Home WakeSpace Scholarship › Electronic Theses and Dissertations

Deep Learning Quantification of Vascular Permeability in Cancer

Electronic Theses and Dissertations

Item Files

Item Details

title
Deep Learning Quantification of Vascular Permeability in Cancer
author
Arledge, Chad
abstract
Magnetic resonance imaging (MRI) is a powerful noninvasive tool for assessing the tumor microenvironment. Advancements in MR techniques have increased noninvasive access to a significant amount of useful information on cancer metabolism and tumor heterogeneity, encompassing spatial, functional, and metabolic imaging. In particular, dynamic contrast enhanced (DCE) MRI has emerged as a quantitative standard for assessing tumor microvascular perfusion and permeability. Vascular permeability parameters derived from pharmacokinetic (PK) models applied to DCE MRI datasets have shown great promise for evaluating tumor vascular function and therapeutic response in both pre-clinical and clinical applications.
subject
Convolutional Neural Network
Deep Learning
Dynamic Contrast Enhanced MRI
Ensemble Learning
Generative Adversarial Network
Vascular Permeability
contributor
Zhao, Dawen (advisor)
Topaloglu, Umit (committee member)
Bourland, J. Daniel (committee member)
Chan, Michael D. (committee member)
Niazi, Khalid (committee member)
date
2025-06-24T08:36:39Z (accessioned)
2025 (issued)
degree
Biomedical Engineering (discipline)
embargo
2025-12-23 (terms)
2025-12-23 (liftdate)
identifier
http://hdl.handle.net/10339/111050 (uri)
language
en (iso)
publisher
Wake Forest University
type
Dissertation

Usage Statistics