City Research Online

Quantitative texture analysis in MR imaging in the assessment of Alzheimer’s disease

Leandrou, S. (2021). Quantitative texture analysis in MR imaging in the assessment of Alzheimer’s disease. (Unpublished Doctoral thesis, City, University of London)

Abstract

Alzheimer’s disease (AD) is a progressive neurodegenerative disease which is clinically characterized by cognitive impairment and memory loss. Anatomically, AD initially affects specific structures within the Medial Temporal Lobe (MTL), which are essential for declarative memory. A definitive diagnosis of AD relies on post-mortem biopsy therefore, clinical assessment and cognitive tests are currently used. However, these tests are not sensitive to detect AD in an early stage.

The aim of this research was to investigate the usefulness of quantitative Magnetic Resonance Imaging (MRI) and specifically of texture features in the assessment of Mild Cognitive Impairment (MCI) which is the pre-dementia stage and AD. Firstly, two types of magnetic fields where investigated in order to examine whether, a stronger MR magnetic field would benefit quantitative imaging analysis derived from texture features. Secondly, texture features were extracted from the entorhinal cortex and evaluated in the diagnosis and prediction of MCI and AD. To the best of our knowledge this is the first research that investigated how the MR field strength affects texture features and used entorhinal cortex texture features on the assessment of AD.

The main results of this PhD showed that (1) texture features could provide more sensitive measures when they are extracted from stronger MRI magnetic field, such as 3T, compared to 1.5T. From a disease classification and prediction perspective, (2) entorhinal cortex texture features provide better classification between Normal Controls (NC), MCI and AD subjects, and (3) better prediction of the conversion from MCI to AD. In conclusion, this research has shown for the first time in the literature that entorhinal cortex texture features from MRI could contribute towards the early classification of AD.

Publication Type: Thesis (Doctoral)
Subjects: R Medicine > RZ Other systems of medicine
T Technology > TA Engineering (General). Civil engineering (General)
Departments: Doctoral Theses
Doctoral Theses > School of Mathematics, Computer Science and Engineering Doctoral Theses
School of Mathematics, Computer Science & Engineering > Computer Science > Human Computer Interaction Design
Date available in CRO: 20 Jul 2021 09:41
Date deposited: 20 July 2021
URI: https://openaccess.city.ac.uk/id/eprint/26475
[img]
Preview
Text - Accepted Version
Download (2MB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login