Deep Learning-Based Feature Extraction with MRI Data in Neuroimaging Genetics for Alzheimer’s Disease

on behalf of the Alzheimer’s Disease Neuroimaging Initiative

doi:10.3390/genes14030626

Deep Learning-Based Feature Extraction with MRI Data in Neuroimaging Genetics for Alzheimer’s Disease

on behalf of the Alzheimer’s Disease Neuroimaging Initiative

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

7 Scopus citations

Abstract

The prognosis and treatment of patients suffering from Alzheimer’s disease (AD) have been among the most important and challenging problems over the last few decades. To better understand the mechanism of AD, it is of great interest to identify genetic variants associated with brain atrophy. Commonly, in these analyses, neuroimaging features are extracted based on one of many possible brain atlases with FreeSurf and other popular software; this, however, may cause the loss of important information due to our incomplete knowledge about brain function embedded in these suboptimal atlases. To address the issue, we propose convolutional neural network (CNN) models applied to three-dimensional MRI data for the whole brain or multiple, divided brain regions to perform completely data-driven and automatic feature extraction. These image-derived features are then used as endophenotypes in genome-wide association studies (GWASs) to identify associated genetic variants. When we applied this method to ADNI data, we identified several associated SNPs that have been previously shown to be related to several neurodegenerative/mental disorders, such as AD, depression, and schizophrenia.

Original language	English (US)
Article number	626
Journal	Genes
Volume	14
Issue number	3
DOIs	https://doi.org/10.3390/genes14030626
State	Published - Mar 2023

Bibliographical note

Funding Information:
We thank two reviewers and the editor for helpful reviews. Data collection and sharing for this project was funded by 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 National Institute on Aging and 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; Transition Therapeutics. The Canadian Institutes of Health Research provides funds to support the ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health ( www.fnih.org ). The guarantee organization is Northern California Institute for Research and Education, and the study is coordinated by Alzheimer’s Therapeutic Research Institute at University of Southern California. ADNI data are disseminated by Laboratory for Neuro Imaging at University of Southern California.

Funding Information:
This research was funded by NIH grants R01 AG069895, RF1 AG067924, R01 AG065636, and U01 AG073079, and by Minnesota Supercomputing Institute at University of Minnesota.

Publisher Copyright:
© 2023 by the authors.

Keywords

CNNs
SNPs
endophenotypes
genome-wide association study (GWAS)
principle components (PCs)

Publisher link

10.3390/genes14030626

Find It

Find It at U of M Libraries

Cite this

@article{5b6f8d0c54ef4bc18505e418499fef96,

title = "Deep Learning-Based Feature Extraction with MRI Data in Neuroimaging Genetics for Alzheimer{\textquoteright}s Disease",

abstract = "The prognosis and treatment of patients suffering from Alzheimer{\textquoteright}s disease (AD) have been among the most important and challenging problems over the last few decades. To better understand the mechanism of AD, it is of great interest to identify genetic variants associated with brain atrophy. Commonly, in these analyses, neuroimaging features are extracted based on one of many possible brain atlases with FreeSurf and other popular software; this, however, may cause the loss of important information due to our incomplete knowledge about brain function embedded in these suboptimal atlases. To address the issue, we propose convolutional neural network (CNN) models applied to three-dimensional MRI data for the whole brain or multiple, divided brain regions to perform completely data-driven and automatic feature extraction. These image-derived features are then used as endophenotypes in genome-wide association studies (GWASs) to identify associated genetic variants. When we applied this method to ADNI data, we identified several associated SNPs that have been previously shown to be related to several neurodegenerative/mental disorders, such as AD, depression, and schizophrenia.",

keywords = "CNNs, SNPs, endophenotypes, genome-wide association study (GWAS), principle components (PCs)",

author = "{on behalf of the Alzheimer{\textquoteright}s Disease Neuroimaging Initiative} and Dipnil Chakraborty and Zhong Zhuang and Haoran Xue and Fiecas, {Mark B.} and Xiatong Shen and Wei Pan",

