Surface-constrained volumetric registration for the early developing brain

The T1-weighted and T2-weighted MRI contrasts of the infant brain evolve drastically during the first year of life. This poses significant challenges to inter- and intra-subject registration, which is key to subsequent statistical analyses. Existing registration methods that do not consider temporal contrast changes are ineffective for infant brain MRI data. To address this problem, we present in this paper a method for deformable registration of infant brain MRI. The key advantage of our method is threefold: (i) To deal with appearance changes, registration is performed based on segmented tissue maps instead of image intensity. Segmentation is performed by using an infant-centric algorithm previously developed by our group. (ii) Registration is carried out with respect to both cortical surfaces and volumetric tissue maps, thus allowing precise alignment of both cortical and subcortical structures. (iii) A dynamic elasticity model is utilized to allow large non-linear deformation. Experimental results in comparison with well-established registration methods indicate that our method yields superior accuracy in both cortical and subcortical alignment.

[1]  Olivier Salvado,et al.  3D shape context surface registration for cortical mapping , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[2]  Yaozong Gao,et al.  Learning‐based deformable registration for infant MRI by integrating random forest with auto‐context model , 2017, Medical physics.

[3]  Dinggang Shen,et al.  Consistent reconstruction of cortical surfaces from longitudinal brain MR images , 2012, NeuroImage.

[4]  Nicholas Ayache,et al.  Spherical Demons: Fast Diffeomorphic Landmark-Free Surface Registration , 2010, IEEE Transactions on Medical Imaging.

[5]  Rebecca C. Knickmeyer,et al.  A Structural MRI Study of Human Brain Development from Birth to 2 Years , 2008, The Journal of Neuroscience.

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

[7]  John H. Gilmore,et al.  Imaging structural and functional brain development in early childhood , 2018, Nature Reviews Neuroscience.

[8]  Dinggang Shen,et al.  HAMMER: hierarchical attribute matching mechanism for elastic registration , 2002, IEEE Transactions on Medical Imaging.

[9]  E. Kuhl,et al.  Mechanical properties of gray and white matter brain tissue by indentation. , 2015, Journal of the mechanical behavior of biomedical materials.

[10]  Dinggang Shen,et al.  Spatial distribution and longitudinal development of deep cortical sulcal landmarks in infants , 2014, NeuroImage.

[11]  Dinggang Shen,et al.  A computational growth model for measuring dynamic cortical development in the first year of life. , 2012, Cerebral cortex.

[12]  Yaozong Gao,et al.  LINKS: Learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images , 2015, NeuroImage.

[13]  Danni Ai,et al.  Local statistical deformation models for deformable image registration , 2018, Neurocomputing.

[14]  Yalin Wang,et al.  A Multivariate Surface-Based Analysis of the Putamen in Premature Newborns: Regional Differences within the Ventral Striatum , 2013, PloS one.

[15]  S. Heim,et al.  Development of structure and function in the infant brain: Implications for cognition, language and social behaviour , 2006, Neuroscience & Biobehavioral Reviews.

[16]  Dinggang Shen,et al.  Construction of 4D high-definition cortical surface atlases of infants: Methods and applications , 2015, Medical Image Anal..

[17]  D. Louis Collins,et al.  Retrospective evaluation of intersubject brain registration , 2003, IEEE Transactions on Medical Imaging.

[18]  Dinggang Shen,et al.  Statistical representation of high-dimensional deformation fields with application to statistically constrained 3D warping , 2006, Medical Image Anal..

[19]  Dinggang Shen,et al.  Learning-based deformable registration of MR brain images , 2006, IEEE Transactions on Medical Imaging.

[20]  Dinggang Shen,et al.  Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning , 2016, IEEE Transactions on Biomedical Engineering.

[21]  Dinggang Shen,et al.  Hierarchical and symmetric infant image registration by robust longitudinal-example-guided correspondence detection. , 2015, Medical physics.

[22]  Sahar Ahmad,et al.  Dynamic elasticity model for inter-subject non-rigid registration of 3D MRI brain scans , 2017, Biomed. Signal Process. Control..

[23]  J. Gilmore,et al.  Dynamic Development of Regional Cortical Thickness and Surface Area in Early Childhood. , 2015, Cerebral cortex.

[24]  Dinggang Shen,et al.  LABEL: Pediatric brain extraction using learning-based meta-algorithm , 2012, NeuroImage.

