Deep neural networks on graph signals for brain imaging analysis
This work addresses brain imaging analysis for neuroscience applications, presenting an incremental improvement by combining existing graph-based methods with neural networks.
The paper tackles the problem of analyzing noise-degraded brain imaging data like MEG by proposing a deep neural network that integrates graph connectivity information with fully-connected layers, resulting in more discriminative representations and improved classification accuracy.
Brain imaging data such as EEG or MEG are high-dimensional spatiotemporal data often degraded by complex, non-Gaussian noise. For reliable analysis of brain imaging data, it is important to extract discriminative, low-dimensional intrinsic representation of the recorded data. This work proposes a new method to learn the low-dimensional representations from the noise-degraded measurements. In particular, our work proposes a new deep neural network design that integrates graph information such as brain connectivity with fully-connected layers. Our work leverages efficient graph filter design using Chebyshev polynomial and recent work on convolutional nets on graph-structured data. Our approach exploits graph structure as the prior side information, localized graph filter for feature extraction and neural networks for high capacity learning. Experiments on real MEG datasets show that our approach can extract more discriminative representations, leading to improved accuracy in a supervised classification task.