Tumor Radiogenomics with Bayesian Layered Variable Selection

• Activity Number: 334 - Functional and Geometric Approaches for Imaging Data
• Type: Invited
• Date/Time: Thursday, August 12, 2021 : 10:00 AM to 11:50 AM
• Sponsor: Section on Statistics in Imaging
• Author(s): Shariq Mohammed* and Sebastian Kurtek and Karthik Bharath and Arvind Rao and Veerabhadran Baladandayuthapani
• Companies: University of Michigan and The Ohio State University and University of Nottingham and University of Michigan and University of Michigan
• Keywords: cancer driver genes; lower grade gliomas; radiogenomic associations; spike-and-slab prior

Abstract

We propose a statistical framework to integrate radiological magnetic resonance imaging (MRI) and genomic data to identify the underlying radiogenomic associations in lower grade gliomas (LGG). We devise a novel imaging phenotype by dividing the tumor region into concentric spherical layers that mimics the tumor evolution process. MRI data within each layer is represented by voxel--intensity-based probability density functions which capture the complete information about tumor heterogeneity. Under a Riemannian-geometric framework these densities are mapped to a vector of principal component scores which act as imaging phenotypes. Subsequently, we build Bayesian variable selection models for each layer with the imaging phenotypes as the response and the genomic markers as predictors. Our novel hierarchical prior formulation incorporates the interior-to-exterior structure of the layers, and the correlation between the genomic markers. We employ a computationally-efficient Expectation--Maximization-based strategy for estimation. With a focus on the cancer driver genes in LGG, we discuss some biologically relevant findings.