AI-based dimensional neuroimaging system for characterizing heterogeneity in brain structure and function in major depressive disorder: COORDINATE-MDD consortium design and rationale
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
AI-based dimensional neuroimaging system for characterizing heterogeneity in brain structure and function in major depressive disorder : COORDINATE-MDD consortium design and rationale. / Fu, Cynthia H Y; Erus, Guray; Fan, Yong; Antoniades, Mathilde; Arnone, Danilo; Arnott, Stephen R; Chen, Taolin; Choi, Ki Sueng; Fatt, Cherise Chin; Frey, Benicio N; Frokjaer, Vibe G; Ganz, Melanie; Garcia, Jose; Godlewska, Beata R; Hassel, Stefanie; Ho, Keith; McIntosh, Andrew M; Qin, Kun; Rotzinger, Susan; Sacchet, Matthew D; Savitz, Jonathan; Shou, Haochang; Singh, Ashish; Stolicyn, Aleks; Strigo, Irina; Strother, Stephen C; Tosun, Duygu; Victor, Teresa A; Wei, Dongtao; Wise, Toby; Woodham, Rachel D; Zahn, Roland; Anderson, Ian M; Deakin, J F William; Dunlop, Boadie W; Elliott, Rebecca; Gong, Qiyong; Gotlib, Ian H; Harmer, Catherine J; Kennedy, Sidney H; Knudsen, Gitte M; Mayberg, Helen S; Paulus, Martin P; Qiu, Jiang; Trivedi, Madhukar H; Whalley, Heather C; Yan, Chao-Gan; Young, Allan H; Davatzikos, Christos.
In: BMC Psychiatry, Vol. 23, No. 1, 59, 23.01.2023.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - AI-based dimensional neuroimaging system for characterizing heterogeneity in brain structure and function in major depressive disorder
T2 - COORDINATE-MDD consortium design and rationale
AU - Fu, Cynthia H Y
AU - Erus, Guray
AU - Fan, Yong
AU - Antoniades, Mathilde
AU - Arnone, Danilo
AU - Arnott, Stephen R
AU - Chen, Taolin
AU - Choi, Ki Sueng
AU - Fatt, Cherise Chin
AU - Frey, Benicio N
AU - Frokjaer, Vibe G
AU - Ganz, Melanie
AU - Garcia, Jose
AU - Godlewska, Beata R
AU - Hassel, Stefanie
AU - Ho, Keith
AU - McIntosh, Andrew M
AU - Qin, Kun
AU - Rotzinger, Susan
AU - Sacchet, Matthew D
AU - Savitz, Jonathan
AU - Shou, Haochang
AU - Singh, Ashish
AU - Stolicyn, Aleks
AU - Strigo, Irina
AU - Strother, Stephen C
AU - Tosun, Duygu
AU - Victor, Teresa A
AU - Wei, Dongtao
AU - Wise, Toby
AU - Woodham, Rachel D
AU - Zahn, Roland
AU - Anderson, Ian M
AU - Deakin, J F William
AU - Dunlop, Boadie W
AU - Elliott, Rebecca
AU - Gong, Qiyong
AU - Gotlib, Ian H
AU - Harmer, Catherine J
AU - Kennedy, Sidney H
AU - Knudsen, Gitte M
AU - Mayberg, Helen S
AU - Paulus, Martin P
AU - Qiu, Jiang
AU - Trivedi, Madhukar H
AU - Whalley, Heather C
AU - Yan, Chao-Gan
AU - Young, Allan H
AU - Davatzikos, Christos
N1 - © 2023. The Author(s).
