Graph Saliency Maps Through Spectral Convolutional Networks: Application to Sex Classification with Brain Connectivity
Graph convolutional networks (GCNs) allow to apply traditional convolution operations in non-Euclidean domains, where data are commonly modelled as irregular graphs. Medical imaging and, in particular, neuroscience studies often rely on such graph representations, with brain connectivity networks being a characteristic example, while ultimately seeking the locus of phenotypic or disease-related differences in the brain. These regions of interest (ROIs) are, then, considered to be closely associated with function and/or behaviour. Driven by this, we explore GCNs for the task of ROI identification and propose a visual attribution method based on class activation mapping. By undertaking a sex classification task as proof of concept, we show that this method can be used to identify salient nodes (brain regions) without prior node labels. Based on experiments conducted on neuroimaging data of more than 5000 participants from UK Biobank, we demonstrate the robustness of the proposed method in highlighting reproducible regions across individuals. We further evaluate the neurobiological relevance of the identified regions based on evidence from large-scale UK Biobank studies.
This research has been conducted using the UK Biobank Resource under Application Number 12579 and funded by the EPSRC Doctoral Prize Fellowship funding scheme.
- 2.Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
- 4.Ritchie, S.J., Cox, S.R., Shen, X., et al.: Sex differences in the adult human brain: evidence from 5,216 UK Biobank participants. bioRxiv (2017)Google Scholar
- 5.Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2921–2929. IEEE (2016)Google Scholar
- 6.Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model CNNs. In: Proceedings of CVPR, vol. 1, p. 3 (2017)Google Scholar
- 7.Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, pp. 3844–3852 (2016)Google Scholar
- 8.Levie, R., Monti, F., Bresson, X., Bronstein, M.M.: CayleyNets: graph convolutional neural networks with complex rational spectral filters. arXiv preprint arXiv:1705.07664 (2017)
- 9.Zhou, Z., Li, X.: Convolution on graph: a high-order and adaptive approach (2018)Google Scholar
- 10.Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
- 11.Baumgartner, C.F., Koch, L.M., Tezcan, K.C., Ang, J.X., Konukoglu, E.: Visual feature attribution using Wasserstein GANs. arXiv preprint arXiv:1711.08998 (2017)
- 13.Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. arXiv preprint arXiv:1412.6856 (2014)
- 14.Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
- 17.Beckmann, C.F., Smith, S.M.: Probabilistic independent component analysis for functional magnetic resonance imaging. IEEE TMI 23(2), 137–152 (2004)Google Scholar