A Caltech Library Service

Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm

Oh, Jihoon and Oh, Baek-Lok and Lee, Kyong-Uk and Chae, Jeong-Ho and Yun, Kyongsik (2020) Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm. Frontiers in Psychiatry, 11 . Art. No. 16. ISSN 1664-0640. PMCID PMC7008229.

[img] PDF - Published Version
Creative Commons Attribution.

[img] Archive (ZIP) (Supplementary Figures, Tables, and Videos) - Supplemental Material
Creative Commons Attribution.


Use this Persistent URL to link to this item:


Objective: Although distinctive structural abnormalities occur in patients with schizophrenia, detecting schizophrenia with magnetic resonance imaging (MRI) remains challenging. This study aimed to detect schizophrenia in structural MRI data sets using a trained deep learning algorithm. Method: Five public MRI data sets (BrainGluSchi, COBRE, MCICShare, NMorphCH, and NUSDAST) from schizophrenia patients and normal subjects, for a total of 873 structural MRI data sets, were used to train a deep convolutional neural network. Results: The deep learning algorithm trained with structural MR images detected schizophrenia in randomly selected images with reliable performance (area under the receiver operating characteristic curve [AUC] of 0.96). The algorithm could also identify MR images from schizophrenia patients in a previously unencountered data set with an AUC of 0.71 to 0.90. The deep learning algorithm’s classification performance degraded to an AUC of 0.71 when a new data set with younger patients and a shorter duration of illness than the training data sets was presented. The brain region contributing the most to the performance of the algorithm was the right temporal area, followed by the right parietal area. Semitrained clinical specialists hardly discriminated schizophrenia patients from healthy controls (AUC: 0.61) in the set of 100 randomly selected brain images. Conclusions: The deep learning algorithm showed good performance in detecting schizophrenia and identified relevant structural features from structural brain MRI data; it had an acceptable classification performance in a separate group of patients at an earlier stage of the disease. Deep learning can be used to delineate the structural characteristics of schizophrenia and to provide supplementary diagnostic information in clinical settings.

Item Type:Article
Related URLs:
URLURL TypeDescription CentralArticle
Yun, Kyongsik0000-0002-6103-7187
Additional Information:© 2020 Oh, Oh, Lee, Chae and Yun. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Received: 28 June 2019; Accepted: 08 January 2020; Published: 03 February 2020. The BrainGluSchi data set was obtained from University of New Mexico Hospitals to measure glutamatergic and neuronal dysfunction in the gray and white matter of schizophrenia patients. COBRE (The Center for Biomedical Research Excellence in Brain Function and Mental Illness) has published structural and functional MRI data obtained from schizophrenia patients and normal subjects, and resting-state functional MRI data were used to diagnose schizophrenia. MCICShare comprised structural and resting-state functional MRI data. NUSDAST (Northwestern University Schizophrenia Data and Software Tool) includes longitudinal data (up to 2 years) obtained from schizophrenia patients, and NMorphCH data (Neuromorphometry by Computer Algorithm Chicago) were acquired by the Northwestern University Neuroimaging Data Archive (NUNDA). The authors appreciate S. Rho, K. Yu, J. Oh, K. Kim, S. Lee, J. Lim, and S. Kim for their constructive comments and help with evaluation of the structural MRI data. Data Availability Statement: The datasets generated for this study are available on request to the corresponding authors. Ethics Statement: The studies involving human participants were reviewed and approved by Institutional Review Board of Seoul St. Mary’s Hospital (KC18ZESI0615). Written informed consent for participation was not required for this study in accordance with the national legislation and the institutional requirements. Author Contributions: Concept and design: JO, KY. Data acquisition: JO, K-UL. Analysis: JO, KY. Data interpretation: KY, JO, B-LO, K-UL. Drafting of the manuscript: JO, KY. Critical revision of the manuscript: J-HC, B-LO, K-UL. Obtaining funding: JO. This study was supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number: HL19C0007) and the Research Fund of Seoul St. Mary’s Hospital, The Catholic University of Korea. The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Funding AgencyGrant Number
Korea Health Industry Development InstituteUNSPECIFIED
Ministry of Health and Welfare (Korea)HL19C0007
Seoul St. Mary’s HospitalUNSPECIFIED
Catholic University of KoreaUNSPECIFIED
Subject Keywords:schizophrenia, deep learning, MRI, classification, structural abnormalities
PubMed Central ID:PMC7008229
Record Number:CaltechAUTHORS:20200312-145714944
Persistent URL:
Official Citation:Oh J, Oh B-L, Lee K-U, Chae J-H and Yun K (2020) Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm. Front. Psychiatry 11:16. doi: 10.3389/fpsyt.2020.00016
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:101900
Deposited By: Tony Diaz
Deposited On:12 Mar 2020 22:22
Last Modified:03 Aug 2020 22:39

Repository Staff Only: item control page