Browsing by Author "Shoemaker, Katherine"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
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.Item Hierarchical Normalized Completely Random Measures for Robust Graphical Modeling(Project Euclid, 2019) Cremaschi, Andrea; Argiento, Raffaele; Shoemaker, Katherine; Peterson, Christine; Vannucci, MarinaGaussian graphical models are useful tools for exploring network structures in multivariate normal data. In this paper we are interested in situations where data show departures from Gaussianity, therefore requiring alternative modeling distributions. The multivariate t-distribution, obtained by dividing each component of the data vector by a gamma random variable, is a straightforward generalization to accommodate deviations from normality such as heavy tails. Since different groups of variables may be contaminated to a different extent, Finegold and Drton (2014) introduced the Dirichlet t-distribution, where the divisors are clustered using a Dirichlet process. In this work, we consider a more general class of nonparametric distributions as the prior on the divisor terms, namely the class of normalized completely random measures (NormCRMs). To improve the effectiveness of the clustering, we propose modeling the dependence among the divisors through a nonparametric hierarchical structure, which allows for the sharing of parameters across the samples in the data set. This desirable feature enables us to cluster together different components of multivariate data in a parsimonious way. We demonstrate through simulations that this approach provides accurate graphical model inference, and apply it to a case study examining the dependence structure in radiomics data derived from The Cancer Imaging Atlas.Item Statistical Approaches for Interpretable Radiomics(2019-04-17) Shoemaker, Katherine; Peterson, Christine B.; Vannucci, MarinaImaging 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.