Home WakeSpace Scholarship › Electronic Theses and Dissertations

Estimation of Dynamic Contrast-Enhanced MRI Kinetic Parameters in Glioblastoma Using Deep Learning.

Electronic Theses and Dissertations

Item Files

Item Details

abstract
Glioblastoma (GBM) is one of the most aggressive cancers, which is commonly characterized by increased angiogenesis, hypercellularity, and disrupted blood-brain-barrier (BBB). Dynamic Contrast-Enhanced (DCE) MRI is an emerging non-invasive MR imaging technique to assess the invasiveness of the tumor by studying BBB. By fully automating the generation of kinetic parameter maps, we can reduce the amount of data produced and also eliminate user bias. This project compares two approaches to generate kinetic parameter maps: extended Tofts (Ex-Tofts) model and a deep learning network.
subject
CNN
DCE MRI
Deep learning
GBM
mice
Tofts
contributor
Sankepalle, Deeksha Maheswari (author)
Zhao, Dawen (committee chair)
Weis, Jared (committee member)
Topaloglu, Umit (committee member)
date
2020-08-28T08:35:24Z (accessioned)
2020 (issued)
degree
Biomedical Engineering (discipline)
2021-08-27 (liftdate)
embargo
2021-08-27 (terms)
identifier
http://hdl.handle.net/10339/96946 (uri)
language
en (iso)
publisher
Wake Forest University
title
Estimation of Dynamic Contrast-Enhanced MRI Kinetic Parameters in Glioblastoma Using Deep Learning.
type
Thesis

Usage Statistics