Alzheimer's disease classification based on combination of multi-model convolutional networks

Alzheimer's disease (AD) is an irreversible neurodegenerative disorder with progressive impairment of memory and cognitive functions. It brings increasingly troubling in today's society. Its early diagnosis and warning are particularly important. Structural magnetic resonance images (MRI)...

Full description

Saved in:
Bibliographic Details
Published in:IST 2017 : conference proceedings : IEEE International Conference on Imaging Systems and Techniques : Beihang University, Beijing, China, October 18-20, 2017 pp. 1 - 5
Main Authors: Fan Li, Danni Cheng, Manhua Liu
Format: Conference Proceeding
Language:English
Published: IEEE 01.10.2017
Subjects:
Alzheimer's disease
Brain modeling
convolutional autoencoder
convolutional neural network
Diseases
Feature extraction
feature fusion
Image classification
Kernel
Three-dimensional displays
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Alzheimer's disease (AD) is an irreversible neurodegenerative disorder with progressive impairment of memory and cognitive functions. It brings increasingly troubling in today's society. Its early diagnosis and warning are particularly important. Structural magnetic resonance images (MRI) play an important role to help understand the brain anatomical changes related to AD. Traditional methods are usually based on extraction of handcrafted features and training a classifier to distinguish AD from other groups. Motivated by the success of deep learning in image classification, this paper proposes a classification method based on combination of multimodel 3D convolutional networks to learn the various features from MR brain images. First, a deep 3D convolutional neural network (3D CNN) is built to hierarchically transform the MR image into more compact high-level features. Second, the multiscale 3D convolutional autoencoders (3D CAEs) are constructed to extract features from MR brain images. The features learned by these models are combined with the upper fully connected layers for image classification in AD diagnosis. The proposed method can automatically learn the generic features from the imaging data for classification without segmentations of brain tissues and regions. Our method is evaluated using T1-weighted MR brain images on 428 subjects including 199 AD patients and 229 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an accuracy of 88.31% for AD classification and an AUC (area under the ROC curve) of 92.73%, demonstrating the promising classification performances.
AbstractList Alzheimer's disease (AD) is an irreversible neurodegenerative disorder with progressive impairment of memory and cognitive functions. It brings increasingly troubling in today's society. Its early diagnosis and warning are particularly important. Structural magnetic resonance images (MRI) play an important role to help understand the brain anatomical changes related to AD. Traditional methods are usually based on extraction of handcrafted features and training a classifier to distinguish AD from other groups. Motivated by the success of deep learning in image classification, this paper proposes a classification method based on combination of multimodel 3D convolutional networks to learn the various features from MR brain images. First, a deep 3D convolutional neural network (3D CNN) is built to hierarchically transform the MR image into more compact high-level features. Second, the multiscale 3D convolutional autoencoders (3D CAEs) are constructed to extract features from MR brain images. The features learned by these models are combined with the upper fully connected layers for image classification in AD diagnosis. The proposed method can automatically learn the generic features from the imaging data for classification without segmentations of brain tissues and regions. Our method is evaluated using T1-weighted MR brain images on 428 subjects including 199 AD patients and 229 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an accuracy of 88.31% for AD classification and an AUC (area under the ROC curve) of 92.73%, demonstrating the promising classification performances.
