Back to search

Cornell University

Inverse Problem In Quantitative Susceptibility Mapping: Numerical And Machine Learning Approaches

Abstract

dc:description.abstract

Magnetic susceptibility reflects the concentration of bio-metal elements such as iron, calcium or gadolinium, providing means to investigate diseases such as multiple sclerosis, Alzheimer’s disease, hemorrhage and calcification. Numerous approaches have been proposed to provide magnetic susceptibility estimation from magnetic resonance imaging (MRI). While those methods are designed for specific body parts or pathologies, a unified framework is elusive from literature for reliable susceptibility estimation in both normal and pathological scenarios. This thesis developed algorithms that improve the accuracy, robustness and applicability of quantitative susceptibility mapping (QSM) for both healthy and pathological subjects. First, a dedicated regularized model was proposed to enable automated zero reference for QSM using cerebrospinal fluid. Second, convolutional neural network was combined with numerical optimization for superior anatomical contrast in QSM reconstruction. Finally, a total field inversion approach was presented to enable QSM for both healthy subject and hemorrhage patient. With the technical advances in this thesis, QSM requires less manual effort in susceptibility quantification, admits detailed recovery of anatomical structures and applies to both healthy subject and patient via a unified framework.

Degree

thesis:*
Name thesis:degree_name
Ph.D., Biomedical Engineering
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Biomedical Engineering
Grantor
Cornell University
Year dc:date.issued
2019

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Liu, Zhe
Chair dc:contributor.chair
  • Wang, Yi
Committee member dc:contributor.committeemember
  • Doerschuk, Peter

Subjects

dc:subject × 7

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Dc Identifier Bibid
11050460
Dc Identifier Other
ProQuest Submission ID: 11290
ProQuest Publication ID: 13428363

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Liu, Zhe. Inverse Problem In Quantitative Susceptibility Mapping: Numerical And Machine Learning Approaches. Doctor of Philosophy thesis, Cornell University, 2019. https://hdl.handle.net/1813/67478