Roman Filipovych

Semi-supervised Pattern Classification of Medical Images: Application to Mild Cognitive Impairment (MCI)

Many progressive disorders are characterized by unclear or transient diagnoses for specific subgroups of patients. Commonly used supervised pattern recognition methodology may not be the most suitable approach to deriving image-based biomarkers in such cases, as it relies on the availability of categorically labeled data (e.g., patients and controls). In this paper, we explore the potential of semi-supervised pattern classification to provide image-based biomarkers in the absence of precise diagnostic information for some individuals. We employ semi-supervised support vector machines (SVM) and apply them to the problem of classifying MR brain images of patients with uncertain diagnoses. We examine patterns in serial scans of ADNI participants with mild cognitive impairment (MCI), and propose that in the absence of sufficient follow-up evaluations of individuals with MCI, semi-supervised strategy is potentially more appropriate than the fully-supervised paradigm employed up to date.

Sparse Dictionary Learning of Resting State fMRI Networks

Research in resting state fMRI (rsfMRI) has revealed the presence of stable, anti-correlated functional sub-networks in the brain. Task-positive networks are active during a cognitive process and are anti-correlated with task-negative networks, which are active during rest. In this paper, based on the assumption that the structure of the resting state functional brain connectivity is sparse, we utilize sparse dictionary modeling to identify distinct functional sub-networks. We propose two ways of formulating the sparse functional network learning problem that characterize the underlying functional connectivity from different perspectives. Our results show that the whole-brain functional connectivity can be concisely represented with highly modular, overlapping task-positive/negative pairs of sub-networks.

JointMMCC: Joint Maximum-Margin Classification and Clustering of Imaging Data

A number of conditions are characterized by pathologies that form continuous or nearly-continuous spectra spanning from the absence of pathology to very pronounced pathological changes (e.g., normal aging, mild cognitive impairment, Alzheimers). Moreover, diseases are often highly heterogeneous with a number of diagnostic subcategories or subconditions lying within the spectra (e.g., autism spectrum disorder, schizophrenia). Discovering coherent subpopulations of subjects within the spectrum of pathological changes may further our understanding of diseases, and potentially identify subconditions that require alternative or modified treatment options. In this paper, we propose an approach that aims at identifying coherent subpopulations with respect to the underlying MRI in the scenario where the condition is heterogeneous and pathological changes form a continuous spectrum. We describe a joint maximum-margin classification and clustering (JointMMCC) approach that jointly detects the pathologic population via semi-supervised classification, as well as disentangles heterogeneity of the pathological cohort by solving a clustering subproblem. We propose an efficient solution to the nonconvex optimization problem associated with JointMMCC. We apply our proposed approach to an medical resonance imaging study of aging, and identify coherent subpopulations (i.e., clusters) of cognitively less stable adults.

Multi-kernel classification for integration of clinical and imaging data: application to prediction of cognitive decline in older adults

Diagnosis of neurologic and neuropsychiatric disorders typically involves considerable assessment including clinical observation, neuroimaging, and biological and neuropsychological measurements. While it is reasonable to expect that the integration of neuroimaging data and complementary non-imaging measures is likely to improve early diagnosis on individual basis, due to technical challenges associated with the task of combining different data types, medical image pattern recognition analysis has been largely focusing solely on neuroimaging evaluations. In this paper, we explore the potential of integrating neuroimaging and clinical information within a pattern classification framework, and propose that the multi-kernel learning (MKL) paradigm may be suitable for building a multimodal classifier of a disorder, as well as for automatic identification of the relevance of each information type. We apply our approach to the problem of detecting cognitive decline in healthy older adults from single-visit evaluations, and show that the performance of a classifier can be improved when nouroimaging and clinical evaluations are used simultaneously within a MKL-based classification framework.

