Junhao Wen, Zhijian Yang, Ilya M Nasrallah, Yuhan Cui, Guray Erus, Dhivya Srinivasan, Ahmed Abdulkadir, Elizabeth Mamourian, Gyujoon Hwang, Ashish Singh, Mark Bergman, Jingxuan Bao, Erdem Varol, Zhen Zhou, Aleix Boquet-Pujadas, Jiong Chen, Arthur W Toga, Andrew J Saykin, Timothy J Hohman, Paul M Thompson, Sylvia Villeneuve, Randy Gollub, Aristeidis Sotiras, Katharina Wittfeld, Hans J Grabe, Duygu Tosun, Murat Bilgel, Yang An, Daniel S Marcus, Pamela LaMontagne, Tammie L Benzinger, Susan R Heckbert, Thomas R Austin, Lenore J Launer, Mark Espeland, Colin L Masters, Paul Maruff, Jurgen Fripp, Sterling C Johnson, John C Morris, Marilyn S Albert, R Nick Bryan, Susan M Resnick, Luigi Ferrucci, Yong Fan, Mohamad Habes, David Wolk, Li Shen, Haochang Shou, Christos Davatzikos
Alzheimer's disease (AD) is associated with heterogeneous atrophy patterns. We employed a semi-supervised representation learning technique known as Surreal-GAN, through which we identified two latent dimensional representations of brain atrophy in symptomatic mild cognitive impairment (MCI) and AD patients: the "diffuse-AD" (R1) dimension shows widespread brain atrophy, and the "MTL-AD" (R2) dimension displays focal medial temporal lobe (MTL) atrophy. Critically, only R2 was associated with widely known sporadic AD genetic risk factors (e...
October 5, 2024: Translational Psychiatry