Topology-Based Kernels With Application to Inference Problems in Alzheimer's Disease

Alzheimer's disease (AD) research has recently witnessed a great deal of activity focused on developing new statistical learning tools for automated inference using imaging data. The workhorse for many of these techniques is the support vector machine (SVM) framework (or more generally kernel-based methods). Most of these require, as a first step, specification of a kernel matrix K between input examples (i.e., images). The inner product between images Ii and Ij in a feature space can generally be written in closed form and so it is convenient to treat K as “given.” However, in certain neuroimaging applications such an assumption becomes problematic. As an example, it is rather challenging to provide a scalar measure of similarity between two instances of highly attributed data such as cortical thickness measures on cortical surfaces. Note that cortical thickness is known to be discriminative for neurological disorders, so leveraging such information in an inference framework, especially within a multi-modal method, is potentially advantageous. But despite being clinically meaningful, relatively few works have successfully exploited this measure for classification or regression. Motivated by these applications, our paper presents novel techniques to compute similarity matrices for such topologically-based attributed data. Our ideas leverage recent developments to characterize signals (e.g., cortical thickness) motivated by the persistence of their topological features, leading to a scheme for simple constructions of kernel matrices. As a proof of principle, on a dataset of 356 subjects from the Alzheimer's Disease Neuroimaging Initiative study, we report good performance on several statistical inference tasks without any feature selection, dimensionality reduction, or parameter tuning.

[1]  Karl J. Friston,et al.  Voxel-Based Morphometry—The Methods , 2000, NeuroImage.

[2]  A. McKinney,et al.  Automated MRI measures identify individuals with mild cognitive impairment and Alzheimer's disease , 2010 .

[3]  Dinggang Shen,et al.  Classification of Structural Images via High-Dimensional Image Warping, Robust Feature Extraction, and SVM , 2005, MICCAI.

[4]  Moo K. Chung,et al.  Weighted Fourier Series Representation and Its Application to Quantifying the Amount of Gray Matter , 2007, IEEE Transactions on Medical Imaging.

[5]  P. Thompson,et al.  Computational anatomical methods as applied to ageing and dementia. , 2007, The British journal of radiology.

[6]  H. Edelsbrunner,et al.  Persistent Homology — a Survey , 2022 .

[7]  David Cohen-Steiner,et al.  Stability of Persistence Diagrams , 2005, Discret. Comput. Geom..

[8]  Daoqiang Zhang,et al.  Multimodal classification of Alzheimer's disease and mild cognitive impairment , 2011, NeuroImage.

[9]  C. Jack,et al.  Hypothetical model of dynamic biomarkers of the Alzheimer's pathological cascade , 2010, The Lancet Neurology.

[10]  Sterling C. Johnson,et al.  The Influence of Alzheimer Disease Family History and Apolipoprotein E ε4 on Mesial Temporal Lobe Activation , 2006, The Journal of Neuroscience.

[11]  Moo K. Chung Heat kernel smoothing on unit sphere , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[12]  N. Schuff,et al.  Different regional patterns of cortical thinning in Alzheimer's disease and frontotemporal dementia. , 2006, Brain : a journal of neurology.

[13]  K. Ishii,et al.  Voxel-based morphometric comparison between early- and late-onset mild Alzheimer's disease and assessment of diagnostic performance of z score images. , 2005, AJNR. American journal of neuroradiology.

[14]  Gunnar Rätsch,et al.  Large Scale Multiple Kernel Learning , 2006, J. Mach. Learn. Res..

[15]  Z. Khachaturian Alzheimer's & Dementia: The Journal of the Alzheimer's Association , 2008, Alzheimer's & Dementia.

[16]  Afra J. Zomorodian,et al.  Topology for Computing (Cambridge Monographs on Applied and Computational Mathematics) , 2005 .

[17]  F. Shi,et al.  Hippocampal Shape Analysis of Alzheimer Disease Based on Machine Learning Methods , 2007, American Journal of Neuroradiology.

[18]  X. Wu,et al.  Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI , 2008, NeuroImage.

[19]  Herbert Edelsbrunner,et al.  Topological persistence and simplification , 2000, Proceedings 41st Annual Symposium on Foundations of Computer Science.

[20]  S. Resnick,et al.  Detection of prodromal Alzheimer's disease via pattern classification of magnetic resonance imaging , 2008, Neurobiology of Aging.

