...

• VASARI Research Project - Multiple readers reviewing TCGA brain cases and evaluating them based on the VASARI feature set and evaluating the results for reader agreement along with possible connection to related clinical/genetic/pathology data collected for the TCGA.  This project is being led by Adam Flanders at Thomas Jefferson University.
• DSC T2* MR Perfusion Analysis - Survival prediction using molecular classification of glioblastomas using DSC T2* MR perfusion. This project has been accepted/presented at multiple conferences (see below) and is being led by Rajan Jain at Henry Ford Hospital.
• Prediction of outcome using clinical, imaging and genetic information - This project seeks to use the VASARI Research Project output in combination with data from the TCGA Data Portal to evaluate survival and time to recurrence.  This project is being led by Max Wintermark and Manal Nicolas Jilwan of the University of Virginia.
• Mapping of Edema/Cellular Invasion to MR Phenotypes - This project set out to present the first comprehensive radiogenomic analysis using quantitative MRI volumetrics and large-scale gene- and microRNA expression profiling in GBM.  This project was led by Pascal Zinn and Rivka Colen of MDACC and BWH respectively.
• Growth Kinetics - A collaboration between Andrew Trister at Sage Bionetworks and Kristin Swanson at the University of Washington to make measurements of tumor growth kinetics in two modes (diffusion and proliferation) from pretreatment MRIs.
• Man-machine correlation of VASARI features between human and machine observers - This project is being led by Dave Gutman (Emory) and Rivka Colen (BWH).
• Analysis of Diffusion-Sensitized MRI for Predicting the Histopathologic, Genomic, and Clinical Features - This is a newer project being initiated and led by Scott Hwang at Emory University
• CAD Texture Analysis - Led by Ashlee Byrd and Brad Erickson at Mayo, they are using multispectral features, including intensity, texture, and morphology, to identify imaging features that predict genetic patterns.
• Clustering (supervised & unsupervised) of GBM cases into semantically-distinct categories using image-derived features, followed by examination of genomic correlates from the obtained clusters.  Led by Arvind Rao, Dave Gutman, and Adam Flanders.
• Stanford TCGA radiogenomics project:  We are studying computational image features that characterize shape, texture and size of glioblastoma multiforme patients. More specifically, we extract computational image features from MRI images and investigate their clinical relevance and correlation with molecular data.  Investigators: Olivier Gevaert, Sylvia Plevritis.

Publications

...