Multi-subject Manifold Alignment of Functional Network Structures via Joint Diagonalization

Functional magnetic resonance imaging group studies rely on the ability to establish correspondence across individuals. This enables location specific comparison of functional brain characteristics. Registration is often based on morphology and does not take variability of functional localization into account. This can lead to a loss of specificity, or confounds when studying diseases. In this paper we propose multi-subject functional registration by manifold alignment via coupled joint diagonalization. The functional network structure of each subject is encoded in a diffusion map, where functional relationships are decoupled from spatial position. Two-step manifold alignment estimates initial correspondences between functionally equivalent regions. Then, coupled joint diagonalization establishes common eigenbases across all individuals, and refines the functional correspondences. We evaluate our approach on fMRI data acquired during a language paradigm. Experiments demonstrate the benefits in matching accuracy achieved by coupled joint diagonalization compared to previously proposed functional alignment approaches, or alignment based on structural correspondences.

[1]  Polina Golland,et al.  Learning an Atlas of a Cognitive Process in Its Functional Geometry , 2011, IPMI.

[2]  Charles K. Chui,et al.  Special issue on diffusion maps and wavelets , 2006 .

[3]  Stephen M Smith,et al.  Variability in fMRI: A re‐examination of inter‐session differences , 2005, Human brain mapping.

[4]  Hongbin Zha,et al.  Unsupervised Image Matching Based on Manifold Alignment , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Leo Grady,et al.  FOCUSR: Feature Oriented Correspondence Using Spectral Regularization--A Method for Precise Surface Matching , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Andriy Myronenko,et al.  Point Set Registration: Coherent Point Drift , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[8]  Spyros S. Kollias,et al.  Intraoperative validation of functional magnetic resonance imaging and cortical reorganization patterns in patients with brain tumors involving the primary motor cortex , 1999 .

[9]  Wotao Yin,et al.  A feasible method for optimization with orthogonality constraints , 2013, Math. Program..

[10]  Daniel D. Lee,et al.  Semisupervised alignment of manifolds , 2005, AISTATS.

[11]  Polina Golland,et al.  Decoupling function and anatomy in atlases of functional connectivity patterns: Language mapping in tumor patients , 2014, NeuroImage.

[12]  Chang Wang,et al.  A General Framework for Manifold Alignment , 2009, AAAI Fall Symposium: Manifold Learning and Its Applications.

[13]  Karl J. Friston,et al.  Statistical parametric maps in functional imaging: A general linear approach , 1994 .

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

[15]  Chang Wang,et al.  Multiscale Manifold Learning , 2013, AAAI.

[16]  EynardDavide,et al.  Multimodal Manifold Analysis by Simultaneous Diagonalization of Laplacians , 2015 .

[17]  Peter J. Ramadge,et al.  Inter-subject alignment of human cortical anatomy using functional connectivity , 2013, NeuroImage.

[18]  Radu Horaud,et al.  Articulated shape matching using Laplacian eigenfunctions and unsupervised point registration , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Leo Grady,et al.  Fast Brain Matching with Spectral Correspondence , 2011, IPMI.

[20]  Bryan R. Conroy,et al.  Function-based Intersubject Alignment of Human Cortical Anatomy , 2009, Cerebral cortex.

[21]  Sridhar Mahadevan,et al.  Manifold alignment using Procrustes analysis , 2008, ICML '08.

[22]  Di Jiang,et al.  Groupwise spatial normalization of fMRI data based on multi-range functional connectivity patterns , 2013, NeuroImage.

[23]  Ahmed M. Elgammal,et al.  Learning a Joint Manifold Representation from Multiple Data Sets , 2010, 2010 20th International Conference on Pattern Recognition.

[24]  Terry M. Peters,et al.  3D statistical neuroanatomical models from 305 MRI volumes , 1993, 1993 IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference.

[25]  Antoine Souloumiac,et al.  Jacobi Angles for Simultaneous Diagonalization , 1996, SIAM J. Matrix Anal. Appl..

[26]  Daniel Rueckert,et al.  Groupwise Simultaneous Manifold Alignment for High-Resolution Dynamic MR Imaging of Respiratory Motion , 2013, IPMI.