Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm

Jihoon Oh; Baek-Lok Oh; Kyong-Uk Lee; Jeong-Ho Chae; Kyongsik Yun

doi:10.3389/fpsyt.2020.00016

Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm

Front Psychiatry. 2020 Feb 3:11:16. doi: 10.3389/fpsyt.2020.00016. eCollection 2020.

Authors

Jihoon Oh¹, Baek-Lok Oh², Kyong-Uk Lee³, Jeong-Ho Chae¹, Kyongsik Yun^{4

5}

Affiliations

¹ Department of Psychiatry, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea.
² Department of Ophthalmology, Seoul National University Hospital, Seoul, South Korea.
³ Department of Psychiatry, Uijeongbu St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea.
⁴ Computation and Neural Systems, California Institute of Technology, Pasadena, CA, United States.
⁵ Bio-Inspired Technologies and Systems, Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA, United States.

Abstract

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.

Keywords: MRI; classification; deep learning; schizophrenia; structural abnormalities.