The University of Southampton
University of Southampton Institutional Repository

Blood vessel shape description for detection of Alzheimer’s disease

Blood vessel shape description for detection of Alzheimer’s disease
Blood vessel shape description for detection of Alzheimer’s disease
Alzheimer’s disease (AD) is the most common form of dementia and is characterised by the deposition of aggregated proteins in neurofibrillary tangles or amyloid plaques within the vascular structure of the brain. Amyloid plaques consist of amyloid-beta (A?) in the extracellular spaces of the brain or in the walls of blood vessels, reflecting a failure to eliminate A? from the ageing brain. The failure to remove A? is potentially reflected in the vessels’ shape: vessel shape can improve or reduce fluid flow and thus drainage, according to tortuosity and other shape factors.

Neuropathological studies on post-mortem human tissue have described that the small vessels of aged brains are more tortuous compared to Young brains and tortuosity increases with the presence of Alzheimer pathology[1-4]. There is currently much interest in the diagnosis of AD, especially at the early stages where therapy could be better directed (or even deployed). The central aim of this thesis is to determine whether diagnosis is possible from image data, of brain tissue and MRI scans of the brain. We propose that the capillaries can be analysed as a branching structure, which appears to be a new analysis for medical images. The approach includes new measurements of the branching structure which are enriched by analysis of the vessels’ tortuosity and density. The introduction of measures of shape by compactness and Fourier descriptors further enriches this study.

The branching structures are detected by evidence gathering approaches and described by their structure. This allows recognition to be achieved; the structure of those samples derived from patients with AD differs from that for normal subjects. The descriptions can be classified using machine learning techniques, as such, achieving an automated process from image to recognition. We analysed the structure of the blood vessels in a database of brain tissue images collected from control, age-matched and patients with severe AD. The database comprises five subjects of each of the three types imaged in controlled conditions, and five MRI images of a normal brain from the Brain Tissue Resource of Newcastle UK. We show that by automated image analysis we are able to discriminate between brain tissue samples from patients presenting AD and from the normal samples.

We also show discriminative capability between posterior and anterior regions of the brain imaged in 3D by MRI. The branching structure is the description that is most suited for classification purposes. On this initial dataset, statistically significant differences (p=0.04) were seen between anterior and posterior and we can achieve 90% correct classification from a combination of these descriptions.

We are thus confident that these approaches are well suited to further investigation aiming for a diagnostic tool for clinical use in the assessment of possibility of Alzheimer’s disease.
Sahrim, Musab
9f93c355-4ebe-4ada-91a9-6eed03aa288e
Sahrim, Musab
9f93c355-4ebe-4ada-91a9-6eed03aa288e
Nixon, Mark
2b5b9804-5a81-462a-82e6-92ee5fa74e12

(2016) Blood vessel shape description for detection of Alzheimer’s disease. University of Southampton, Physical Sciences and Engineering, Doctoral Thesis, 129pp.

Record type: Thesis (Doctoral)

Abstract

Alzheimer’s disease (AD) is the most common form of dementia and is characterised by the deposition of aggregated proteins in neurofibrillary tangles or amyloid plaques within the vascular structure of the brain. Amyloid plaques consist of amyloid-beta (A?) in the extracellular spaces of the brain or in the walls of blood vessels, reflecting a failure to eliminate A? from the ageing brain. The failure to remove A? is potentially reflected in the vessels’ shape: vessel shape can improve or reduce fluid flow and thus drainage, according to tortuosity and other shape factors.

Neuropathological studies on post-mortem human tissue have described that the small vessels of aged brains are more tortuous compared to Young brains and tortuosity increases with the presence of Alzheimer pathology[1-4]. There is currently much interest in the diagnosis of AD, especially at the early stages where therapy could be better directed (or even deployed). The central aim of this thesis is to determine whether diagnosis is possible from image data, of brain tissue and MRI scans of the brain. We propose that the capillaries can be analysed as a branching structure, which appears to be a new analysis for medical images. The approach includes new measurements of the branching structure which are enriched by analysis of the vessels’ tortuosity and density. The introduction of measures of shape by compactness and Fourier descriptors further enriches this study.

The branching structures are detected by evidence gathering approaches and described by their structure. This allows recognition to be achieved; the structure of those samples derived from patients with AD differs from that for normal subjects. The descriptions can be classified using machine learning techniques, as such, achieving an automated process from image to recognition. We analysed the structure of the blood vessels in a database of brain tissue images collected from control, age-matched and patients with severe AD. The database comprises five subjects of each of the three types imaged in controlled conditions, and five MRI images of a normal brain from the Brain Tissue Resource of Newcastle UK. We show that by automated image analysis we are able to discriminate between brain tissue samples from patients presenting AD and from the normal samples.

We also show discriminative capability between posterior and anterior regions of the brain imaged in 3D by MRI. The branching structure is the description that is most suited for classification purposes. On this initial dataset, statistically significant differences (p=0.04) were seen between anterior and posterior and we can achieve 90% correct classification from a combination of these descriptions.

We are thus confident that these approaches are well suited to further investigation aiming for a diagnostic tool for clinical use in the assessment of possibility of Alzheimer’s disease.

PDF
Musab Sahrim revised thesis 5.0.pdf - Other
Download (7MB)

More information

Published date: January 2016
Organisations: University of Southampton, Vision, Learning and Control

Identifiers

Local EPrints ID: 388508
URI: http://eprints.soton.ac.uk/id/eprint/388508
PURE UUID: 8587511d-166c-465b-9a23-09e059dd2d50
ORCID for Mark Nixon: ORCID iD orcid.org/0000-0002-9174-5934

Catalogue record

Date deposited: 29 Feb 2016 12:28
Last modified: 06 Jun 2018 13:18

Export record

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×