Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease using structural MR and FDG-PET images

doi:10.1038/s41598-018-22871-z

Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease using structural MR and FDG-PET images

Research output: Contribution to journal › Article › peer-review

188 Citations (SciVal)

Abstract

Alzheimer’s Disease (AD) is a progressive neurodegenerative disease where biomarkers for disease based on pathophysiology may be able to provide objective measures for disease diagnosis and staging. Neuroimaging scans acquired from MRI and metabolism images obtained by FDG-PET provide in-vivo measurements of structure and function (glucose metabolism) in a living brain. It is hypothesized that combining multiple different image modalities providing complementary information could help improve early diagnosis of AD. In this paper, we propose a novel deep-learning-based framework to discriminate individuals with AD utilizing a multimodal and multiscale deep neural network. Our method delivers 82.4% accuracy in identifying the individuals with mild cognitive impairment (MCI) who will convert to AD at 3 years prior to conversion (86.4% combined accuracy for conversion within 1–3 years), a 94.23% sensitivity in classifying individuals with clinical diagnosis of probable AD, and a 86.3% specificity in classifying non-demented controls improving upon results in published literature.

Original language	English
Article number	5697
Journal	Scientific Reports
Volume	8
Issue number	1
DOIs	https://doi.org/10.1038/s41598-018-22871-z
State	Published - Dec 1 2018

Bibliographical note

Funding Information:
This work was supported by National Science Engineering Research Council (NSERC), Canadian Institutes of Health Research (CIHR), Michael Smith Foundation for Health Research (MSFHR), Brain Canada, Genome BC and the Pacific Alzheimer Research Foundation (PARF). Data collection and sharing for this project was funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer’s Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California.

Publisher Copyright:
© 2018, The Author(s).

ASJC Scopus subject areas

General

Access to Document

10.1038/s41598-018-22871-z

Cite this

@article{9963e647466d49949a8b60ad11a00ee7,

title = "Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer{\textquoteright}s Disease using structural MR and FDG-PET images",

abstract = "Alzheimer{\textquoteright}s Disease (AD) is a progressive neurodegenerative disease where biomarkers for disease based on pathophysiology may be able to provide objective measures for disease diagnosis and staging. Neuroimaging scans acquired from MRI and metabolism images obtained by FDG-PET provide in-vivo measurements of structure and function (glucose metabolism) in a living brain. It is hypothesized that combining multiple different image modalities providing complementary information could help improve early diagnosis of AD. In this paper, we propose a novel deep-learning-based framework to discriminate individuals with AD utilizing a multimodal and multiscale deep neural network. Our method delivers 82.4% accuracy in identifying the individuals with mild cognitive impairment (MCI) who will convert to AD at 3 years prior to conversion (86.4% combined accuracy for conversion within 1–3 years), a 94.23% sensitivity in classifying individuals with clinical diagnosis of probable AD, and a 86.3% specificity in classifying non-demented controls improving upon results in published literature.",

author = "Donghuan Lu and Karteek Popuri and Ding, {Gavin Weiguang} and Rakesh Balachandar and Beg, {Mirza Faisal} and Michael Weiner and Paul Aisen and Ronald Petersen and Cliford Jack and William Jagust and John Trojanowki and Arthur Toga and Laurel Beckett and Robert Green and Andrew Saykin and Morris, {John C.} and Leslie Shaw and Jefrey Kaye and Joseph Quinn and Lisa Silbert and Betty Lind and Raina Carter and Sara Dolen and Lon Schneider and Sonia Pawluczyk and Mauricio Beccera and Liberty Teodoro and Bryan Spann and James Brewer and Helen Vanderswag and Adam Fleisher and Judith Heidebrink and Joanne Lord and Sara Mason and Colleen Albers and David Knopman and Kris Johnson and Rachelle Doody and Javier Villanueva-Meyer and Munir Chowdhury and Susan Rountree and Mimi Dang and Yaakov Stern and Lawrence Honig and Karen Bell and Beau Ances and Maria Carroll and Mary Creech and Erin Franklin and Greg Jicha",

note = "Funding Information: This work was supported by National Science Engineering Research Council (NSERC), Canadian Institutes of Health Research (CIHR), Michael Smith Foundation for Health Research (MSFHR), Brain Canada, Genome BC and the Pacific Alzheimer Research Foundation (PARF). Data collection and sharing for this project was funded by the Alzheimer{\textquoteright}s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer{\textquoteright}s Association; Alzheimer{\textquoteright}s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer{\textquoteright}s Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. Publisher Copyright: {\textcopyright} 2018, The Author(s).",

year = "2018",

month = dec,

day = "1",

doi = "10.1038/s41598-018-22871-z",

language = "English",

volume = "8",

number = "1",

}

TY - JOUR

T1 - Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease using structural MR and FDG-PET images

AU - Lu, Donghuan

AU - Popuri, Karteek

AU - Ding, Gavin Weiguang

AU - Balachandar, Rakesh

AU - Beg, Mirza Faisal

AU - Weiner, Michael

AU - Aisen, Paul

AU - Petersen, Ronald

AU - Jack, Cliford

AU - Jagust, William

AU - Trojanowki, John

AU - Toga, Arthur

AU - Beckett, Laurel

AU - Green, Robert

AU - Saykin, Andrew

AU - Morris, John C.

