A Multi-Layered Approach for Detecting Alzheimer's Disease (AD) Using Deep Learning Model

Authors

  • Nutalapati Ashok Research Scholar, Department of CSE, Acharya Nagarjuna University
  • K. Gangadhara Rao Principal, University College of Science, Acharya Nagarjuna University, HOD, Department of CSE, Acharya Nagarjuna University

DOI:

https://doi.org/10.15379/ijmst.v10i3.3528

Keywords:

Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), and Single Photon Emission Computed Tomography (SPECT).

Abstract

Alzheimer's disease (AD) is a chronic brain disorder that affects the brain cells finally. The common cause of AD is dementia which reduces memory, thinking, behavior, and social skills. All these changes affect a person's ability to function. It is challenging to detect the disease in the early stages. Some of the most common diagnosing techniques are Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), and Single Photon Emission Computed Tomography (SPECT). These techniques provide information regarding the external and internal regions of the brain activities for diagnosing AD. Sometimes with the above methods, it is impossible to analyze AD accurately. The retina is a significant part of the eye which provides the vision to humans. Several studies made that the retina reveals that AD patients have some variations in the retina layers in addition to brain changes. Therefore, the retina becomes a biomarker for diagnosing AD. There are different techniques available for an eye examination. Most noticeable are Fundus Imaging and Optical Coherence Tomography (OCT). This paper introduces multi-layered Deep Learning (MLDL) to diagnose AD in the early stages from retinal abnormalities. Results show that the proposed approach achieved 98.7% accuracy in detecting AD.

Downloads

Download data is not yet available.

Downloads

Published

2023-08-22

How to Cite

[1]
N. . Ashok and K. G. . Rao, “A Multi-Layered Approach for Detecting Alzheimer’s Disease (AD) Using Deep Learning Model”, ijmst, vol. 10, no. 3, pp. 3701-3708, Aug. 2023.