Classification of MDD using a Transformer classifier with large‐scale multisite resting‐state fMRI data

• Published in: Human brain mapping 2024-01, Vol.45 (1), p.e26542-n/a
• Main Authors: Dai, Peishan, Zhou, Ying, Shi, Yun, Lu, Da, Chen, Zailiang, Zou, Beiji, Liu, Kun, Liao, Shenghui
• Format: Article
• Language: English
• Subjects: Abnormalities; Accuracy; Brain; Brain mapping; Brain research; Cerebral cortex; Classification; Complexity; Cortex (frontal); Datasets; Deep learning; Feature selection; Females; functional connectivity; Functional magnetic resonance imaging; Machine learning; major depressive disorder; Mathematical models; Mental depression; Mental disorders; Natural language; Neural networks; Parameters; recurrence; Sample size; Time series; Training; Transformer; Transformers
• ISSN: 1065-9471; 1097-0193
• DOI: 10.1002/hbm.26542

Major depressive disorder (MDD) is one of the most common psychiatric disorders worldwide with high recurrence rate. Identifying MDD patients, particularly those with recurrent episodes with resting‐state fMRI, may reveal the relationship between MDD and brain function. We proposed a Transformer‐Encoder model, which utilized functional connectivity extracted from large‐scale multisite rs‐fMRI datasets to classify MDD and HC. The model discarded the Transformer's Decoder part, reducing the model's complexity and decreasing the number of parameters to adapt to the limited sample size and it does not require a complex feature selection process and achieves end‐to‐end classification. Additionally, our model is suitable for classifying data combined from multiple brain atlases and has an optional unsupervised pre‐training module to acquire optimal initial parameters and speed up the training process. The model's performance was tested on a large‐scale multisite dataset and identified brain regions affected by MDD using the Grad‐CAM method. After conducting five‐fold cross‐validation, our model achieved an average classification accuracy of 68.61% on a dataset consisting of 1611 samples. For the selected recurrent MDD dataset, the model reached an average classification accuracy of 78.11%. Abnormalities were detected in the frontal gyri and cerebral cortex of MDD patients in both datasets. Furthermore, the identified brain regions in the recurrent MDD dataset generally exhibited a higher contribution to the model's performance. Major depressive disorder (MDD) classification may reveal the relationship between MDD and brain function, and aid in the diagnosis and treatment of the disorder. We proposed a Transformer‐Encoder model for MDD classification without feature selection, identifying the brain regions affected by MDD on a large‐scale multisite dataset.