A Spherical Convolutional Neural Network for White Matter Structure Imaging via dMRI

Diffusion Magnetic Resonance Imaging (dMRI) is a powerful non-invasive and in-vivo imaging modality for probing brain white matter structure. Convolutional neural networks (CNNs) have been shown to be a powerful tool for many computer vision problems where the signals are acquired on a regular grid and where translational invariance is important. However, as we are considering dMRI signals that are acquired on a sphere, rotational invariance, rather than translational, is desired. In this work, we propose a spherical CNN model with fully spectral domain convolutional and non-linear layers. It provides rotational invariance and is adapted to the real nature of dMRI signals and uniform random distribution of sampling points. The proposed model is positively evaluated on the problem of estimation of neurite orientation dispersion and density imaging (NODDI) parameters on the data from Human Connectome Project (HCP).

[1]  M. Sugiura.  Unitary representations and harmonic analysis : an introduction , 1990 .

[2]  Alan Connelly,et al.  MRtrix3: A fast, flexible and open software framework for medical image processing and visualisation , 2019, NeuroImage.

[3]  Herbert H. H. Homeier,et al.  Some Properties of the Coupling Coefficients of Real Spherical Harmonics and Their Relation to Gaunt Coefficients , 1996 .

[4]  D. Le Bihan,et al.  Diffusion tensor imaging: Concepts and applications , 2001, Journal of magnetic resonance imaging : JMRI.

[5]  Jianhui Zhong,et al.  DLpN: Single-Shell NODDI Using Deep Learner Estimated Isotropic Volume Fraction , 2021, ArXiv.

[6]  Chun-Hung Yeh,et al.  MRtrix3: A fast, flexible and open software framework for medical image processing and visualisation , 2019, NeuroImage.

[7]  M. E. Rose.  Elementary Theory of Angular Momentum , 1957 .

[8]  Yaniv Assaf,et al.  Composite hindered and restricted model of diffusion (CHARMED) MR imaging of the human brain , 2005, NeuroImage.

[9]  Daniel Cremers,et al.  Rotation-Equivariant Deep Learning for Diffusion MRI , 2021, ArXiv.

[10]  R. Deriche,et al.  Diffusion MRI Fiber Orientation Distribution Function Estimation Using Voxel-Wise Spherical U-Net , 2021, Computational Diffusion MRI.

[11]  Daniel C. Alexander,et al.  NODDI: Practical in vivo neurite orientation dispersion and density imaging of the human brain , 2012, NeuroImage.

[12]  Daniel C Alexander,et al.  Noninvasive quantification of solid tumor microstructure using VERDICT MRI. , 2014, Cancer research.

[13]  Kostas Daniilidis,et al.  Learning SO(3) Equivariant Representations with Spherical CNNs , 2017, International Journal of Computer Vision.

[14]  David H. Miller,et al.  Sensitivity of multi-shell NODDI to multiple sclerosis white matter changes: a pilot study. , 2017, Functional neurology.

[15]  Chuyang Ye,et al.  A deep network for tissue microstructure estimation using modified LSTM units , 2019, Medical Image Anal..

[16]  Timothy Edward John Behrens,et al.  Characterization and propagation of uncertainty in diffusion‐weighted MR imaging , 2003, Magnetic resonance in medicine.

[17]  Dorit Merhof,et al.  Direct Estimation of Fiber Orientations Using Deep Learning in Diffusion Imaging , 2016, MLMI@MICCAI.

[18]  Guido Gerig,et al.  Equivariant Spherical Deconvolution: Learning Sparse Orientation Distribution Functions from Spherical Data , 2021, IPMI.

[19]  Baba C. Vemuri,et al.  DMR-CNN: A CNN Tailored For DMR Scans With Applications To PD Classification , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[20]  D. Healy,et al.  Computing Fourier Transforms and Convolutions on the 2-Sphere , 1994 .

[21]  P. Basser,et al.  Axcaliber: A method for measuring axon diameter distribution from diffusion MRI , 2008, Magnetic resonance in medicine.

[22]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[23]  Nicola Toschi,et al.  Early axonal damage in normal appearing white matter in multiple sclerosis: Novel insights from multi-shell diffusion MRI , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  David J. Schwartzman,et al.  Neurite orientation and dispersion density imaging (NODDI) detects cortical and corticospinal tract degeneration in ALS , 2018, Journal of Neurology, Neurosurgery, and Psychiatry.

[25]  Rachid Deriche,et al.  The Dmipy Toolbox: Diffusion MRI Multi-Compartment Modeling and Microstructure Recovery Made Easy , 2019, Front. Neuroinform..

[26]  Josien P. W. Pluim,et al.  Muti-shell Diffusion MRI Harmonisation and Enhancement Challenge (MUSHAC): Progress and Results , 2019, Computational Diffusion MRI.

[27]  Zhiwei Li,et al.  Fast learning of fiber orientation distribution function for MR tractography using convolutional neural network. , 2019, Medical physics.

[28]  Chuyang Ye.  Estimation of Tissue Microstructure Using a Deep Network Inspired by a Sparse Reconstruction Framework , 2017, IPMI.

[29]  R. Deriche,et al.  Design of multishell sampling schemes with uniform coverage in diffusion MRI , 2013, Magnetic resonance in medicine.

[30]  Zhen Lin,et al.  Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network , 2018, NeurIPS.

[31]  Daniel Cremers,et al.  q-Space Deep Learning: Twelve-Fold Shorter and Model-Free Diffusion MRI Scans , 2016, IEEE Transactions on Medical Imaging.

[32]  Essa Yacoub,et al.  The WU-Minn Human Connectome Project: An overview , 2013, NeuroImage.