Gupta, Monideepa (2020) Cluster Analysis of FDG-PET Imaging of a Dementia Cohort. Master's Thesis / Essay, Biomedical Engineering.
|
Text
mBME_2020_MDGupta.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (139kB) |
Abstract
Dementia refers to a clinical syndrome characterized by a progressive cognitive decline that interferes with the ability to function independently. Alzheimer’s disease(AD) is the most common subtype of dementia. It is a neurodegenerative disease causing dementia, which comprises about 60% to 80% of cases. The sensitivity and specificity of the clinical diagnosis of these conditions suggest a substantial amount of misdiagnosis. The objective of this study was to perform a quantitative analysis of FDG-PET images, a reliable biomarker showing synaptic dysfunction and neurodegeneration, from patients experiencing dementia. This study will form a basis to explore the potential of eventually developing a classification model. For this, two clustering analysis, HCA and K-means were investigated, first, on the data matrix of Healthy controls and AD and later mild cognitive impairment, an objective cognitive impairment condition with the preserved function, subject type was also included. Principal component analysis, a feature extraction unsupervised machine learning algorithm, was performed to transform the high dimensional image to low dimensional principal component space, to be then used for clustering. K-means clustering resulted in a good separation between Healthy controls and Alzheimer’s disease.From the results, it can be inferred that quantitative analysis of functional images from dementia cohort holds potential to be utilized in the development of a classification model.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Willemsen, A.T.M. and Peretti, D.E. |
| Degree programme: | Biomedical Engineering |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 28 Aug 2020 12:57 |
| Last Modified: | 28 Aug 2020 12:57 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/23272 |
Actions (login required)
 |
View Item |