large-throughput scanning technologies, digital pathology whole slide imaging has recently become an emerging tool not only promising for disease diagnosis and treatment evaluation, but also for high-throughput quantitative information extraction for a wide scope of diseases, ranging from brain (Han et al, 2011; Kong et al, 2011), breast (Petushi et al, 2006), lung (Xing and Yang 2013), colorectal, neuroblastoma (Kong et al, 2009), lymphoma (Cooper et al, 2009), to prostate cancer (Jafari-Khouzani and Soltanian-Zadeh, 2003; Tabesh et al, 2007). Importantly, this new field presents salient merits that help researchers and clinicians better understand the underlying biological mechanisms of pathological evolutions and progressions of distinct diseases (Jara-Lazaro et al, 2010; Kong et al, 2012).…”