Georgia Institute of Technology
Optimizing reconstruction and segmentation of free-breathing whole-heart CMR to enable clinical implementation
Abstract
dc:description.abstractOptimizing reconstruction and segmentation of free-breathing whole-heart CMR to enable clinical implementation Yitong Yang 117 Pages Directed by Dr. John N. Oshinski Cardiac disease is the leading cause of death in the United States. Although bedside ultrasound is convenient to use and computational tomography (CT) has high spatial resolution, magnetic resonance imaging remains the gold-standard for assessing cardiac function in non-invasive diagnostic imaging. With the development of free-breathing and ECG free whole-heart cardiac magnetic resonance (CMR) imaging, CMR image acquisition is greatly simplified requiring only placing a planning box around a heart. However, the process from data acquisition to image formation, or the image reconstruction, is currently a bottleneck in applying this technology to the clinical environment. This thesis aims to tackle this challenge of long reconstruction times and labor-intensive downstream image analysis and illustrate the clinical significance of such technology in characterizing right heart functional changes during respiration on pediatric congenital heart disease. In this thesis, the specific aims are: 1) develop and apply numerical and machine learning-based techniques to streamline the reconstruction and functional analysis of motion-resolved whole-heart CMR; 2) investigate respiratory variation of right heart function and hemodynamics using 5D flow on healthy and pediatric congenital heart disease patients. By developing accelerated reconstruction and segmentation methods, this work advances the clinical translation of 5D free-running CMR for free-breathing, whole-heart, motion-resolved imaging.
Degree
thesis:*- Name thesis:degree_name
- Biomedical Engineering, PhD
- Department thesis:degree_department
- Biomedical Engineering (Joint GT/Emory Department)
- Grantor
- Georgia Institute of Technology
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Yang, Yitong
- Advisor dc:contributor.advisor
-
- Oshinski, John N.
- Committee members dc:contributor.committeemember
-
- Eva Dyer
- Matthias Chung
- Matthias Stuber
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/81724