Graph Convolutions on Spectral Embeddings: Learning of Cortical Surface Data

Neuronal cell bodies mostly reside in the cerebral cortex. The study of this thin and highly convoluted surface is essential for understanding how the brain works. The analysis of surface data is, however, challenging due to the high variability of the cortical geometry. This paper presents a novel approach for learning and exploiting surface data directly across surface domains. Current approaches rely on geometrical simplifications, such as spherical inflations, a popular but costly process. For instance, the widely used FreeSurfer takes about 3 hours to parcellate brain surfaces on a standard machine. Direct learning of surface data via graph convolutions would provide a new family of fast algorithms for processing brain surfaces. However, the current limitation of existing state-of-the-art approaches is their inability to compare surface data across different surface domains. Surface bases are indeed incompatible between brain geometries. This paper leverages recent advances in spectral graph matching to transfer surface data across aligned spectral domains. This novel approach enables a direct learning of surface data across compatible surface bases. It exploits spectral filters over intrinsic representations of surface neighborhoods. We illustrate the benefits of this approach with an application to brain parcellation. We validate the algorithm over 101 manually labeled brain surfaces. The results show a significant improvement in labeling accuracy over recent Euclidean approaches, while gaining a drastic speed improvement over conventional methods.

[1]  Ben Glocker,et al.  Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks , 2017, MICCAI.

[2]  Maks Ovsjanikov,et al.  Functional maps , 2012, ACM Trans. Graph..

[3]  Xavier Bresson,et al.  CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters , 2017, IEEE Transactions on Signal Processing.

[4]  Nikos Makris,et al.  Automatically parcellating the human cerebral cortex. , 2004, Cerebral cortex.

[5]  Pierre Vandergheynst,et al.  Geodesic Convolutional Neural Networks on Riemannian Manifolds , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[6]  Nicholas Ayache,et al.  Brain Transfer: Spectral Analysis of Cortical Surfaces and Functional Maps , 2015, IPMI.

[7]  Alexander M. Bronstein,et al.  Coupled quasi‐harmonic bases , 2012, Comput. Graph. Forum.

[8]  Jose Dolz,et al.  3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study , 2016, NeuroImage.

[9]  Jonathan Masci,et al.  Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Arno Klein,et al.  Large-scale evaluation of ANTs and FreeSurfer cortical thickness measurements , 2014, NeuroImage.

[11]  Nicholas Ayache,et al.  Spectral Forests: Learning of Surface Data, Application to Cortical Parcellation , 2015, MICCAI.

[12]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[13]  Satrajit S. Ghosh,et al.  Mindboggling morphometry of human brains , 2016, bioRxiv.

[14]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Michael M. Bronstein,et al.  Making Laplacians commute , 2013, ArXiv.

[16]  Christos Davatzikos,et al.  ODVBA: Optimally-Discriminative Voxel-Based Analysis , 2011, IEEE Transactions on Medical Imaging.

[17]  Michael Weiner,et al.  Unbiased tensor-based morphometry: Improved robustness and sample size estimates for Alzheimer's disease clinical trials , 2013, NeuroImage.

[18]  Davide Eynard,et al.  Multimodal Manifold Analysis by Simultaneous Diagonalization of Laplacians , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Ben Glocker,et al.  Spectral Graph Convolutions for Population-based Disease Prediction , 2017, MICCAI.

[20]  Vince D. Calhoun,et al.  Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls , 2017, NeuroImage.

[21]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

[22]  Jonathan Masci,et al.  Learning shape correspondence with anisotropic convolutional neural networks , 2016, NIPS.

[23]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.