[25]  J. Gilmore,et al.  Mapping Longitudinal Development of Local Cortical Gyrification in Infants from Birth to 2 Years of Age , 2014, The Journal of Neuroscience.

[26]  J. Gilmore,et al.  Mapping region-specific longitudinal cortical surface expansion from birth to 2 years of age. , 2013, Cerebral cortex.

[27]  Nasser Kehtarnavaz,et al.  Brain Functional Localization: A Survey of Image Registration Techniques , 2007, IEEE Transactions on Medical Imaging.

[28]  Dinggang Shen,et al.  Longitudinal development of cortical thickness, folding, and fiber density networks in the first 2 years of life , 2014, Human brain mapping.

[29]  Stephen M. Smith,et al.  A global optimisation method for robust affine registration of brain images , 2001, Medical Image Anal..

[30]  Dinggang Shen,et al.  Mapping longitudinal hemispheric structural asymmetries of the human cerebral cortex from birth to 2 years of age. , 2014, Cerebral cortex.

[31]  J. Gilmore,et al.  Spatial Patterns, Longitudinal Development, and Hemispheric Asymmetries of Cortical Thickness in Infants from Birth to 2 Years of Age , 2015, The Journal of Neuroscience.

[32]  N. Makris,et al.  Regional infant brain development: an MRI-based morphometric analysis in 3 to 13 month olds. , 2013, Cerebral cortex.

[33]  Dinggang Shen,et al.  Simulating deformations of MR brain images for validation of atlas-based segmentation and registration algorithms , 2006, NeuroImage.

[34]  Bruce Fischl,et al.  Improved tractography alignment using combined volumetric and surface registration , 2010, NeuroImage.

[35]  Jing Hua,et al.  Non-rigid Surface Registration Using Spherical Thin-Plate Splines , 2007, MICCAI.

[36]  A. Dale,et al.  Cortical Surface-Based Analysis II: Inflation, Flattening, and a Surface-Based Coordinate System , 1999, NeuroImage.

[37]  J. Gilmore,et al.  Structural and Maturational Covariance in Early Childhood Brain Development , 2016, Cerebral cortex.

[38]  Daniel Rueckert,et al.  Automatic segmentation and reconstruction of the cortex from neonatal MRI , 2007, NeuroImage.

[39]  Richard M. Leahy,et al.  A Method for Automated Cortical Surface Registration and Labeling , 2012, WBIR.

[40]  Tom Vercauteren,et al.  Diffeomorphic demons: Efficient non-parametric image registration , 2009, NeuroImage.

[41]  Dinggang Shen,et al.  Development of Cortical Anatomical Properties from Early Childhood to Early Adulthood , 2022 .

[42]  Anders M. Dale,et al.  Cortical Surface-Based Analysis I. Segmentation and Surface Reconstruction , 1999, NeuroImage.

[43]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[44]  Hyunjin Park,et al.  Cortical surface registration using spherical thin-plate spline with sulcal lines and mean curvature as features , 2012, Journal of Neuroscience Methods.

[45]  Dinggang Shen,et al.  Computational neuroanatomy of baby brains: A review , 2019, NeuroImage.

[46]  Alan C. Evans,et al.  Early brain development in infants at high risk for autism spectrum disorder , 2017, Nature.

[47]  Bruce Fischl,et al.  Combined Volumetric and Surface Registration , 2009, IEEE Transactions on Medical Imaging.

[48]  Dinggang Shen,et al.  Predict brain MR image registration via sparse learning of appearance and transformation , 2015, Medical Image Anal..

[49]  Marc Niethammer,et al.  Quicksilver: Fast predictive image registration – A deep learning approach , 2017, NeuroImage.

[50]  R. Gur,et al.  Age-related volumetric changes of brain gray and white matter in healthy infants and children. , 2001, Cerebral cortex.

[51]  Snehashis Roy,et al.  Cross contrast multi‐channel image registration using image synthesis for MR brain images , 2017, Medical Image Anal..

[52]  Brian B. Avants,et al.  Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain , 2008, Medical Image Anal..

[53]  Dinggang Shen,et al.  Measuring the dynamic longitudinal cortex development in infants by reconstruction of temporally consistent cortical surfaces , 2014, NeuroImage.

[54]  Dinggang Shen,et al.  Improved image registration by sparse patch-based deformation estimation , 2015, NeuroImage.

[55]  Paul M. Thompson,et al.  Surface-Constrained Volumetric Brain Registration Using Harmonic Mappings , 2007, IEEE Transactions on Medical Imaging.