Chris Hinrichs

Predictive Markers for AD in a Multi-Modality Framework: An Analysis of MCI Progression in the ADNI Population

Alzheimers Disease (AD) and other neurodegenerative diseases affect over 20 million people worldwide, and this number is projected to significantly increase in the coming decades. Proposed imaging-based markers have shown steadily improving levels of sensitivity/specificity in classifying individual subjects as AD or normal. Several of these efforts have utilized statistical machine learning techniques, using brain images as input, as means of deriving such AD-related markers. A common characteristic of this line of research is a focus on either (1) using a single imaging modality for classification, or (2) incorporating several modalities, but reporting separate results for each. One strategy to improve on the success of these methods is to leverage all available imaging modalities together in a single automated learning framework. The rationale is that some subjects may show signs of pathology in one modality but not in another-by combining all available images a clearer view of the progression of disease pathology will emerge. Our method is based on the Multi-Kernel Learning (MKL) framework, which allows the inclusion of an arbitrary number of views of the data in a maximum margin, kernel learning framework. The principal innovation behind MKL is that it learns an optimal combination of kernel (similarity) matrices while simultaneously training a classifier. In classification experiments MKL outperformed an SVM trained on all available features by 3%-4%. We are especially interested in whether such markers are capable of identifying early signs of the disease. To address this question, we have examined whether our multi-modal disease marker (MMDM) can predict conversion from Mild Cognitive Impairment (MCI) to AD. Our experiments reveal that this measure shows significant group differences between MCI subjects who progressed to AD, and those who remained stable for 3 years. These differences were most significant in MMDMs based on imaging data. We also discuss the relationship between our MMDM and an individuals conversion from MCI to AD.

MKL for Robust Multi-modality AD Classification

We study the problem of classifying mild Alzheimers disease (AD) subjects from healthy individuals (controls) using multi-modal image data, to facilitate early identification of AD related pathologies. Several recent papers have demonstrated that such classification is possible with MR or PET images, using machine learning methods such as SVM and boosting. These algorithms learn the classifier using one type of image data. However, AD is not well characterized by one imaging modality alone, and analysis is typically performed using several image types--each measuring a different type of structural/functional characteristic. This paper explores the AD classification problem using multiple modalities simultaneously. The difficulty here is to assess the relevance of each modality (which cannot be assumed a priori), as well as to optimize the classifier. To tackle this problem, we utilize and adapt a recently developed idea called Multi-Kernel learning (MKL). Briefly, each imaging modality spawns one (or more kernels) and we simultaneously solve for the kernel weights and a maximum margin classifier. To make the model robust, we propose strategies to suppress the influence of a small subset of outliers on the classifier--this yields an alternative minimization based algorithm for robust MKL. We present promising multi-modal classification experiments on a large dataset of images from the ADNI project.

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

Alzheimers 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 Alzheimers Disease Neuroimaging Initiative study, we report good performance on several statistical inference tasks without any feature selection, dimensionality reduction, or parameter tuning.

Extracting and summarizing white matter hyperintensities using supervised segmentation methods in Alzheimer’s disease risk and aging studies

Precise detection and quantification of white matter hyperintensities (WMH) observed in T2‐weighted Fluid Attenuated Inversion Recovery (FLAIR) Magnetic Resonance Images (MRI) is of substantial interest in aging, and age‐related neurological disorders such as Alzheimers disease (AD). This is mainly because WMH may reflect co‐morbid neural injury or cerebral vascular disease burden. WMH in the older population may be small, diffuse, and irregular in shape, and sufficiently heterogeneous within and across subjects. Here, we pose hyperintensity detection as a supervised inference problem and adapt two learning models, specifically, Support Vector Machines and Random Forests, for this task. Using texture features engineered by texton filter banks, we provide a suite of effective segmentation methods for this problem. Through extensive evaluations on healthy middle‐aged and older adults who vary in AD risk, we show that our methods are reliable and robust in segmenting hyperintense regions. A measure of hyperintensity accumulation, referred to as normalized effective WMH volume, is shown to be associated with dementia in older adults and parental family history in cognitively normal subjects. We provide an open source library for hyperintensity detection and accumulation (interfaced with existing neuroimaging tools), that can be adapted for segmentation problems in other neuroimaging studies. Hum Brain Mapp 35:4219–4235, 2014.

MKL-based sample enrichment and customized outcomes enable smaller AD clinical trials

Recently, the field of neuroimaging analysis has seen a large number of studies which use machine learning methods to make predictions about the progression of Alzheimers Disease (AD) in mildly demented subjects. Among these, Multi-Kernel Learning (MKL) has emerged as a powerful tool for systematically aggregating diverse data views, and several groups have shown that MKL is uniquely suited to combining different imaging modalities into a single learned model. The next phase of this research is to employ these predictive abilities to design more efficient clinical trials. Two issues can hamper a trials effectiveness: the presence of non-pathological subjects in a study, and the sensitivity of the chosen outcome measure to the pathology of interest. We offer two approaches for dealing with these issues: trial enrichment, in which MKL-derived predictions are used to screen out subjects unlikely to benefit from a treatment; and custom outcome measures which use an SVM to select a weighted voxel average for use as an outcome measure. We provide preliminary evidence that these two strategies can lead to significant reductions in sample sizes in hypothetical trials, which directly gives reduced costs and higher efficiency in the drug development cycle.

