Neuro4Neuro: A neural network approach for neural tract segmentation using large-scale population-based diffusion imaging

Subtle changes in white matter (WM) microstructure have been associated with normal aging and neurodegeneration. To study these associations in more detail, it is highly important that the WM tracts can be accurately and reproducibly characterized from brain diffusion MRI. In addition, to enable analysis of WM tracts in large datasets and in clinical practice it is essential to have methodology that is fast and easy to apply. This work therefore presents a new approach for WM tract segmentation: Neuro4Neuro, that is capable of direct extraction of WM tracts from diffusion tensor images using convolutional neural network (CNN). This 3D end-to-end method is trained to segment 25 WM tracts in aging individuals from a large population-based study (N=9752, 1.5T MRI). The proposed method showed good segmentation performance and high reproducibility, i.e., a high spatial agreement (Cohen's kappa, κ=0.72-0.83) and a low scan-rescan error in tract-specific diffusion measures (e.g., fractional anisotropy: ε=1%-5%). The reproducibility of the proposed method was higher than that of a tractography-based segmentation algorithm, while being orders of magnitude faster (0.5s to segment one tract). In addition, we showed that the method successfully generalizes to diffusion scans from an external dementia dataset (N=58, 3T MRI). In two proof-of-principle experiments, we associated WM microstructure obtained using the proposed method with age in a normal elderly population, and with disease subtypes in a dementia cohort. In concordance with the literature, results showed a widespread reduction of microstructural organization with aging and substantial group-wise microstructure differences between dementia subtypes. In conclusion, we presented a highly reproducible and fast method for WM tract segmentation that has the potential of being used in large-scale studies and clinical practice.

[1]  Paul M. Thompson,et al.  Automatic clustering of white matter fibers in brain diffusion MRI with an application to genetics , 2014, NeuroImage.

[2]  Bo Li,et al.  Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset , 2018, MLMI@MICCAI.

[3]  Martin Styner,et al.  TRAFIC: fiber tract classification using deep learning , 2018, Medical Imaging.

[4]  Michael Brady,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[5]  Maxime Descoteaux,et al.  Recognition of white matter bundles using local and global streamline-based registration and clustering , 2017, NeuroImage.

[6]  Nick C Fox,et al.  Sensitivity of revised diagnostic criteria for the behavioural variant of frontotemporal dementia. , 2011, Brain : a journal of neurology.

[7]  Derek K. Jones,et al.  The effect of filter size on VBM analyses of DT-MRI data , 2005, NeuroImage.

[8]  Arthur W. Toga,et al.  Atlas-based whole brain white matter analysis using large deformation diffeomorphic metric mapping: Application to normal elderly and Alzheimer's disease participants , 2009, NeuroImage.

[9]  Wiro Niessen,et al.  A hybrid deep learning framework for integrated segmentation and registration: evaluation on longitudinal white matter tract changes , 2019, MICCAI.

[10]  C. Tappert,et al.  A Survey of Binary Similarity and Distance Measures , 2010 .

[11]  Wiro J. Niessen,et al.  White matter atrophy and lesion formation explain the loss of structural integrity of white matter in aging , 2008, NeuroImage.

[12]  Paul M. Thompson,et al.  Fibernet 2.0: An Automatic Neural Network Based Tool for Clustering White Matter Fibers in the Brain , 2017, bioRxiv.

[13]  Maxime Descoteaux,et al.  Tractography and machine learning: Current state and open challenges , 2019, Magnetic resonance imaging.

[14]  Stephen M. Smith,et al.  Using GPUs to accelerate computational diffusion MRI: From microstructure estimation to tractography and connectomes , 2018, NeuroImage.

[15]  Wiro J. Niessen,et al.  Tract-specific white matter degeneration in aging: The Rotterdam Study , 2015, Alzheimer's & Dementia.

[16]  Wiro J. Niessen,et al.  Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification , 2007, NeuroImage.

[17]  Randy L. Gollub,et al.  Reproducibility of quantitative tractography methods applied to cerebral white matter , 2007, NeuroImage.

[18]  Thomas R. Barrick,et al.  Atlas-based segmentation of white matter tracts of the human brain using diffusion tensor tractography and comparison with classical dissection , 2008, NeuroImage.

[19]  Jan Sijbers,et al.  ExploreDTI: a graphical toolbox for processing, analyzing, and visualizing diffusion MR data , 2009 .

[20]  P. Szeszko,et al.  MRI atlas of human white matter , 2006 .

[21]  Peter F. Neher,et al.  Learn to Track: Deep Learning for Tractography , 2017, bioRxiv.

[22]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[23]  Simon K. Warfield,et al.  Automated delineation of white matter fiber tracts with a multiple region-of-interest approach , 2012, NeuroImage.

[24]  Bruce Fischl,et al.  Joint reconstruction of white-matter pathways from longitudinal diffusion MRI data with anatomical priors , 2016, NeuroImage.

[25]  Stefan Klein,et al.  Improving alignment in Tract-based spatial statistics: Evaluation and optimization of image registration , 2013, NeuroImage.

[26]  Peter F. Neher,et al.  TractSeg - Fast and accurate white matter tract segmentation , 2018, NeuroImage.

[27]  Carl-Fredrik Westin,et al.  The white matter query language: a novel approach for describing human white matter anatomy , 2015, Brain Structure and Function.

[28]  Alexandra J. Golby,et al.  Deep White Matter Analysis: Fast, Consistent Tractography Segmentation Across Populations and dMRI Acquisitions , 2019, MICCAI.

