© 2022 Ragavamsi Davuluri and Ragupathy Rengaswamy. This open-access article is distributed under a Creative Commons
Attribution (CC-BY) 4.0 license.
Journal of Computer Science
Journal of Computer Science
Original Research Paper
Improved Classification Model using CNN for Detection of
Alzheimer’s Disease
Ragavamsi Davuluri and Ragupathy Rengaswamy
Department of Computer Science and Engineering, Annamalai University, Chidambaram, Tamil Nadu, India
Article history
Received: 26-03-2022
Revised: 19-04-2022
Accepted: 07-05-2022
Corresponding Author:
Ragavamsi Davuluri
Department of Computer Science
and Engineering, Annamalai
University, Chidambaram, Tamil
Nadu, India
E-mail: raaga.vamsi@gmail.com
Abstract: Alzheimer’s Disease (AD) is commonly called a
neurodegenerative disorder and it is a common form of dementia. There is
no permanent cure for this brain disease hence the early diagnosis of such
disease using medical imaging system is highly significant. Machine
learning models play a vital role in the detection of AD. Since most of the
conventional machine learning models find it difficult to detect the
essential features to classify the disease, an advanced deep learning
framework called Convolutional Neural Network (CNN) is used in this
study to detect essential features automatically and classify the disease. The
building components of the proposed CNN-based classification method
include convolution layer, batch normalization process, ReLU, and Max-
pooling operation. The main objective of this CNN-based classification
method is to predict whether the patient is suffering from Alzheimer's
disease through the analysis of brain MRI. The proposed methodology
implemented is identical to a classification-based system that undergoes
training, evaluation, and testing process. Finally, the softmax layer is applied
for classification, and the Adam optimization technique is applied for reducing
the loss, and by applying Adam quicker convergence can be achieved. The
proposed improved CNN classification method achieves an accuracy of 97.8%.
Keywords: Alzheimer’s Disease Detection, Magnetic Resonance Imaging,
Convolution Neural Network, Deep Learning
Introduction
Alzheimer's disease is a neuropsychiatric ailment that
causes memory loss in persons over the age of 65.
Alzheimer's disease affects 50 million people worldwide,
with the number expected to nearly quadruple by
2050.The aberrant build-up of proteins in and around
brain cells is assumed to be the origin of AD. The brain
tissues get damaged due to Alzheimer’s disease and it may
lead to nerve cell death if it was not diagnosed in its earlier
stages. AD leads to memory loss and also disrupts the
human body's functions like speaking, writing, and
reading. Alzheimer's disease patients usually suffer from
lung dysfunction, malnutrition, cognitive impairment
(Soysal et al., 2014), and functional dependence. Precise
and accurate detection of AD is quietly not possible since
improper medications are required. Detection of AD in its
earlier stages (also called a pre-clinical stage) can save the
patient's life and also helps in the retreatment process
(Dubois et al., 2016). The symptoms of AD will develop
slowly but the defection effects are severe when it starts
in the human brain (Picón et al., 2019). Several medical
tests are required to detect Alzheimer's and it leads to the
generation of multivariate heterogeneous data (Davuluri and
Rengaswamy, 2020). A standard medical workup for
Alzheimer's disease often includes structural imaging
with Magnetic Resonance Imaging (MRI) or Computed
Tomography (CT) (Davuluri and Rengaswamy, 2022a).
To resolve various kind of problems that is related to
brain image data analysis can be done by using Machine
Learning (ML) and deep CNN based approaches
(Mehmood et al., 2020). For diagnosing the disease, MRI
is used (Davuluri and Rengaswamy, 2022b). Deep
Learning (DL) algorithms are mostly applied for object
recognition tasks and competitions like Imagenet Large
Scale Visual Recognition Challenge (ILSVRC)
(Russakovsky et al., 2015) that intersect with time and
increased use of medical records and image detection
process. DL algorithms are mostly used to analyze large
datasets and it is very useful for the diagnosis of AD. CNN
is an effective technique to detect and classify Alzheimer's
and its stages using brain MRI images (Salehi et al., 2020).