Learning kernels for variants of normalized cuts: Convex relaxations and applications

We propose a new algorithm for learning kernels for variants of the Normalized Cuts (NCuts) objective – i.e., given a set of training examples with known partitions, how should a basis set of similarity functions be combined to induce NCuts favorable distributions. Such a procedure facilitates design of good affinity matrices. It also helps assess the importance of different feature types for discrimination. Rather than formulating the learning problem in terms of the spectral relaxation, the alternative we pursue here is to work in the original discrete setting (i.e., the relaxation occurs much later). We show that this strategy is useful – while the initial specification seems rather difficult to optimize efficiently, a set of manipulations reveal a related model which permits a nice SDP relaxation. A salient feature of our model is that the eventual problem size is only a function of the number of input kernels and not the training set size. This relaxation also allows strong optimality guarantees, if certain conditions are satisfied. We show that the sub-kernel weights obtained provide a complementary approach for MKL based methods. Our experiments on Cal-tech101 and ADNI (a brain imaging dataset) show that the quality of solutions is competitive with the state-of-the-art.

Accelerating permutation testing in voxel-wise analysis through subspace tracking: A new plugin for SnPM

Abstract Permutation testing is a non‐parametric method for obtaining the max null distribution used to compute corrected p‐values that provide strong control of false positives. In neuroimaging, however, the computational burden of running such an algorithm can be significant. We find that by viewing the permutation testing procedure as the construction of a very large permutation testing matrix, Symbol, one can exploit structural properties derived from the data and the test statistics to reduce the runtime under certain conditions. In particular, we see that Symbol is low‐rank plus a low‐variance residual. This makes Symbol a good candidate for low‐rank matrix completion, where only a very small number of entries of Symbol (Symbol of all entries in our experiments) have to be computed to obtain a good estimate. Based on this observation, we present RapidPT, an algorithm that efficiently recovers the max null distribution commonly obtained through regular permutation testing in voxel‐wise analysis. We present an extensive validation on a synthetic dataset and four varying sized datasets against two baselines: Statistical NonParametric Mapping (SnPM13) and a standard permutation testing implementation (referred as NaivePT). We find that RapidPT achieves its best runtime performance on medium sized datasets (Symbol), with speedups of 1.5× ‐ 38× (vs. SnPM13) and 20x‐1000× (vs. NaivePT). For larger datasets (Symbol) RapidPT outperforms NaivePT (6× ‐ 200×) on all datasets, and provides large speedups over SnPM13 when more than 10000 permutations (2× ‐ 15×) are needed. The implementation is a standalone toolbox and also integrated within SnPM13, able to leverage multi‐core architectures when available. Symbol. No caption available. Symbol. No caption available. Symbol. No caption available. Symbol. No caption available. HighlightsA fast and robust permutation testing approach for multiple hypothesis testing is proposed.Our permutation testing approach is ˜20× faster then current methods.The proposed model is in the developing (soon to be released) version of SnPM.

Extracting white matter hyperintensities in Alzheimer's disease risk and aging studies using supervised segmentation methods

memory complaints, MMSE 26 and CDR1⁄40), 100 MCI (MMSE 24 and CDR1⁄40.5, memory impairment based on Rey Auditory Verbal Learning Test and that did not meet DSM IV criteria for AD dementia) and 198 AD (12 MMSE 26 and CDR 0.5 and meeting DSM IV criteria). Subjects with other types of dementia and/or non-AD grounds for cognitive issues were not offered to participate. Clinical data, neuropsychological tests and biomarkers (blood, urine and CSF whenever possible) will be collected at Baseline and every 6 months until Month 48. MRI scans (3DT1, 3DT2, FLAIR, SWI, DWI and DTI) will be collected up to 3 times between Baseline and Month 48, using a Philips Achieva 3T scanner, for consenting subjects (n1⁄4158). The volume of intracranial cavity (ICV), left and right hippocampi (HCV), lateral ventricles (LVV) and whole brain (WBV) were assessed at Baseline using an automated multi-atlas segmentation algorithm. Descriptive statistics of HCV, LVV and WBV were computed for each group after normalization by ICV. Difference between groups was assessed using an ANCOVA, with age and ICV as covariates, and by ROC analysis. Results: HCV, LVVand WBV results are listed in Table 1. Significant differences (p<0.05) were found between each group, except for LVV between MCI and AD (see Fig.1a-c). ROC analysis showed best group separation for HCV between NC and AD (AUC1⁄40.89, see Fig.1d). HCV was also the best endpoint to separate NC and MCI (AUC1⁄40.71), while WBV best separatedMCI and AD (AUC1⁄40.72).Conclusions:BaselineMRI endpoints showed significant differences between NC, MCI and AD. Disease progression will be monitored, among others, through conversion to dementia and evolution of volumetric MRI biomarkers. The study will provide valuable clinical, biological and MRI data on a large sample of elderly subjects. The monocentric aspect of the study will help decrease variability.