eTheses Repository

Texture analysis of multimodal magnetic resonance images in support of diagnostic classification of childhood brain tumours

Tantisatirapong, Suchada (2015)
Ph.D. thesis, University of Birmingham.

Loading
PDF (7Mb)Redacted Version

Abstract

Primary brain tumours are recognised as the most common form of solid tumours in children, with pilocytic astrocytoma, medulloblastoma and ependymoma being found most frequently. Despite their high mortality rate, early detection can be facilitated through the use of Magnetic Resonance Imaging (MRI), which is the preferred scanning technique for paediatric patients. MRI offers a variety of imaging sequences through structural and functional imaging, as well as providing complementary tissue information. However visual examination of MR images provides limited ability to characterise distinct histological types of brain tumours. In order to improve diagnostic classification, we explore the use of a computer-aided system based on texture analysis (TA) methods. TA has been applied on conventional MRI but has been less commonly studied on diffusion MRI of brain-related pathology. Furthermore, the combination of textural features derived from both imaging approaches has not yet been widely studied. In this thesis, the aim of the research is to investigate TA based on multi-centre multimodal MRI, in order to provide more comprehensive information and develop an automated processing framework for the classification of childhood brain tumours.

Type of Work:Ph.D. thesis.
Supervisor(s):Arvanitis, Theodoros N. and Peet, Andrew and Davies, Nigel
School/Faculty:Colleges (2008 onwards) > College of Engineering & Physical Sciences
Department:School of Electronic, Electrical and Computer Engineering
Subjects:RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry
TK Electrical engineering. Electronics Nuclear engineering
Institution:University of Birmingham
ID Code:5811
This unpublished thesis/dissertation is copyright of the author and/or third parties. The intellectual property rights of the author or third parties in respect of this work are as defined by The Copyright Designs and Patents Act 1988 or as modified by any successor legislation. Any use made of information contained in this thesis/dissertation must be in accordance with that legislation and must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the permission of the copyright holder.
Export Reference As : ASCII + BibTeX + Dublin Core + EndNote + HTML + METS + MODS + OpenURL Object + Reference Manager + Refer + RefWorks
Share this item :
QR Code for this page

Repository Staff Only: item control page