Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm

Objective: Although distinctive structural abnormalities occur in patients with schizophrenia, detecting schizophrenia with 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 were used to train a deep convolutional neural network (a total of 873 structural MRI sets). Results: A deep learning algorithm trained with structural MR images detected schizophrenia in randomly selected images with a reliable performance (AUC of 0.96). It could also find MR images from schizophrenia patients in an untrained 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 regions contributing the most to the performance of the algorithm were the right temporal area, followed by the right parietal area. Semitrained clinical specialists hardly discriminated schizophrenia from healthy controls (AUC: 0.61) in the set of 100 randomly selected brain images. Conclusions: The deep learning algorithm showed good performance for 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 structural characteristics of schizophrenia and to provide supplementary information on the diagnosis in clinical settings.