AU - Shaw, Leslie

AU - Kaye, Jefrey

AU - Quinn, Joseph

AU - Silbert, Lisa

AU - Lind, Betty

AU - Carter, Raina

AU - Dolen, Sara

AU - Schneider, Lon

AU - Pawluczyk, Sonia

AU - Beccera, Mauricio

AU - Teodoro, Liberty

AU - Spann, Bryan

AU - Brewer, James

AU - Vanderswag, Helen

AU - Fleisher, Adam

AU - Heidebrink, Judith

AU - Lord, Joanne

AU - Mason, Sara

AU - Albers, Colleen

AU - Knopman, David

AU - Johnson, Kris

AU - Doody, Rachelle

AU - Villanueva-Meyer, Javier

AU - Chowdhury, Munir

AU - Rountree, Susan

AU - Dang, Mimi

AU - Stern, Yaakov

AU - Honig, Lawrence

AU - Bell, Karen

AU - Ances, Beau

AU - Carroll, Maria

AU - Creech, Mary

AU - Franklin, Erin

AU - Jicha, Greg

N1 - Funding Information: This work was supported by National Science Engineering Research Council (NSERC), Canadian Institutes of Health Research (CIHR), Michael Smith Foundation for Health Research (MSFHR), Brain Canada, Genome BC and the Pacific Alzheimer Research Foundation (PARF). Data collection and sharing for this project was funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through generous contributions from the following: AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research & Development, LLC.; Johnson & Johnson Pharmaceutical Research & Development LLC.; Lumosity; Lundbeck; Merck & Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research is providing funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health (www.fnih.org). The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer’s Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California. Publisher Copyright: © 2018, The Author(s).

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Alzheimer’s Disease (AD) is a progressive neurodegenerative disease where biomarkers for disease based on pathophysiology may be able to provide objective measures for disease diagnosis and staging. Neuroimaging scans acquired from MRI and metabolism images obtained by FDG-PET provide in-vivo measurements of structure and function (glucose metabolism) in a living brain. It is hypothesized that combining multiple different image modalities providing complementary information could help improve early diagnosis of AD. In this paper, we propose a novel deep-learning-based framework to discriminate individuals with AD utilizing a multimodal and multiscale deep neural network. Our method delivers 82.4% accuracy in identifying the individuals with mild cognitive impairment (MCI) who will convert to AD at 3 years prior to conversion (86.4% combined accuracy for conversion within 1–3 years), a 94.23% sensitivity in classifying individuals with clinical diagnosis of probable AD, and a 86.3% specificity in classifying non-demented controls improving upon results in published literature.

AB - Alzheimer’s Disease (AD) is a progressive neurodegenerative disease where biomarkers for disease based on pathophysiology may be able to provide objective measures for disease diagnosis and staging. Neuroimaging scans acquired from MRI and metabolism images obtained by FDG-PET provide in-vivo measurements of structure and function (glucose metabolism) in a living brain. It is hypothesized that combining multiple different image modalities providing complementary information could help improve early diagnosis of AD. In this paper, we propose a novel deep-learning-based framework to discriminate individuals with AD utilizing a multimodal and multiscale deep neural network. Our method delivers 82.4% accuracy in identifying the individuals with mild cognitive impairment (MCI) who will convert to AD at 3 years prior to conversion (86.4% combined accuracy for conversion within 1–3 years), a 94.23% sensitivity in classifying individuals with clinical diagnosis of probable AD, and a 86.3% specificity in classifying non-demented controls improving upon results in published literature.

UR - http://www.scopus.com/inward/record.url?scp=85052338503&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052338503&partnerID=8YFLogxK

U2 - 10.1038/s41598-018-22871-z

DO - 10.1038/s41598-018-22871-z

M3 - Article

C2 - 29632364

AN - SCOPUS:85052338503

VL - 8

IS - 1

M1 - 5697

ER -

Multimodal and Multiscale Deep Neural Networks for the Early Diagnosis of Alzheimer’s Disease using structural MR and FDG-PET images

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this