Three-Dimensional Convolutional Autoencoder Extracts Features of Structural Brain Images With a “Diagnostic Label-Free” Approach: Application to Schizophrenia Datasets

• Published in: Frontiers in neuroscience Vol. 15; p. 652987
• Main Authors: Yamaguchi, Hiroyuki, Hashimoto, Yuki, Sugihara, Genichi, Miyata, Jun, Murai, Toshiya, Takahashi, Hidehiko, Honda, Manabu, Hishimoto, Akitoyo, Yamashita, Yuichi
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 07.07.2021; Frontiers Media S.A
• Subjects: Biomedical research; Brain research; convolutional autoencoder; Datasets; Deep learning; Dementia; Discrimination; machine learning; Magnetic resonance imaging; Medical imaging; Medical research; Mental disorders; Neural networks; Neuroimaging; Neuroscience; Patients; Regression analysis; Schizophrenia; structural MRI; Three dimensional imaging; deep learning; structural MRI; convolutional autoencoder; schizophrenia; diagnostic label; machine learning; neuroimaging
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2021.652987

There has been increasing interest in performing psychiatric brain imaging studies using deep learning. However, most studies in this field disregard three-dimensional (3D) spatial information and targeted disease discrimination, without considering the genetic and clinical heterogeneity of psychiat...