Pet-based heterogeneity analysis: Strategies for radiomic feature selection
Okoro, Goodluck
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/125703
Description
Title
Pet-based heterogeneity analysis: Strategies for radiomic feature selection
Author(s)
Okoro, Goodluck
Issue Date
2024-07-16
Director of Research (if dissertation) or Advisor (if thesis)
Dobrucki, Wawrzyniec
Department of Study
Bioengineering
Discipline
Bioengineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Keyword(s)
Radiomics
feature selection
repeatability
heterogeneity analysis
positron emission tomography
Abstract
Although several radiomic features have been reported for heterogeneity analysis in Positron Emission Tomography (PET) imaging, there is a lack of standardization and consensus on the most appropriate set of heterogeneity parameters to use in different imaging applications. In this study, with computer-generated heterogeneous images and different heterogeneous phantom patterns, I used 20 widely reported repeatable radiomic features to investigate the impact of critical parameters such as image acquisition time, heterogeneous patterns, image resolution, reconstruction parameters, and choice of filter on repeatability and feature selection. My findings reveal the pivotal role of image acquisition time in influencing the reliability of radiomic features and heterogeneity calculations. Furthermore, by imaging a phantom over a duration of time and analyzing radiomic features at different time points, it is possible to capture the dynamics of feature stability in the context of changing acquisition times. With this methodology, I observed that certain intensity-based radiomic features exhibit greater stability amidst variations in imaging and post-processing parameters. I have also presented suggestions on possible ways to approach heterogeneity analysis for a more robust radiomic feature selection.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
