search query: @supervisor Oja, Erkki / total: 113
reference: 16 / 113
« previous | next »
Author:Cao, Yang
Title:Multi-variate analysis of brain images in seasonal affective disorder
Publication type:Master's thesis
Publication year:2013
Pages:63 s. + liitt. 6      Language:   eng
Department/School:Perustieteiden korkeakoulu
Main subject:Informaatiotekniikka   (T-61)
Supervisor:Oja, Erkki
Instructor:Leemput, Koen Van
OEVS:
Electronic archive copy is available via Aalto Thesis Database.
Instructions

Reading digital theses in the closed network of the Aalto University Harald Herlin Learning Centre

In the closed network of Learning Centre you can read digital and digitized theses not available in the open network.

The Learning Centre contact details and opening hours: https://learningcentre.aalto.fi/en/harald-herlin-learning-centre/

You can read theses on the Learning Centre customer computers, which are available on all floors.

Logging on to the customer computers

  • Aalto University staff members log on to the customer computer using the Aalto username and password.
  • Other customers log on using a shared username and password.

Opening a thesis

  • On the desktop of the customer computers, you will find an icon titled:

    Aalto Thesis Database

  • Click on the icon to search for and open the thesis you are looking for from Aaltodoc database. You can find the thesis file by clicking the link on the OEV or OEVS field.

Reading the thesis

  • You can either print the thesis or read it on the customer computer screen.
  • You cannot save the thesis file on a flash drive or email it.
  • You cannot copy text or images from the file.
  • You cannot edit the file.

Printing the thesis

  • You can print the thesis for your personal study or research use.
  • Aalto University students and staff members may print black-and-white prints on the PrintingPoint devices when using the computer with personal Aalto username and password. Color printing is possible using the printer u90203-psc3, which is located near the customer service. Color printing is subject to a charge to Aalto University students and staff members.
  • Other customers can use the printer u90203-psc3. All printing is subject to a charge to non-University members.
Location:P1 Ark Aalto  7113   | Archive
Keywords:neuroimaging
univariate method
multivariate method
sparse learning
SVMs
VMB
RVM
RVoxM
SPM
seasonal affective disorder
Abstract (eng): In this dissertation, I present different approaches of statistical analysis which can be used in medical research for both structural magnetic imaging and functional imaging.
In particular, I study univariate and multivariate methods and experimented using brain imaging data.

Methods mainly talked in my thesis are voxel-based morphometry (VBM), support vector machine (SVM), relevance vector machine (RVM), and relevance voxel machine (RVoxM).
VBM is a widely used univariate method which is already implanted in the software of MATLAB within the SPM package.
SVM and RVM are two existing multi-variate methods which can solve both classification and regression problems regarding to the brain image scans, and the differences between these two methods are such that the first one is easier to handle in practice while the latter offers more sparse results.
Another multi-variate analysis method RVoxM takes neighbourhood into consideration when comparing with RVM and therefore offers a more reasonable way to think about the future of neuroimaging, especially in the field of functional imaging.
Thus in the first part of my thesis, I introduce the methodology of the univariate method and multivariate methods.
Together with methodology, I provide the comparison of each approach.

As theory should serve for practice, in the second part of my thesis, I describe the experiments I have done using the mentioned methods with anatomical data and functional data.
I focus on seasonal affective disorder (SAD) when facing functional imaging problem, for the situation of SAD in Finland is quite severe.
After that I offer a discussion and conclusion.

All in all, the univariate and multi-variate methods do excellent jobs in solving neuroimaging problems.
In the future, the theory will be more mature and so is the corresponding implementation of engineering.
ED:2013-02-25
INSSI record number: 45846
+ add basket
« previous | next »
INSSI