Related Experiment Video
Updated: Dec 27, 2025
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm
Jihoon Oh1, Baek-Lok Oh2, Kyong-Uk Lee3
1Department of Psychiatry, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, South Korea.
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.
Insights
Deep learning algorithms accurately detect schizophrenia using structural MRI scans, identifying key brain regions. This approach shows promise for supplementary diagnostic information in clinical settings.
Area of Science:
- Neuroimaging
- Artificial Intelligence
- Psychiatry
Background:
- Schizophrenia diagnosis is challenging despite known structural brain abnormalities.
- Magnetic resonance imaging (MRI) offers structural insights but lacks definitive diagnostic markers.
- Developing automated methods for schizophrenia detection from MRI is crucial.
Purpose of the Study:
- To develop and evaluate a deep learning algorithm for detecting schizophrenia using structural MRI data.
- To assess the algorithm's performance on independent datasets and identify key brain regions involved.
Main Methods:
- A deep convolutional neural network was trained on 873 structural MRI datasets from schizophrenia patients and healthy controls.
- The algorithm was tested on both familiar and novel datasets, including one with early-stage patients.
- Performance was quantified using the area under the receiver operating characteristic curve (AUC).
Main Results:
- The algorithm achieved a high AUC of 0.96 in detecting schizophrenia on randomly selected images.
- Performance on an unseen dataset was strong (AUC 0.71-0.90), but decreased to AUC 0.71 for early-stage patients.
- The right temporal and parietal areas were most influential in the algorithm's classification.
Conclusions:
- Deep learning effectively detects schizophrenia from structural MRI, highlighting significant brain regions.
- The algorithm demonstrates acceptable performance for early-stage schizophrenia, suggesting clinical utility.
- This AI approach can supplement diagnosis by delineating schizophrenia's structural characteristics.
