Balanced Graph Structure Information for Brain Disease Detection
This work addresses brain disease detection for medical diagnostics, presenting an incremental improvement by combining existing graph structure types to mitigate their individual limitations.
The paper tackled the problem of detecting brain diseases like autism or schizophrenia by proposing Bargrain, a method that models both filtered correlation and optimal sample graphs using GCNs to address noise and overfitting issues in existing approaches, resulting in outperforming state-of-the-art methods in classification tasks as measured by average F1 scores.
Analyzing connections between brain regions of interest (ROI) is vital to detect neurological disorders such as autism or schizophrenia. Recent advancements employ graph neural networks (GNNs) to utilize graph structures in brains, improving detection performances. Current methods use correlation measures between ROI's blood-oxygen-level-dependent (BOLD) signals to generate the graph structure. Other methods use the training samples to learn the optimal graph structure through end-to-end learning. However, implementing those methods independently leads to some issues with noisy data for the correlation graphs and overfitting problems for the optimal graph. In this work, we proposed Bargrain (balanced graph structure for brains), which models two graph structures: filtered correlation matrix and optimal sample graph using graph convolution networks (GCNs). This approach aims to get advantages from both graphs and address the limitations of only relying on a single type of structure. Based on our extensive experiment, Bargrain outperforms state-of-the-art methods in classification tasks on brain disease datasets, as measured by average F1 scores.