Activity Number:
|
311
- Modern Statistical Methods for Imaging Genomics
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 5, 2020 : 10:00 AM to 11:50 AM
|
Sponsor:
|
Section on Statistics in Imaging
|
Abstract #312688
|
|
Title:
|
A Bayesian 2D Functional Linear Model: Application to GLCM Matrices in LGG Cancer Radiomics Data
|
Author(s):
|
Thierry Chekouo * and Shariq Mohammed and Arvind Rao
|
Companies:
|
University of Calgary and University of Michigan and University of Michigan
|
Keywords:
|
GLCM;
Functional data analysis;
Bayesian variable selection;
IDH
|
Abstract:
|
In cancer radiomics, textural-features evaluated from gray-level co-occurrence matrices (GLCM) have been studied to evaluate gray-level spatial dependence within region of interests in the brain. Most of these analysis work with summary statistics (or texture-based features), and potentially overlook other structural properties in the GLCM. In our proposed Bayesian framework, we treat each GLCM as a realization of a 2D stochastic functional process observed with error at discrete time points. The latent process is then combined with the outcome model to evaluate the prediction performance. We use simulation studies to assess the performance of our method and apply it to data collected from individuals with lower grade gliomas. We found our approach to outperform competing methods that do use only summary statistics to predict isocitrate dehydrogenase (IDH) mutation status.
|
Authors who are presenting talks have a * after their name.