Author Fan Li
Manhua Liu
Danni Cheng
Author_xml – sequence: 1
  surname: Fan Li
  fullname: Fan Li
  organization: Dept. of Instrum. Sci. & Eng., Shanghai Jiao Tong Univ., Shanghai, China
– sequence: 2
  surname: Danni Cheng
  fullname: Danni Cheng
  organization: Dept. of Instrum. Sci. & Eng., Shanghai Jiao Tong Univ., Shanghai, China
– sequence: 3
  surname: Manhua Liu
  fullname: Manhua Liu
  email: mhliu@sjtu.edu.cn
  organization: Dept. of Instrum. Sci. & Eng., Shanghai Jiao Tong Univ., Shanghai, China
BookMark eNotkE1LxDAURSMoqGP3gpvsXHXMa5I2XQ6DHwMDLuxWhjR5wWiaSNNR9NdbmVndyzlwF_eSnMYUkZBrYEsA1t5tXrplxaBZqqoGWdcnpGgbBZKrGuqKqXNS5PzOGIO2VkJUF-R1FX7f0A843mZqfUadkZqgc_bOGz35FGk_M0vnYtLQ-3iAydFhHyZfDslimFX8SmH_r3SgEafvNH7kK3LmdMhYHHNBuof7bv1Ubp8fN-vVtvQtm0qlhAUtOfQKNOPQCN1qbaRtjLPc2UpaJlXDTCtRKC4AQSsH6Ix1jZWCL8jNYdYj4u5z9IMef3bHD_gfAMtVyg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/IST.2017.8261566
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9781538616208
1538616203
EndPage 5
ExternalDocumentID 8261566
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i90t-884d1a531b81a03174a9aac5d7cfd3fd25d05870c95e48341e1a8f1efcdf7d543
IEDL.DBID RIE
IngestDate Wed Aug 27 02:22:51 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-884d1a531b81a03174a9aac5d7cfd3fd25d05870c95e48341e1a8f1efcdf7d543
PageCount 5
ParticipantIDs ieee_primary_8261566
PublicationCentury 2000
PublicationDate 2017-Oct.
PublicationDateYYYYMMDD 2017-10-01
PublicationDate_xml – month: 10
  year: 2017
  text: 2017-Oct.
PublicationDecade 2010
PublicationTitle IST 2017 : conference proceedings : IEEE International Conference on Imaging Systems and Techniques : Beihang University, Beijing, China, October 18-20, 2017
PublicationTitleAbbrev IST
PublicationYear 2017
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001968442
Score 1.6894865
Snippet Alzheimer's disease (AD) is an irreversible neurodegenerative disorder with progressive impairment of memory and cognitive functions. It brings increasingly...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Alzheimer's disease
Brain modeling
convolutional autoencoder
convolutional neural network
Diseases
Feature extraction
feature fusion
Image classification
Kernel
Three-dimensional displays
Title Alzheimer's disease classification based on combination of multi-model convolutional networks
URI https://ieeexplore.ieee.org/document/8261566
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5q8aAXH634JgfBi2k3u8kmOYpYFKQU7KEXKdk8sFC30ocHf71Jdm0VvHgLAyEwk2GSme-bAbgyNktJbhWmzCSYGi6xTFWCdSBBWpZLZyJR-In3-2I0koMG3Ky5MNbaCD6znbCMtXwz06uQKuv6p3D4bmzBFud5xdXa5FNkLihNvyuRiew-Pg8DdIt36m2_5qfE8NHb-9_B-9De8PDQYB1hDqBhy0PY_dFCsAUvt9PPVzt5s_PrBaqrLUiHJ3HAAEW1oxCpDPILf7v8R7gSzhyKYEIcZ-GggD6vb6GaorIChy_aMOzdD-8ecD0yAU9kssRCUEOUd6tCEOXdlVMlldLMcO1M5kzqDcK8h2rJbMgiEkuUcMQ6bRw3jGZH0CxnpT0GVOiUy0JzYkRBpaYFEc47lAntbRjJ1Am0gp7G71VTjHGtotO_xWewE0xRoeDOobmcr-wFbOuP5WQxv4yW_AIDCKIj
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5qFdSLj1Z8m4PgxbSb3WyTHEUsLdZScA-9SMnmgYW6lT48-OtNdtdWwYu3MBACMxkmmfm-GYBrbaKQtIzENNYBppoJLEIZYOVJkCZuCatzonCP9ft8OBSDCtyuuDDGmBx8Zhp-mdfy9VQtfaqs6Z7C_ruxAZt-clbJ1lpnVESLUxp-1yID0ew-Jx68xRrlxl8TVPIA0t7739H7UF8z8dBgFWMOoGKyQ9j90USwBi93k89XM34zs5s5KustSPlHsUcB5YpHPlZp5BbufrmvcCGcWpTDCXE-DQd5_Hl5D-UEZQU8fF6HpP2Q3HdwOTQBj0WwwJxTTaRzrJQT6RyWUSmkVLFmyurI6tCZJHY-qkRsfB6RGCK5JcYqbZmOaXQE1WyamWNAqQqZSBUjmqdUKJoSbp1Lad_gJiaRPIGa19PovWiLMSpVdPq3-Aq2O8lTb9Tr9h_PYMebpcDEnUN1MVuaC9hSH4vxfHaZW_ULoaulbA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IST+2017+%3A+conference+proceedings+%3A+IEEE+International+Conference+on+Imaging+Systems+and+Techniques+%3A+Beihang+University%2C+Beijing%2C+China%2C+October+18-20%2C+2017&rft.atitle=Alzheimer%27s+disease+classification+based+on+combination+of+multi-model+convolutional+networks&rft.au=Fan+Li&rft.au=Danni+Cheng&rft.au=Manhua+Liu&rft.date=2017-10-01&rft.pub=IEEE&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FIST.2017.8261566&rft.externalDocID=8261566