PY - 2023/1/23
Y1 - 2023/1/23
N2 - BACKGROUND: Efforts to develop neuroimaging-based biomarkers in major depressive disorder (MDD), at the individual level, have been limited to date. As diagnostic criteria are currently symptom-based, MDD is conceptualized as a disorder rather than a disease with a known etiology; further, neural measures are often confounded by medication status and heterogeneous symptom states.METHODS: We describe a consortium to quantify neuroanatomical and neurofunctional heterogeneity via the dimensions of novel multivariate coordinate system (COORDINATE-MDD). Utilizing imaging harmonization and machine learning methods in a large cohort of medication-free, deeply phenotyped MDD participants, patterns of brain alteration are defined in replicable and neurobiologically-based dimensions and offer the potential to predict treatment response at the individual level. International datasets are being shared from multi-ethnic community populations, first episode and recurrent MDD, which are medication-free, in a current depressive episode with prospective longitudinal treatment outcomes and in remission. Neuroimaging data consist of de-identified, individual, structural MRI and resting-state functional MRI with additional positron emission tomography (PET) data at specific sites. State-of-the-art analytic methods include automated image processing for extraction of anatomical and functional imaging variables, statistical harmonization of imaging variables to account for site and scanner variations, and semi-supervised machine learning methods that identify dominant patterns associated with MDD from neural structure and function in healthy participants.RESULTS: We are applying an iterative process by defining the neural dimensions that characterise deeply phenotyped samples and then testing the dimensions in novel samples to assess specificity and reliability. Crucially, we aim to use machine learning methods to identify novel predictors of treatment response based on prospective longitudinal treatment outcome data, and we can externally validate the dimensions in fully independent sites.CONCLUSION: We describe the consortium, imaging protocols and analytics using preliminary results. Our findings thus far demonstrate how datasets across many sites can be harmonized and constructively pooled to enable execution of this large-scale project.
AB - BACKGROUND: Efforts to develop neuroimaging-based biomarkers in major depressive disorder (MDD), at the individual level, have been limited to date. As diagnostic criteria are currently symptom-based, MDD is conceptualized as a disorder rather than a disease with a known etiology; further, neural measures are often confounded by medication status and heterogeneous symptom states.METHODS: We describe a consortium to quantify neuroanatomical and neurofunctional heterogeneity via the dimensions of novel multivariate coordinate system (COORDINATE-MDD). Utilizing imaging harmonization and machine learning methods in a large cohort of medication-free, deeply phenotyped MDD participants, patterns of brain alteration are defined in replicable and neurobiologically-based dimensions and offer the potential to predict treatment response at the individual level. International datasets are being shared from multi-ethnic community populations, first episode and recurrent MDD, which are medication-free, in a current depressive episode with prospective longitudinal treatment outcomes and in remission. Neuroimaging data consist of de-identified, individual, structural MRI and resting-state functional MRI with additional positron emission tomography (PET) data at specific sites. State-of-the-art analytic methods include automated image processing for extraction of anatomical and functional imaging variables, statistical harmonization of imaging variables to account for site and scanner variations, and semi-supervised machine learning methods that identify dominant patterns associated with MDD from neural structure and function in healthy participants.RESULTS: We are applying an iterative process by defining the neural dimensions that characterise deeply phenotyped samples and then testing the dimensions in novel samples to assess specificity and reliability. Crucially, we aim to use machine learning methods to identify novel predictors of treatment response based on prospective longitudinal treatment outcome data, and we can externally validate the dimensions in fully independent sites.CONCLUSION: We describe the consortium, imaging protocols and analytics using preliminary results. Our findings thus far demonstrate how datasets across many sites can be harmonized and constructively pooled to enable execution of this large-scale project.
KW - Humans
KW - Depressive Disorder, Major/diagnosis
KW - Prospective Studies
KW - Reproducibility of Results
KW - Brain
KW - Neuroimaging
KW - Magnetic Resonance Imaging/methods
KW - Artificial Intelligence
U2 - 10.1186/s12888-022-04509-7
DO - 10.1186/s12888-022-04509-7
M3 - Journal article
C2 - 36690972
VL - 23
JO - B M C Psychiatry
JF - B M C Psychiatry
SN - 1471-244X
IS - 1
M1 - 59
ER -
ID: 334012776