A Composite Multivariate Polygenic and Neuroimaging Score for Prediction of Conversion to Alzheimer's Disease

Alzheimers disease (AD) and Mild Cognitive Impairment (MCI) are characterized by widespread pathological changes in the brain. At the same time, Alzheimers disease is heritable with complex genetic underpinnings that may influence the timing of the related pathological changes in the brain and can affect the progression from MCI to AD. In this paper, we present a multivariate imaging genetics approach for prediction of conversion to Alzheimers disease in patients with mild cognitive impairment. We employ multivariate pattern recognition approaches to obtain neuroimaging and polygenic discriminators between the healthy individuals and AD patients. We then design, in a linear manner, a composite imaging-genetic score for prediction of conversion to Alzheimers disease in patients with mild cognitive impairment. We apply our approach within the Alzheimers Disease Neuroimaging Initiative and show that the integration of polygenic and neuroimaging information improves prediction of conversion to AD.

Pattern analysis in neuroimaging: Beyond two-class categorization

One of the many advantages of multivariate pattern recognition approaches over conventional mass‐univariate group analysis using voxel‐wise statistical tests is their potential to provide highly sensitive and specific markers of diseases on an individual basis. However, a vast majority of imaging problems addressed by pattern recognition are viewed from the perspective of a two‐class classification. In this article, we provide a summary of selected works that propose solutions to biomedical problems where the widely‐accepted classification paradigm is not appropriate. These pattern recognition approaches address common challenges in many imaging studies: high heterogeneity of populations and continuous progression of diseases. We focus on diseases associated with aging and propose that clustering‐based approaches may be more suitable for disentanglement of the underlying heterogeneity, while high‐dimensional pattern regression methodology is appropriate for prediction of continuous and gradual clinical progression from magnetic resonance brain images.

Understanding heterogeneity in normal older adult populations via clustering of longitudinal data

Populations of healthy older individuals are often highly heterogeneous, as prevalence of various underlying pathologies increases with age. Finding coherent groups of normal older adults may allow to identify subpopulations that are at risk of developing Alzheimers disease (AD). In this paper, we propose an approach that utilizes longitudinal magnetic resonance imaging (MRI) data to obtain natural groupings of older adult subjects via an unsupervised (i.e., clustering) technique. We develop a k-medoids-like clustering algorithm that simultaneously finds clusters of longitudinal images, as well as weights brain regions in such a way that the obtained clusters are maximally coherent. We propose a cluster-based measure that reflects the individual subjects cognitive decline. The proposed method is unsupervised and is suitable for analyzing AD at its very early stages.

Identifying Multivariate Imaging Patterns: Supervised, Semi-Supervised, and Unsupervised Learning Perspectives

Abstract One of the limitations of conventional mass-univariate group analyzes using voxel-wise statistical tests is their inability to provide sensitive and specific markers of diseases on an individual basis, and thus to serve as diagnostic and prognostic tools. Recent advances in machine learning methods and their applications to neuroimaging studies have shown that multivariate imaging patterns have the potential to identify and predict diagnoses based on the imaging information at an individual subject level. At the same time, different clinical questions warrant the use of specific computational tools whose applicability depends on a number of factors, not the least of which is the availability of reliable diagnostic information that is used to design the predictive models. In this chapter, we provide a summary of selected works that address the task of identifying descriptive imaging patterns from different learning perspectives, including supervised, semi-supervised, and unsupervised learning paradigms. We pay special attention to analyzing diseases and conditions characterized by high heterogeneity and continuous progression. The application focus of this chapter is on designing neuroimaging descriptors of aging, Alzheimer’s disease, mild cognitive impairment, and schizophrenia.

Three-year conversion of MCI to Alzheimer’s disease and cognitive decline can be predicted from polygenetic and imaging profiles

or not the spatial amyloid pattern predicted cognitive decline. Results: The difference map of an individual’s spatial pattern of amyloid deposition from the normative model of amyloid deposition was predictive of cognitive decline, and when prediction is restricted to PiB-positive participants (cDVR > 1.2) (Sojkova 2011b), the accuracy increases further. The average difference map for stable and declining groups indicates that the declining group may have increased amyloid deposition in the lateral temporal and precuneus areas (Figure 1). Conclusions: By estimating the difference between an individual’s amyloid pattern and a normative model, it may be possible to predict whether the individual is cognitively declining. Regions in which the most pronounced deviations were observed included the lateral temporal lobe and precuneus areas. Table 3 Classification results for AD versus control andMCI-C versusMCI-NC. For MCI subjects, predictions were performed using a model built with AD/ IC-P-010 THREE-YEAR CONVERSION OF MCI TO