note = "Funding Information: We thank two reviewers and the editor for helpful reviews. Data collection and sharing for this project was funded by 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 National Institute on Aging and 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; Transition Therapeutics. The Canadian Institutes of Health Research provides funds to support the ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health ( www.fnih.org ). The guarantee organization is Northern California Institute for Research and Education, and the study is coordinated by Alzheimer{\textquoteright}s Therapeutic Research Institute at University of Southern California. ADNI data are disseminated by Laboratory for Neuro Imaging at University of Southern California. Funding Information: This research was funded by NIH grants R01 AG069895, RF1 AG067924, R01 AG065636, and U01 AG073079, and by Minnesota Supercomputing Institute at University of Minnesota. Publisher Copyright: {\textcopyright} 2023 by the authors.",

year = "2023",

month = mar,

doi = "10.3390/genes14030626",

language = "English (US)",

volume = "14",

journal = "Genes",

issn = "2073-4425",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "3",

}

TY - JOUR

T1 - Deep Learning-Based Feature Extraction with MRI Data in Neuroimaging Genetics for Alzheimer’s Disease

AU - on behalf of the Alzheimer’s Disease Neuroimaging Initiative

AU - Chakraborty, Dipnil

AU - Zhuang, Zhong

AU - Xue, Haoran

AU - Fiecas, Mark B.

AU - Shen, Xiatong

AU - Pan, Wei

N1 - Funding Information: We thank two reviewers and the editor for helpful reviews. Data collection and sharing for this project was funded by 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 National Institute on Aging and 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; Transition Therapeutics. The Canadian Institutes of Health Research provides funds to support the ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health ( www.fnih.org ). The guarantee organization is Northern California Institute for Research and Education, and the study is coordinated by Alzheimer’s Therapeutic Research Institute at University of Southern California. ADNI data are disseminated by Laboratory for Neuro Imaging at University of Southern California. Funding Information: This research was funded by NIH grants R01 AG069895, RF1 AG067924, R01 AG065636, and U01 AG073079, and by Minnesota Supercomputing Institute at University of Minnesota. Publisher Copyright: © 2023 by the authors.

PY - 2023/3

Y1 - 2023/3

N2 - The prognosis and treatment of patients suffering from Alzheimer’s disease (AD) have been among the most important and challenging problems over the last few decades. To better understand the mechanism of AD, it is of great interest to identify genetic variants associated with brain atrophy. Commonly, in these analyses, neuroimaging features are extracted based on one of many possible brain atlases with FreeSurf and other popular software; this, however, may cause the loss of important information due to our incomplete knowledge about brain function embedded in these suboptimal atlases. To address the issue, we propose convolutional neural network (CNN) models applied to three-dimensional MRI data for the whole brain or multiple, divided brain regions to perform completely data-driven and automatic feature extraction. These image-derived features are then used as endophenotypes in genome-wide association studies (GWASs) to identify associated genetic variants. When we applied this method to ADNI data, we identified several associated SNPs that have been previously shown to be related to several neurodegenerative/mental disorders, such as AD, depression, and schizophrenia.

AB - The prognosis and treatment of patients suffering from Alzheimer’s disease (AD) have been among the most important and challenging problems over the last few decades. To better understand the mechanism of AD, it is of great interest to identify genetic variants associated with brain atrophy. Commonly, in these analyses, neuroimaging features are extracted based on one of many possible brain atlases with FreeSurf and other popular software; this, however, may cause the loss of important information due to our incomplete knowledge about brain function embedded in these suboptimal atlases. To address the issue, we propose convolutional neural network (CNN) models applied to three-dimensional MRI data for the whole brain or multiple, divided brain regions to perform completely data-driven and automatic feature extraction. These image-derived features are then used as endophenotypes in genome-wide association studies (GWASs) to identify associated genetic variants. When we applied this method to ADNI data, we identified several associated SNPs that have been previously shown to be related to several neurodegenerative/mental disorders, such as AD, depression, and schizophrenia.

KW - CNNs

KW - SNPs

KW - endophenotypes

KW - genome-wide association study (GWAS)

KW - principle components (PCs)

UR - http://www.scopus.com/inward/record.url?scp=85151110667&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85151110667&partnerID=8YFLogxK

U2 - 10.3390/genes14030626

DO - 10.3390/genes14030626

M3 - Article

C2 - 36980898

AN - SCOPUS:85151110667

SN - 2073-4425

VL - 14

JO - Genes

JF - Genes

IS - 3

M1 - 626

ER -

Deep Learning-Based Feature Extraction with MRI Data in Neuroimaging Genetics for Alzheimer’s Disease

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this