STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data

TL;DR

This paper introduces STANet, a deep learning model combining CNN and RNN for improved depression diagnosis using small, unbalanced fMRI datasets, achieving higher accuracy and AUC than existing methods.

Contribution

The study presents a novel spatio-temporal aggregation network that integrates ICA, multi-scale convolution, SMOTE, and AFGRU for more accurate depression classification from fMRI data.

Findings

Achieved 82.38% accuracy and 90.72% AUC in depression diagnosis.

STANet outperforms traditional classifiers and other deep learning models.

SMOTE improves minority class representation and model performance.

Abstract

Accurate diagnosis of depression is crucial for timely implementation of optimal treatments, preventing complications and reducing the risk of suicide. Traditional methods rely on self-report questionnaires and clinical assessment, lacking objective biomarkers. Combining fMRI with artificial intelligence can enhance depression diagnosis by integrating neuroimaging indicators. However, the specificity of fMRI acquisition for depression often results in unbalanced and small datasets, challenging the sensitivity and accuracy of classification models. In this study, we propose the Spatio-Temporal Aggregation Network (STANet) for diagnosing depression by integrating CNN and RNN to capture both temporal and spatial features of brain activity. STANet comprises the following steps:(1) Aggregate spatio-temporal information via ICA. (2) Utilize multi-scale deep convolution to capture detailed features. (3) Balance data using the SMOTE to generate new samples for minority classes. (4) Employ the AFGRU classifier, which combines Fourier transformation with GRU, to capture long-term dependencies, with an adaptive weight assignment mechanism to enhance model generalization. The experimental results demonstrate that STANet achieves superior depression diagnostic performance with 82.38% accuracy and a 90.72% AUC. The STFA module enhances classification by capturing deeper features at multiple scales. The AFGRU classifier, with adaptive weights and stacked GRU, attains higher accuracy and AUC. SMOTE outperforms other oversampling methods. Additionally, spatio-temporal aggregated features achieve better performance compared to using only temporal or spatial features. STANet outperforms traditional or deep learning classifiers, and functional connectivity-based classifiers, as demonstrated by ten-fold cross-validation.