The Woodruff School

SUMMARY

Glioblastoma (GBM) is the most aggressive glioma with poor prognosis due to its heterogeneity. The purpose of this study is to improve the tissue characterization of these highly heterogeneous tumors using delta-radiomic features of dynamic susceptibility contrast enhanced (DSC) MR images, which are commonly used to derive blood perfusion to the tumor, with machine learning approaches.

SUBJECT:	M.S. Thesis Presentation

BY:	Jiwoong Jeong

TIME:	Monday, April 23, 2018, 10:00 a.m.

PLACE:	Boggs, 3-47

TITLE:	Machine-Learning-Based Classification of Gliblastoma Using Dynamic Susceptibility Enhanced MR Image Derived Delta-Radiomic Features

COMMITTEE:	Dr. C-K Wang, Co-Chair (ME) Dr. Xiaofeng Yang, Co-Chair (ME) Dr. Eric Elder (ME) Dr. Tian Liu (Emory)

SUMMARY Glioblastoma (GBM) is the most aggressive glioma with poor prognosis due to its heterogeneity. The purpose of this study is to improve the tissue characterization of these highly heterogeneous tumors using delta-radiomic features of dynamic susceptibility contrast enhanced (DSC) MR images, which are commonly used to derive blood perfusion to the tumor, with machine learning approaches.