An Approach to Classify Alzheimer’s Disease using Vision Transformers

Drewitt, Anitha (2023) An Approach to Classify Alzheimer’s Disease using Vision Transformers. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Over the past decades, different deep-learning approaches in Medical Imaging have shown promising results and performance. Classifying the stages of a disease and thus its early treatment may avoid its further spread resulting in a reduced fatality rate. A neurodegenerative condition called Alzheimer’s disease (AD) is likely to grow, spread, and deteriorate. It causes our brain cells to die leading to complete loss of memory and physical impairment. According to estimates, nearly 6 million Americans aged 65 and older have Alzheimer’s disease, which is a prominent cause of death in developing nations. The study investigates a novel approach for classifying Alzheimer’s disease called ”Vision Transformer”. The research employs publicly available datasets on Kaggle by classifying images into four stages which are Mild Demented, Very Mild Demented, Non-Demented, and Moderate Demented and the accuracy obtained from the model is compared with other deep learning approaches and the limitations and future scope of this research methodology are presented. Accuracy and F1-Score has been used to evaluate the performance of the model. The model has an accuracy rate of 87.5% and a loss of 0.34 in classifying Alzheimer’s disease. On comparing the model with the other historical CNN methods, the algorithm has produced encouraging results for classifying AD and it can be enhanced for wider application. The proposed model can help the physician to classify AD and provide treatment to the affected person which can eventually help in reducing the fatal rate.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Ul Ain, Qurrat UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	17 May 2023 16:54
Last Modified:	17 May 2023 16:54
URI:	https://norma.ncirl.ie/id/eprint/6583

Actions (login required)

View Item