Tumor Radiogenomics with Bayesian Layered Variable Selection

TL;DR

This paper introduces a Bayesian layered variable selection framework integrating MRI and genomic data to identify radiogenomic associations in lower grade gliomas, capturing tumor heterogeneity and evolution.

Contribution

It presents a novel imaging phenotype based on layered tumor regions and a hierarchical Bayesian model that incorporates tumor structure and gene correlations.

Findings

Genes associated with survival and oncogenesis identified in layers

Layered imaging phenotypes improve detection of tumor heterogeneity

Simulation shows superior performance over existing methods

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. Simulation studies demonstrate the superior performance of our approach compared to other approaches. With a focus on the cancer driver genes in LGG, we discuss some biologically relevant findings. Genes implicated with survival and oncogenesis are identified as being associated with the spherical layers, which could potentially serve as early-stage diagnostic markers for disease monitoring, prior to routine invasive approaches.