[21]  B. Hermann,et al.  Middle-Aged Children of Persons With Alzheimer’s Disease: APOE Genotypes and Cognitive Function in the Wisconsin Registry for Alzheimer’s Prevention , 2005, Journal of geriatric psychiatry and neurology.

[22]  R. Woods,et al.  Cortical change in Alzheimer's disease detected with a disease-specific population-based brain atlas. , 2001, Cerebral cortex.

[23]  Herbert Edelsbrunner,et al.  Algorithms in Combinatorial Geometry , 1987, EATCS Monographs in Theoretical Computer Science.

[24]  S. Thibodeau,et al.  Preclinical evidence of Alzheimer's disease in persons homozygous for the epsilon 4 allele for apolipoprotein E. , 1996, The New England journal of medicine.

[25]  Fillia Makedon,et al.  A surface-based approach for classification of 3D neuroanatomic structures , 2004, Intell. Data Anal..

[26]  Moo K. Chung,et al.  Spatially augmented LPboosting for AD classification with evaluations on the ADNI dataset , 2009, NeuroImage.

[27]  Alan C. Evans,et al.  Focal decline of cortical thickness in Alzheimer's disease identified by computational neuroanatomy. , 2004, Cerebral cortex.

[28]  Fillia Makedon,et al.  Hippocampal shape analysis: surface-based representation and classification , 2003, SPIE Medical Imaging.

[29]  Alan C. Evans,et al.  Small-world anatomical networks in the human brain revealed by cortical thickness from MRI. , 2007, Cerebral cortex.

[30]  A M Dale,et al.  Measuring the thickness of the human cerebral cortex from magnetic resonance images. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[31]  Alan C. Evans,et al.  Structural Insights into Aberrant Topological Patterns of Large-Scale Cortical Networks in Alzheimer's Disease , 2008, The Journal of Neuroscience.

[32]  J. Baron,et al.  In Vivo Mapping of Gray Matter Loss with Voxel-Based Morphometry in Mild Alzheimer's Disease , 2001, NeuroImage.

[33]  Lubomir M. Hadjiiski,et al.  Feature selection and classifier performance in computer-aided diagnosis: the effect of finite sample size. , 2000, Medical physics.

[34]  Vin de Silva,et al.  HOMOLOGICAL SENSOR NETWORKS , 2005 .

[35]  C. Jack,et al.  Alzheimer's Disease Neuroimaging Initiative , 2008 .

[36]  Vikas Singh,et al.  Predictive markers for AD in a multi-modality framework: An analysis of MCI progression in the ADNI population , 2011, NeuroImage.

[37]  Mark de Berg,et al.  Computational geometry: algorithms and applications , 1997 .

[38]  Aaron F. Bobick,et al.  Multiscale 3-D Shape Representation and Segmentation Using Spherical Wavelets , 2007, IEEE Transactions on Medical Imaging.

[39]  Christian Gaser,et al.  Identifying patients with obsessive–compulsive disorder using whole-brain anatomy , 2007, NeuroImage.

[40]  Sun I. Kim,et al.  Pattern classification using principal components of cortical thickness and its discriminative pattern in schizophrenia , 2007, NeuroImage.

[41]  Nick C Fox,et al.  Automatic classification of MR scans in Alzheimer's disease. , 2008, Brain : a journal of neurology.

[42]  Nikolaus Weiskopf,et al.  A comparison between voxel-based cortical thickness and voxel-based morphometry in normal aging , 2009, NeuroImage.

[43]  Clifford R. Jack,et al.  Alzheimer's disease diagnosis in individual subjects using structural MR images: Validation studies , 2008, NeuroImage.

[44]  Mayo Clinic,et al.  PRECLINICAL EVIDENCE OF ALZHEIMER’S DISEASE IN PERSONS HOMOZYGOUS FOR THE , 2000 .

[45]  et al.,et al.  Spatial patterns of brain atrophy in MCI patients, identified via high-dimensional pattern classification, predict subsequent cognitive decline , 2008, NeuroImage.

[46]  J. Pariente,et al.  Early diagnosis of Alzheimer's disease using cortical thickness: impact of cognitive reserve , 2009, Brain : a journal of neurology.

[47]  Afra J. Zomorodian Topology for Computing: Applications , 2005 .