Browsing by Author "Peterson, Christine B."

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Bayesian feature selection for radiomics using reliability metrics
    (Frontiers Media S.A., 2023) Shoemaker, Katherine; Ger, Rachel; Court, Laurence E.; Aerts, Hugo; Vannucci, Marina; Peterson, Christine B.
    Introduction: Imaging of tumors is a standard step in diagnosing cancer and making subsequent treatment decisions. The field of radiomics aims to develop imaging based biomarkers using methods rooted in artificial intelligence applied to medical imaging. However, a challenging aspect of developing predictive models for clinical use is that many quantitative features derived from image data exhibit instability or lack of reproducibility across different imaging systems or image-processing pipelines.Methods: To address this challenge, we propose a Bayesian sparse modeling approach for image classification based on radiomic features, where the inclusion of more reliable features is favored via a probit prior formulation.Results: We verify through simulation studies that this approach can improve feature selection and prediction given correct prior information. Finally, we illustrate the method with an application to the classification of head and neck cancer patients by human papillomavirus status, using as our prior information a reliability metric quantifying feature stability across different imaging systems.
  • Thumbnail Image
    Item
    Bayesian Inference of Multiple Gaussian Graphical Models
    (Taylor & Francis, 2015) Peterson, Christine B.; Stingo, Francesco C.; Vannucci, Marina
    In this article, we propose a Bayesian approach to inference on multiple Gaussian graphical models. Specifically, we address the problem of inferring multiple undirected networks in situations where some of the networks may be unrelated, while others share common features. We link the estimation of the graph structures via a Markov random field (MRF) prior, which encourages common edges. We learn which sample groups have a shared graph structure by placing a spike-and-slab prior on the parameters that measure network relatedness. This approach allows us to share information between sample groups, when appropriate, as well as to obtain a measure of relative network similarity across groups. Our modeling framework incorporates relevant prior knowledge through an edge-specific informative prior and can encourage similarity to an established network. Through simulations, we demonstrate the utility of our method in summarizing relative network similarity and compare its performance against related methods. We find improved accuracy of network estimation, particularly when the sample sizes within each subgroup are moderate. We also illustrate the application of our model to infer protein networks for various cancer subtypes and under different experimental conditions.
  • Thumbnail Image
    Item
    Investigating Multiple Candidate Genes and Nutrients in the Folate Metabolism Pathway to Detect Genetic and Nutritional Risk Factors for Lung Cancer
    (Public Library of Science, 2013) Swartz, Michael D.; Peterson, Christine B.; Lupo, Philip J.; Wu, Xifeng; Forman, Michele R.; Spitz, Margaret R.; Hernandez, Ladia M.; Vannucci, Marina; Shete, Sanjay
    Purpose: Folate metabolism, with its importance to DNA repair, provides a promising region for genetic investigation of lung cancer risk. This project investigates genes (MTHFR, MTR, MTRR, CBS, SHMT1, TYMS), folate metabolism related nutrients (B vitamins, methionine, choline, and betaine) and their gene-nutrient interactions. Methods: We analyzed 115 tag single nucleotide polymorphisms (SNPs) and 15 nutrients from 1239 and 1692 non-Hispanic white, histologically-confirmed lung cancer cases and controls, respectively, using stochastic search variable selection (a Bayesian model averaging approach). Analyses were stratified by current, former, and never smoking status. Results: Rs6893114 in MTRR (odds ratio [OR] = 2.10; 95% credible interval [CI]: 1.20–3.48) and alcohol (drinkers vs. non-drinkers, OR = 0.48; 95% CI: 0.26–0.84) were associated with lung cancer risk in current smokers. Rs13170530 in MTRR (OR = 1.70; 95% CI: 1.10–2.87) and two SNP*nutrient interactions [betaine*rs2658161 (OR = 0.42; 95% CI: 0.19–0.88) and betaine*rs16948305 (OR = 0.54; 95% CI: 0.30–0.91)] were associated with lung cancer risk in former smokers. SNPs in MTRR (rs13162612; OR = 0.25; 95% CI: 0.11–0.58; rs10512948; OR = 0.61; 95% CI: 0.41–0.90; rs2924471; OR = 3.31; 95% CI: 1.66–6.59), and MTHFR (rs9651118; OR = 0.63; 95% CI: 0.43–0.95) and three SNP*nutrient interactions (choline*rs10475407; OR = 1.62; 95% CI: 1.11–2.42; choline*rs11134290; OR = 0.51; 95% CI: 0.27–0.92; and riboflavin*rs8767412; OR = 0.40; 95% CI: 0.15–0.95) were associated with lung cancer risk in never smokers. Conclusions: This study identified possible nutrient and genetic factors related to folate metabolism associated with lung cancer risk, which could potentially lead to nutritional interventions tailored by smoking status to reduce lung cancer risk.
  • Thumbnail Image
    Item
    Latent Network Estimation and Variable Selection for Compositional Data Via Variational EM
    (Taylor & Francis, 2022) Osborne, Nathan; Peterson, Christine B.; Vannucci, Marina
    Network estimation and variable selection have been extensively studied in the statistical literature, but only recently have those two challenges been addressed simultaneously. In this article, we seek to develop a novel method to simultaneously estimate network interactions and associations to relevant covariates for count data, and specifically for compositional data, which have a fixed sum constraint. We use a hierarchical Bayesian model with latent layers and employ spike-and-slab priors for both edge and covariate selection. For posterior inference, we develop a novel variational inference scheme with an expectation–maximization step, to enable efficient estimation. Through simulation studies, we demonstrate that the proposed model outperforms existing methods in its accuracy of network recovery. We show the practical utility of our model via an application to microbiome data. The human microbiome has been shown to contribute too many of the functions of the human body, and also to be linked with a number of diseases. In our application, we seek to better understand the interaction between microbes and relevant covariates, as well as the interaction of microbes with each other. We call our algorithm simultaneous inference for networks and covariates and provide a Python implementation, which is available online.
  • Thumbnail Image
    Item
    Statistical Approaches for Interpretable Radiomics
    (2019-04-17) Shoemaker, Katherine; Peterson, Christine B.; Vannucci, Marina
    Imaging of tumors is a standard step in diagnosing cancer and making subsequent treatment decisions. The emerging field of radiomics aims to extract quantitative features from these images which can be used for downstream modeling. Much of the current work in radiomics relies on methods that do not lend themselves to communicating results to physicians. In order for radiomics to be used in clinically accepted tools, there is a motivation to move away from black box methods towards more interpretable approaches. In this thesis, we present two projects that aim to address the need for meaningful features in radiomic analyses. In the first project, we develop a hierarchical tree structure on the image pixels, creating a feature that captures intra-tumor heterogeneity. We demonstrate that this feature can be used in the classification of adrenal lesions. In the second project, to classify subjects on the basis of their radiomic features, we propose a Bayesian variable selection approach that favors the inclusion of more reliable features, and can additionally identify relevant genomic covariates if available. We apply this model to radiomic data from CT scans of head and neck cancer patients, using as our prior information a reliability metric obtained from a study on the impact of different scanners on feature stability.