Details

Autor(en) / Beteiligte

• Mohammed, Shariq
• Kurtek, Sebastian
• Bharath, Karthik
• Rao, Arvind
• Baladandayuthapani, Veerabhadran

Titel

Tumor radiogenomics in gliomas with Bayesian layered variable selection

Ist Teil von

• Medical image analysis, 2023-12, Vol.90, p.102964-102964, Article 102964

Ort / Verlag

Netherlands: Elsevier B.V

Erscheinungsjahr

2023

Quelle

MEDLINE

Beschreibungen/Notizen

• We propose a statistical framework to analyze 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. We provide a R package that can be used to deploy our framework to identify radiogenomic associations. •We provide a novel Bayesian framework for imaging-genomic associations in gliomas.•We create novel tumor heterogeneity phenotypes from concentric spherical tumor layers.•Our prior integrates inner-to-outer tumor layer structure and genomic marker correlation.•We use an efficient Expectation-Maximization-based estimation and offer an R package.•Genes tied to survival and oncogenesis are linked to tumor layers, offering potential diagnostic markers. [Display omitted]