Machine learning approach to super-resolve brain segmentation results
Liang, Yucheng
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/2142/104025
Description
Title
Machine learning approach to super-resolve brain segmentation results
Author(s)
Liang, Yucheng
Contributor(s)
Liang, Zhi-Pei
Issue Date
2019-05
Keyword(s)
super-resolution
machine learning
magnetic resonance spectroscopic imaging
image segmentation
Abstract
In magnetic resonance (MR) spectroscopic imaging, water and lipid suppression are often employed in order to detect the weak spectrum signal from metabolites. However, adding such to the sequence will prolong the scanning time, and the residual might still stay overwhelming. One possible alternative is to use a subspace-based nuisance signal removal method by data processing. Therefore, accurate and high-resolution masks of lipid and brain are urgently needed. In this work, we compared several super-resolution methods, and evaluated their efficacies for correctly predicting the high-resolution MR brain segmentation results. The training data is obtained by using the Statistical Parametric Mapping (SPM) toolbox on the Human Connectome Project (HCP) dataset. U-net results achieve the best human inspection rating. The result is also being tested in a nuisance signals removal pipeline.
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.