[29]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[30]  Tonya White,et al.  White matter ‘potholes’ in early-onset schizophrenia: A new approach to evaluate white matter microstructure using diffusion tensor imaging , 2009, Psychiatry Research: Neuroimaging.

[31]  R. Laforce.  Behavioral and language variants of frontotemporal dementia: A review of key symptoms , 2013, Clinical Neurology and Neurosurgery.

[32]  Monique M. B. Breteler,et al.  The Rotterdam Study: 2016 objectives and design update , 2015, European Journal of Epidemiology.

[33]  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.

[34]  Derek K. Jones,et al.  White matter organization in developmental coordination disorder: A pilot study exploring the added value of constrained spherical deconvolution , 2018, NeuroImage: Clinical.

[35]  F. Crick,et al.  Backwardness of human neuroanatomy , 1993, Nature.

[36]  Tomas Jonsson,et al.  The dimensionality of between‐person differences in white matter microstructure in old age , 2013, Human brain mapping.

[37]  Haruyasu Yamada,et al.  Normal aging in the central nervous system: quantitative MR diffusion-tensor analysis , 2002, Neurobiology of Aging.

[38]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[39]  Carl-Fredrik Westin,et al.  A comparison of three fiber tract delineation methods and their impact on white matter analysis , 2018, NeuroImage.

[40]  Jerry L. Prince,et al.  Direct segmentation of the major white matter tracts in diffusion tensor images , 2011, NeuroImage.

[41]  Matthias J. Müller,et al.  Color-coded diffusion-tensor-imaging of posterior cingulate fiber tracts in mild cognitive impairment , 2005, Neurobiology of Aging.

[42]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[43]  D. Mantini,et al.  Exploring quantitative group-wise differentiation of Alzheimer’s disease and behavioural variant frontotemporal dementia using tract-specific microstructural white matter and functional connectivity measures at multiple time points , 2019, European Radiology.

[44]  Timothy Dozat,et al.  Incorporating Nesterov Momentum into Adam , 2016 .

[45]  Peter A. Calabresi,et al.  Tract probability maps in stereotaxic spaces: Analyses of white matter anatomy and tract-specific quantification , 2008, NeuroImage.

[46]  Kaiming Li,et al.  Automatic clustering of white matter fibers based on symbolic sequence analysis , 2010, Medical Imaging.

[47]  Mark W. Woolrich,et al.  Probabilistic diffusion tractography with multiple fibre orientations: What can we gain? , 2007, NeuroImage.

[48]  Wiro J Niessen,et al.  Global and focal white matter integrity in breast cancer survivors 20 years after adjuvant chemotherapy , 2014, Human brain mapping.

[49]  Anqi Qiu,et al.  Multi-label segmentation of white matter structures: Application to neonatal brains , 2014, NeuroImage.

[50]  Marion Smits,et al.  Early-stage differentiation between presenile Alzheimer’s disease and frontotemporal dementia using arterial spin labeling MRI , 2015, European Radiology.

[51]  S. Wakana,et al.  Fiber tract-based atlas of human white matter anatomy. , 2004, Radiology.

[52]  J. Morris,et al.  The diagnosis of dementia due to Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer's disease , 2011, Alzheimer's & Dementia.

[53]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[54]  Arnav Bhavsar,et al.  FS2Net: Fiber Structural Similarity Network (FS2Net) for Rotation Invariant Brain Tractography Segmentation Using Stacked LSTM Based Siamese Network , 2019, CAIP.

[55]  Seyed-Ahmad Ahmadi,et al.  Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound , 2016, Comput. Vis. Image Underst..

[56]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[57]  Mark W. Woolrich,et al.  FSL , 2012, NeuroImage.

[58]  Pew-Thian Yap,et al.  DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks , 2019, GLMI@MICCAI.

[59]  Carl-Fredrik Westin,et al.  Automatic Tractography Segmentation Using a High-Dimensional White Matter Atlas , 2007, IEEE Transactions on Medical Imaging.

[60]  Klaus H. Maier-Hein,et al.  nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation , 2018, Bildverarbeitung für die Medizin.

[61]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[62]  Stephen M. Smith,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[63]  Brian B. Avants,et al.  High-Dimensional Spatial Normalization of Diffusion Tensor Images Improves the Detection of White Matter Differences: An Example Study Using Amyotrophic Lateral Sclerosis , 2007, IEEE Transactions on Medical Imaging.

[64]  Alan Connelly,et al.  Robust determination of the fibre orientation distribution in diffusion MRI: Non-negativity constrained super-resolved spherical deconvolution , 2007, NeuroImage.

[65]  Christophe Lenglet,et al.  Automatic clustering and population analysis of white matter tracts using maximum density paths , 2014, NeuroImage.

[66]  Daniel Rueckert,et al.  Tract-based spatial statistics: Voxelwise analysis of multi-subject diffusion data , 2006, NeuroImage.

[67]  Peter F. Neher,et al.  The challenge of mapping the human connectome based on diffusion tractography , 2017, Nature Communications.

[68]  P. Ellen Grant,et al.  TRActs constrained by UnderLying INfant anatomy (TRACULInA): An automated probabilistic tractography tool with anatomical priors for use in the newborn brain , 2019, NeuroImage.

[69]  S. Wakana,et al.  MRI Atlas of Human White Matter , 2005 .

[70]  Samuel Powell,et al.  Reliability and Repeatability of Quantitative Tractography Methods for Mapping Structural White Matter Connectivity in Preterm and Term Infants at Term-Equivalent Age , 2014, PloS one.

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