Novel genotype-phenotype associations in human cancers enabled by advanced molecular platforms and computational analysis of whole slide images

Abstract

Technological advances in computing, imaging and genomics have created new opportunities for exploring relationships between histology, molecular events and clinical outcomes using quantitative methods. Slide scanning devices are now capable of rapidly producing massive digital image archives that capture histological details in high-resolution. Commensurate advances in computing and image analysis algorithms enable mining of archives to extract descriptions of histology, ranging from basic human annotations to automatic and precisely quantitative morphometric characterization of hundreds of millions of cells. These imaging capabilities represent a new dimension in tissue-based studies, and when combined with genomic and clinical endpoints, can be used to explore biologic characteristics of the tumor microenvironment and to discover new morphologic biomarkers of genetic alterations and patient outcomes. In this paper we review developments in quantitative imaging technology and illustrate how image features can be integrated with clinical and genomic data to investigate fundamental problems in cancer. Using motivating examples from the study of glioblastomas (GBMs), we demonstrate how public data from The Cancer Genome Atlas (TCGA) can serve as an open platform to conduct in silico tissue based studies that integrate existing data resources. We show how these approaches can be used to explore the relation of the tumor microenvironment to genomic alterations and gene expression patterns and to define nuclear morphometric features that are predictive of genetic alterations and clinical outcomes. Challenges, limitations and emerging opportunities in the area of quantitative imaging and integrative analyses are also discussed.

Integrative Analysis of Histopathological Images and Genomic Data Predicts Clear Cell Renal Cell Carcinoma Prognosis

“…Therefore, an interesting scientific question is the relationship between morphologic and genomic features while an important translational question is if the integration of these two types of features can lead to more accurate prediction of patient outcome. This has been previously explored in various cancers including breast, ovarian, and glioblastoma, and led to new insights into the relationship between cancer tissue morphology and genetic changes such as PTEN mutations (3,(11)(12)(13).…”

Localization of Diagnostically Relevant Regions of Interest in Whole Slide Images: a Comparative Study

“…Histopathological image analysis research tackles many problems related to diagnosis of the disease, including nucleus detection [3][4][5][6][7], prediction of clinical variables (diagnosis [8][9][10][11][12], grade [13][14][15][16][17][18], survival time [19][20][21]), identification of genetic factors controlling tumor morphology (gene expression [20,22], molecular subtypes [20,23]), and localization of ROIs [24][25][26][27][28]. One of the major research directions in histopathological image analysis is to develop image features for different problems and image types.…”

Discriminative bag-of-cells for imaging-genomics

“…3,4 Additionally, 'imaging-genomics' has been coined to refer to recent developments in leveraging new insights gained from genomics with traditional imaging of radiology or histopathology. [5][6][7][8] For histopathological images, features of cells and nuclei, which are used by pathologists to diagnose cancer, provide the most direct connection to the genomic signatures of a patient's tumor. Yet whole slide images (WSIs) contain tens of thousands of cells with diverse characteristics, which makes associating phenotype with genomics challenging.…”

“…Previous works in imaging-genomics have sought to draw connections by first clustering nuclei and cells into types in an unsupervised fashion and then associating with genomic markers, such as gene expression. 5,7,8 Others have looked for connections with specific cell types, leveraging biological understanding, such as the affect of the cellularity of lymphocytes on copy number variation in tumors. 6 There remains a need for machine learning tools that can effectively capture the diversity of cellular phenotypes within and across tumors for high-throughput investigation of general image-genomic associations.…”