Infant Brain Development Prediction With Latent Partial Multi-View Representation Learning

The early postnatal period witnesses rapid and dynamic brain development. However, the relationship between brain anatomical structure and cognitive ability is still unknown. Currently, there is no explicit model to characterize this relationship in the literature. In this paper, we explore this relationship by investigating the mapping between morphological features of the cerebral cortex and cognitive scores. To this end, we introduce a multi-view multi-task learning approach to intuitively explore complementary information from different time-points and handle the missing data issue in longitudinal studies simultaneously. Accordingly, we establish a novel model, latent partial multi-view representation learning. Our approach regards data from different time-points as different views and constructs a latent representation to capture the complementary information from incomplete time-points. The latent representation explores the complementarity across different time-points and improves the accuracy of prediction. The minimization problem is solved by the alternating direction method of multipliers. Experimental results on both synthetic and real data validate the effectiveness of our proposed algorithm.

[1]  Zhixun Su,et al.  Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation , 2011, NIPS.

[2]  Zhi-Hua Zhou,et al.  Analyzing Co-training Style Algorithms , 2007, ECML.

[3]  George Lee,et al.  Supervised multi-view canonical correlation analysis: fused multimodal prediction of disease diagnosis and prognosis , 2014, Medical Imaging.

[4]  Meng Wang,et al.  Optimizing multi-graph learning: towards a unified video annotation scheme , 2007, ACM Multimedia.

[5]  Yaozong Gao,et al.  Can we predict subject‐specific dynamic cortical thickness maps during infancy from birth? , 2017, Human brain mapping.

[6]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[7]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2009, Found. Comput. Math..

[8]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[9]  Dinggang Shen,et al.  Constructing 4D Infant Cortical Surface Atlases Based on Dynamic Developmental Trajectories of the Cortex , 2014, MICCAI.

[10]  Sham M. Kakade,et al.  Multi-view Regression Via Canonical Correlation Analysis , 2007, COLT.

[11]  Yong Yu,et al.  Robust Recovery of Subspace Structures by Low-Rank Representation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  S. Bradley-Johnson.  Mullen Scales of Early Learning , 1997 .

[13]  Jiayu Zhou,et al.  Integrating low-rank and group-sparse structures for robust multi-task learning , 2011, KDD.

[14]  Kim-Han Thung,et al.  Robust Feature-Sample Linear Discriminant Analysis for Brain Disorders Diagnosis , 2015, NIPS.

[15]  Sham M. Kakade,et al.  Multi-view clustering via canonical correlation analysis , 2009, ICML '09.

[16]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[17]  Daniel Rueckert,et al.  Random forest-based similarity measures for multi-modal classification of Alzheimer's disease , 2013, NeuroImage.

[18]  Dinggang Shen,et al.  Predicting infant cortical surface development using a 4D varifold-based learning framework and local topography-based shape morphing , 2016, Medical Image Anal..

[19]  Cheng Soon Ong,et al.  Multiclass multiple kernel learning , 2007, ICML '07.

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

[21]  Dennis Velakoulis,et al.  Variability of the paracingulate sulcus and morphometry of the medial frontal cortex: Associations with cortical thickness, surface area, volume, and sulcal depth , 2008, Human brain mapping.

[22]  P. Jusczyk,et al.  A precursor of language acquisition in young infants , 1988, Cognition.

[23]  Timothy S. Coalson,et al.  A Surface-Based Analysis of Hemispheric Asymmetries and Folding of Cerebral Cortex in Term-Born Human Infants , 2010, The Journal of Neuroscience.

[24]  Dinggang Shen,et al.  Cortical thickness and surface area in neonates at high risk for schizophrenia , 2014, Brain Structure and Function.

[25]  Sidong Liu,et al.  Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease , 2015, IEEE Transactions on Biomedical Engineering.

[26]  Massimiliano Pontil,et al.  Multi-Task Feature Learning , 2006, NIPS.

[27]  Jieping Ye,et al.  An accelerated gradient method for trace norm minimization , 2009, ICML '09.

[28]  Jianjiang Feng,et al.  Smooth Representation Clustering , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Tong Zhang,et al.  A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , 2005, J. Mach. Learn. Res..

[30]  Dinggang Shen,et al.  Joint prediction of longitudinal development of cortical surfaces and white matter fibers from neonatal MRI , 2017, NeuroImage.

[31]  Natacha Akshoomoff,et al.  Use of the Mullen Scales of Early Learning for the Assessment of Young Children with Autism Spectrum Disorders , 2006, Child neuropsychology : a journal on normal and abnormal development in childhood and adolescence.

[32]  Gang Li,et al.  Learning‐based subject‐specific estimation of dynamic maps of cortical morphology at missing time points in longitudinal infant studies , 2016, Human brain mapping.

[33]  David W. Jacobs,et al.  Generalized Multiview Analysis: A discriminative latent space , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

[35]  Paul M. Thompson,et al.  Multi-source feature learning for joint analysis of incomplete multiple heterogeneous neuroimaging data , 2012, NeuroImage.

[36]  Anders M. Dale,et al.  An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest , 2006, NeuroImage.

[37]  Richard H. Bartels,et al.  Algorithm 432 [C2]: Solution of the matrix equation AX + XB = C [F4] , 1972, Commun. ACM.

[38]  I. Melle,et al.  Cortical Volume, Surface Area, and Thickness in Schizophrenia and Bipolar Disorder , 2012, Biological Psychiatry.

[39]  Feiping Nie,et al.  A Closed Form Solution to Multi-View Low-Rank Regression , 2015, AAAI.

[40]  Dinggang Shen,et al.  Multi-task prediction of infant cognitive scores from longitudinal incomplete neuroimaging data , 2019, NeuroImage.

[41]  Jieping Ye,et al.  Multi-Task Feature Learning Via Efficient l2, 1-Norm Minimization , 2009, UAI.

[42]  Tom Heskes,et al.  Task Clustering and Gating for Bayesian Multitask Learning , 2003, J. Mach. Learn. Res..

[43]  Abraham Z. Snyder,et al.  Prediction of brain maturity in infants using machine-learning algorithms , 2016, NeuroImage.

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

[45]  Dinggang Shen,et al.  Environmental Influences on Infant Cortical Thickness and Surface Area , 2019, Cerebral cortex.

[46]  Paul Aljabar,et al.  Longitudinal Regional Brain Development and Clinical Risk Factors in Extremely Preterm Infants. , 2016, The Journal of pediatrics.

[47]  B. Mercier,et al.  A dual algorithm for the solution of nonlinear variational problems via finite element approximation , 1976 .

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

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