High-resolution image analysis of digitized pathology slides coupled with molecular data has enormous potential to provide additional information for stratifying patients in terms of prognosis and therapy. We propose to develop methods, analytic pipelines, and data management tools that will make it feasible to systematically carry out large-scale comparative analyses of brain tumor histological features and of patterns of protein and gene expression. We will develop information models to manage information associated with analysis of brain tumor whole virtual slide data. These models will capture information about context relating to patient data, specimen preparation, and special stains, human observations involving histological classification and characteristics, algorithmic composition, parameterization and input data corresponding to analysis pipelines, and algorithm and human-described segmentations, features, and classifications. We will implement middleware for high-performance database and query support for queries that selects subsets of image data and results based on metadata on images and provenance information; that compare features, spatial structures, and classifications obtained from multiple algorithms as well as human markups; and that compare statistical and summary information on features and classifications across multiple image datasets. Using the information models and middleware, we will carry out analysis studies needed to determine the relationship between image analysis derived tumor information and clinical outcome, gene expression category, genetic gains and losses, and methylation status. We will employ a novel automated multiplex quantum dot immunohistochemistry with peptide controls and quantitative image analysis methodology to map the activity of signal transduction pathways and transcriptional networks relative to the tumor microenvironment using histology feature descriptions. We will leverage multivariate data fusion techniques to simultaneously take into account potential correlations and relationships among the measured image features, molecular signatures to predict patient outcomes. We will deploy a data repository populated with images, features, analysis pipelines, provenance information, and analytic results from our project. This repository will provide a publicly available resource for brain tumor research. All software and information models developed in this project will be open source and free for research use.

Public Health Relevance

High-resolution image analysis of digitized pathology slides coupled with molecular data has enormouspotential to provide additional information for stratifying patients in terms of prognosis and therapy. We proposeto develop methods; analytic pipelines; and data management tools that will make it feasible to systematicallycarry out large-scale comparative analyses of brain tumor histological features and of patterns of protein andgene expression. We will deploy a data repository populated with images; features; and analytic results fromour project that will provide a publicly available resource for brain tumor research.

Agency
National Institute of Health (NIH)
Institute
National Library of Medicine (NLM)
Type
Research Project (R01)
Project #
7R01LM011119-04
Application #
8791364
Study Section
Special Emphasis Panel (ZLM1-ZH-C (01))
Program Officer
Ye, Jane
Project Start
2011-07-01
Project End
2015-05-31
Budget Start
2014-01-09
Budget End
2014-05-31
Support Year
Fiscal Year
2014
Total Cost
$326,868
Indirect Cost
$84,408
Name
State University New York Stony Brook
Department
Type
DUNS #
804878247
City
Stony Brook
State
NY
Country
United States
Zip Code
11794
Boregowda, Rajeev K; Medina, Daniel J; Markert, Elke et al. (2016) The transcription factor RUNX2 regulates receptor tyrosine kinase expression in melanoma. Oncotarget 7:29689-707
Hou, Le; Samaras, Dimitris; Kurc, Tahsin M et al. (2016) Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2016:2424-2433
Yildirim, Esma; Foran, David (2016) Parallel vs. Distributed Data Access for Giga-pixel-resolution Histology Images: Challenges and Opportunities. IEEE J Biomed Health Inform :
Gao, Yi; Ratner, Vadim; Zhu, Liangjia et al. (2016) Hierarchical nucleus segmentation in digital pathology images. Proc SPIE Int Soc Opt Eng 9791:
Gao, Yi; Liu, William; Arjun, Shipra et al. (2016) Multi-scale learning based segmentation of glands in digital colonrectal pathology images. Proc SPIE Int Soc Opt Eng 9791:
Kurc, Tahsin; Qi, Xin; Wang, Daihou et al. (2015) Scalable analysis of Big pathology image data cohorts using efficient methods and high-performance computing strategies. BMC Bioinformatics 16:399
Su, Hai; Shen, Yong; Xing, Fuyong et al. (2015) Robust automatic breast cancer staging using a combination of functional genomics and image-omics. Conf Proc IEEE Eng Med Biol Soc 2015:7226-9
Almeida, Jonas S; Hajagos, Janos; Crnosija, Ivan et al. (2015) OpenHealth Platform for Interactive Contextualization of Population Health Open Data. AMIA Annu Symp Proc 2015:297-305
Gomes, Jeremias M; Teodoro, George; de Melo, Alba et al. (2015) Efficient irregular wavefront propagation algorithms on Intel(®) Xeon Phi(™). Proc Symp Comput Archit High Perform Comput 2015:25-32
Wang, Daihou; Foran, David J; Ren, Jian et al. (2015) Exploring automatic prostate histopathology image Gleason grading via local structure modeling. Conf Proc IEEE Eng Med Biol Soc 2015:2649-52

Showing the most recent 10 out of 56 publications