Files in this item



application/pdfECE499-Sp2019-liang.pdf (937kB)Restricted to U of Illinois
(no description provided)PDF


Title:Machine learning approach to super-resolve brain segmentation results
Author(s):Liang, Yucheng
Contributor(s):Liang, Zhi-Pei
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.
Issue Date:2019-05
Date Available in IDEALS:2019-06-14

This item appears in the following Collection(s)

Item Statistics