The use of artificial neural networks to diagnose Alzheimer�s disease from brain images
Since Alzheimer�s disease (AD) occurs in multiple stages of cognitive impairment, its early diagnosis can be helpful in the process of treatment. Its early diagnosis is thus drawn the attention of researchers and physicians. This study aims to investigate various types of artificial neural network...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Published: |
Springer
2022
|
Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136215668&doi=10.1007%2fs11042-022-13506-7&partnerID=40&md5=36282bc9af13d56600297d8173bfbec1 http://eprints.utp.edu.my/33788/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utp.eprints.33788 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.337882022-09-13T04:41:54Z The use of artificial neural networks to diagnose Alzheimer�s disease from brain images Fouladi, S. Safaei, A.A. Arshad, N.I. Ebadi, M.J. Ahmadian, A. Since Alzheimer�s disease (AD) occurs in multiple stages of cognitive impairment, its early diagnosis can be helpful in the process of treatment. Its early diagnosis is thus drawn the attention of researchers and physicians. This study aims to investigate various types of artificial neural networks (ANNs) used to diagnose and predict AD based on brain images of subjects with mild cognitive impairment (MCI). In this study, articles indexed in the IEEE, Springer, Elsevier, and PubMed Central databases were systematically analyzed over the period from 2010 through the first half of 2020. The initial search was done for the keywords Alzheimer�s, Magnetic resonance imaging (MRI), and neural network, continued for the keywords Alzheimer�s, brain positron emission tomography(PET), and neural network, and ended with the keywords Alzheimer�s, brain computed tomography (CT), and neural network. Eventually, the most relevant articles were selected based on the critical evaluation of the subject under investigation. Searching on the subject through the mentioned databases resulted in 900 articles. Excluding unrelated ones, only 134 articles remained, out of which, 54, 41, 35, and 4 numbers were respectively indexed in PubMed Central, Elsevier, Springer, and IEEE databases. The number of studies increased by about 2.5 times from 2016 to 2017 and followed this growing trend at the rate of 2 times by 2018. The number of these studies was increasing up to the first half of 2020. There was a wide use of data from Alzheimer�s disease neuroimaging initiative (ADNI) database compared to open access series of imaging studies (OASIS) and other databases by the researchers. MRI images, PET images, and their combination were respectively used in 61, 21, and 15 of the researches. This is while only 2 of the studies used CT images, suggestive of their inefficiency compared to other brain imaging techniques in diagnosing AD. Most studies either grouped subjects into Alzheimer�s patients and healthy people or classified them under three groups of subjects with Alzheimer�s, cognitive impairment, and in good health. However, different stages of cognitive impairment have merely considered in 16 of the studies. The main purpose of all studies was AD classification and diagnosis. Further research should be conducted to classify and diagnose this disease in subjects with MCI. It is recommended to use ADNI as a comprehensive database of images from people with various degrees of cognitive impairment, AD, and health control (HC) in future research. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. Springer 2022 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136215668&doi=10.1007%2fs11042-022-13506-7&partnerID=40&md5=36282bc9af13d56600297d8173bfbec1 Fouladi, S. and Safaei, A.A. and Arshad, N.I. and Ebadi, M.J. and Ahmadian, A. (2022) The use of artificial neural networks to diagnose Alzheimer�s disease from brain images. Multimedia Tools and Applications . http://eprints.utp.edu.my/33788/ |
institution |
Universiti Teknologi Petronas |
building |
UTP Resource Centre |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Petronas |
content_source |
UTP Institutional Repository |
url_provider |
http://eprints.utp.edu.my/ |
description |
Since Alzheimer�s disease (AD) occurs in multiple stages of cognitive impairment, its early diagnosis can be helpful in the process of treatment. Its early diagnosis is thus drawn the attention of researchers and physicians. This study aims to investigate various types of artificial neural networks (ANNs) used to diagnose and predict AD based on brain images of subjects with mild cognitive impairment (MCI). In this study, articles indexed in the IEEE, Springer, Elsevier, and PubMed Central databases were systematically analyzed over the period from 2010 through the first half of 2020. The initial search was done for the keywords Alzheimer�s, Magnetic resonance imaging (MRI), and neural network, continued for the keywords Alzheimer�s, brain positron emission tomography(PET), and neural network, and ended with the keywords Alzheimer�s, brain computed tomography (CT), and neural network. Eventually, the most relevant articles were selected based on the critical evaluation of the subject under investigation. Searching on the subject through the mentioned databases resulted in 900 articles. Excluding unrelated ones, only 134 articles remained, out of which, 54, 41, 35, and 4 numbers were respectively indexed in PubMed Central, Elsevier, Springer, and IEEE databases. The number of studies increased by about 2.5 times from 2016 to 2017 and followed this growing trend at the rate of 2 times by 2018. The number of these studies was increasing up to the first half of 2020. There was a wide use of data from Alzheimer�s disease neuroimaging initiative (ADNI) database compared to open access series of imaging studies (OASIS) and other databases by the researchers. MRI images, PET images, and their combination were respectively used in 61, 21, and 15 of the researches. This is while only 2 of the studies used CT images, suggestive of their inefficiency compared to other brain imaging techniques in diagnosing AD. Most studies either grouped subjects into Alzheimer�s patients and healthy people or classified them under three groups of subjects with Alzheimer�s, cognitive impairment, and in good health. However, different stages of cognitive impairment have merely considered in 16 of the studies. The main purpose of all studies was AD classification and diagnosis. Further research should be conducted to classify and diagnose this disease in subjects with MCI. It is recommended to use ADNI as a comprehensive database of images from people with various degrees of cognitive impairment, AD, and health control (HC) in future research. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. |
format |
Article |
author |
Fouladi, S. Safaei, A.A. Arshad, N.I. Ebadi, M.J. Ahmadian, A. |
spellingShingle |
Fouladi, S. Safaei, A.A. Arshad, N.I. Ebadi, M.J. Ahmadian, A. The use of artificial neural networks to diagnose Alzheimer�s disease from brain images |
author_facet |
Fouladi, S. Safaei, A.A. Arshad, N.I. Ebadi, M.J. Ahmadian, A. |
author_sort |
Fouladi, S. |
title |
The use of artificial neural networks to diagnose Alzheimer�s disease from brain images |
title_short |
The use of artificial neural networks to diagnose Alzheimer�s disease from brain images |
title_full |
The use of artificial neural networks to diagnose Alzheimer�s disease from brain images |
title_fullStr |
The use of artificial neural networks to diagnose Alzheimer�s disease from brain images |
title_full_unstemmed |
The use of artificial neural networks to diagnose Alzheimer�s disease from brain images |
title_sort |
use of artificial neural networks to diagnose alzheimer�s disease from brain images |
publisher |
Springer |
publishDate |
2022 |
url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136215668&doi=10.1007%2fs11042-022-13506-7&partnerID=40&md5=36282bc9af13d56600297d8173bfbec1 http://eprints.utp.edu.my/33788/ |
_version_ |
1748705172084752384 |
score |
13.18916 |