Alzheimer's disease diagnosis based on feature extraction using optimised crow search algorithm and deep learning
by Sonal Bansal; Aditya Rustagi; Anupam Kumar
International Journal of Computer Applications in Technology (IJCAT), Vol. 65, No. 4, 2021

Abstract: Alzheimer's Disease (AD) is long-term, progressive, degenerative cognitive illness and one of the causes of dementia. Dementia impairs an individual's ability to think, disrupting normal functioning. Conventional method of diagnosis is collecting symptoms from family members to analyse its impact and stage. MRIs are currently used worldwide for diagnosis and understanding how brain works. With recent advances in applying machine learning to medical images like MRI, it has become a key research discipline amongst experts and analysts. Existing methods of feature extraction from images include CNN, providing large number of feature sets that require great computation power and time to evaluate using traditional machine learning or deep learning algorithms. Consequently, we propose an Optimised Crow Search Algorithm (OCSA) for early detection of AD based on raw MRI image features, yielding a highly representative dense embedding. The mapping learned between this embedding and image labels resulted in diagnosing 98.62% accuracy.

Online publication date: Tue, 31-Aug-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com