TY - JOUR
T1 - A deep learning framework identifies dimensional representations of Alzheimer’s Disease from brain structure
AU - iSTAGING Consortium
AU - Baltimore Longitudinal Study of Aging (BLSA)
AU - Alzheimer’s Disease Neuroimaging Initiative (ADNI)
AU - Yang, Zhijian
AU - Nasrallah, Ilya M.
AU - Shou, Haochang
AU - Wen, Junhao
AU - Doshi, Jimit
AU - Habes, Mohamad
AU - Erus, Guray
AU - Abdulkadir, Ahmed
AU - Resnick, Susan M.
AU - Albert, Marilyn S.
AU - Maruff, Paul
AU - Fripp, Jurgen
AU - Morris, John C.
AU - Wolk, David A.
AU - Davatzikos, Christos
AU - Fan, Yong
AU - Bashyam, Vishnu
AU - Mamouiran, Elizabeth
AU - Melhem, Randa
AU - Pomponio, Raymond
AU - Sahoo, Dushyant
AU - Ashish, Singh
AU - Skampardoni, Ioanna
AU - Sreepada, Lasya
AU - Srinivasan, Dhivya
AU - Yu, Fanyang
AU - Tirumalai, Sindhuja Govindarajan
AU - Cui, Yuhan
AU - Zhou, Zhen
AU - Wittfeld, Katharina
AU - Grabe, Hans J.
AU - Tosun, Duygun
AU - Bilgel, Murat
AU - An, Yang
AU - Marcus, Daniel S.
AU - LaMontagne, Pamela
AU - Heckbert, Susan R.
AU - Austin, Thomas R.
AU - Launer, Lenore J.
AU - Sotiras, Aristeidis
AU - Espeland, Mark
AU - Masters, Colin L.
AU - Völzk, Henry
AU - Johnson, Sterling C.
AU - Ferrucci, Luigi
AU - Bryan, R. Nick
AU - Weiner, Michael
AU - Aisen, Paul
AU - Petersen, Ronald
AU - Grossman, Hillel
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - Heterogeneity of brain diseases is a challenge for precision diagnosis/prognosis. We describe and validate Smile-GAN (SeMI-supervised cLustEring-Generative Adversarial Network), a semi-supervised deep-clustering method, which examines neuroanatomical heterogeneity contrasted against normal brain structure, to identify disease subtypes through neuroimaging signatures. When applied to regional volumes derived from T1-weighted MRI (two studies; 2,832 participants; 8,146 scans) including cognitively normal individuals and those with cognitive impairment and dementia, Smile-GAN identified four patterns or axes of neurodegeneration. Applying this framework to longitudinal data revealed two distinct progression pathways. Measures of expression of these patterns predicted the pathway and rate of future neurodegeneration. Pattern expression offered complementary performance to amyloid/tau in predicting clinical progression. These deep-learning derived biomarkers offer potential for precision diagnostics and targeted clinical trial recruitment.
AB - Heterogeneity of brain diseases is a challenge for precision diagnosis/prognosis. We describe and validate Smile-GAN (SeMI-supervised cLustEring-Generative Adversarial Network), a semi-supervised deep-clustering method, which examines neuroanatomical heterogeneity contrasted against normal brain structure, to identify disease subtypes through neuroimaging signatures. When applied to regional volumes derived from T1-weighted MRI (two studies; 2,832 participants; 8,146 scans) including cognitively normal individuals and those with cognitive impairment and dementia, Smile-GAN identified four patterns or axes of neurodegeneration. Applying this framework to longitudinal data revealed two distinct progression pathways. Measures of expression of these patterns predicted the pathway and rate of future neurodegeneration. Pattern expression offered complementary performance to amyloid/tau in predicting clinical progression. These deep-learning derived biomarkers offer potential for precision diagnostics and targeted clinical trial recruitment.
UR - http://www.scopus.com/inward/record.url?scp=85122435981&partnerID=8YFLogxK
U2 - 10.1038/s41467-021-26703-z
DO - 10.1038/s41467-021-26703-z
M3 - Article
C2 - 34862382
AN - SCOPUS:85122435981
SN - 2041-1723
VL - 12
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 7065
ER -