High dimensional classification of structural MRI Alzheimer's disease data based on large scale regularization

Associations of plasma proteomics and age-related outcomes with brain age in a diverse cohort

Machine learning models are increasingly being used to estimate "brain age" from neuroimaging data. The gap between chronological age and the estimated brain age gap (BAG) is potentially a measure of accelerated and resilient brain aging. Brain age calculated in this fashion has been shown to be associated with mortality, measures of physical function, health, and disease. Here, we estimate the BAG using a voxel-based elastic net regression approach, and then, we investigate its associations with mortality, cognitive status, and measures of health and disease in participants from Atherosclerosis Risk in Communities (ARIC) study who had a brain MRI at visit 5 of the study. Finally, we used the SOMAscan assay containing 4877 proteins to examine the proteomic associations with the MRI-defined BAG. Among N = 1849 participants (age, 76.4 (SD 5.6)), we found that increased values of BAG were strongly associated with increased mortality and increased severity of the cognitive status. Strong associations with mortality persisted when the analyses were performed in cognitively normal participants. In addition, it was strongly associated with BMI, diabetes, measures of physical function, hypertension, prevalent heart disease, and stroke. Finally, we found 33 proteins associated with BAG after a correction for multiple comparisons. The top proteins with positive associations to brain age were growth/differentiation factor 15 (GDF-15), Sushi, von Willebrand factor type A, EGF, and pentraxin domain-containing protein 1 (SEVP 1), matrilysin (MMP7), ADAMTS-like protein 2 (ADAMTS), and heat shock 70 kDa protein 1B (HSPA1B) while EGF-receptor (EGFR), mast/stem-cell-growth-factor-receptor (KIT), coagulation-factor-VII, and cGMP-dependent-protein-kinase-1 (PRKG1) were negatively associated to brain age. Several of these proteins were previously associated with dementia in ARIC. These results suggest that circulating proteins implicated in biological aging, cellular senescence, angiogenesis, and coagulation are associated with a neuroimaging measure of brain aging.

Hierarchical Neighbors Embedding

Manifold learning now plays an important role in machine learning and many relevant applications. In spite of the superior performance of manifold learning techniques in dealing with nonlinear data distribution, their performance would drop when facing the problem of data sparsity. It is hard to obtain satisfactory embeddings when sparsely sampled high-dimensional data are mapped into the observation space. To address this issue, in this article, we propose hierarchical neighbors embedding (HNE), which enhances the local connections through hierarchical combination of neighbors. And three different HNE-based implementations are derived by further analyzing the topological connection and reconstruction performance. The experimental results on both the synthetic and real-world datasets illustrate that our HNE-based methods could obtain more faithful embeddings with better topological and geometrical properties. From the view of embedding quality, HNE develops the outstanding advantages in dealing with data of general distributions. Furthermore, comparing with other state-of-the-art manifold learning methods, HNE shows its superiority in dealing with sparsely sampled data and weak-connected manifolds.

Integration of graph network with kernel SVM and logistic regression for identification of biomarkers in SCA12 and its diagnosis

Spinocerebellar ataxia type 12 is a hereditary and neurodegenerative illness commonly found in India. However, there is no established noninvasive automatic diagnostic system for its diagnosis and identification of imaging biomarkers. This work proposes a novel four-phase machine learning-based diagnostic framework to find spinocerebellar ataxia type 12 disease-specific atrophic-brain regions and distinguish spinocerebellar ataxia type 12 from healthy using a real structural magnetic resonance imaging dataset. Firstly, each brain region is represented in terms of statistics of coefficients obtained using 3D-discrete wavelet transform. Secondly, a set of relevant regions are selected using a graph network-based method. Thirdly, a kernel support vector machine is used to capture nonlinear relationships among the voxels of a brain region. Finally, the linear relationship among the brain regions is captured to build a decision model to distinguish spinocerebellar ataxia type 12 from healthy by using the regularized logistic regression method. A classification accuracy of 95% and a harmonic mean of precision and recall, i.e. F1-score of 94.92%, is achieved. The proposed framework provides relevant regions responsible for the atrophy. The importance of each region is captured using Shapley Additive exPlanations values. We also performed a statistical analysis to find volumetric changes in spinocerebellar ataxia type 12 group compared to healthy. The promising result of the proposed framework shows that clinicians can use it for early and timely diagnosis of spinocerebellar ataxia type 12.

Voxel Extraction and Multiclass Classification of Identified Brain Regions across Various Stages of Alzheimer's Disease Using Machine Learning Approaches

This study sought to investigate how different brain regions are affected by Alzheimer's disease (AD) at various phases of the disease, using independent component analysis (ICA). The study examines six regions in the mild cognitive impairment (MCI) stage, four in the early stage of Alzheimer's disease (AD), six in the moderate stage, and six in the severe stage. The precuneus, cuneus, middle frontal gyri, calcarine cortex, superior medial frontal gyri, and superior frontal gyri were the areas impacted at all phases. A general linear model (GLM) is used to extract the voxels of the previously mentioned regions. The resting fMRI data for 18 AD patients who had advanced from MCI to stage 3 of the disease were obtained from the ADNI public source database. The subjects include eight women and ten men. The voxel dataset is used to train and test ten machine learning algorithms to categorize the MCI, mild, moderate, and severe stages of Alzheimer's disease. The accuracy, recall, precision, and F1 score were used as conventional scoring measures to evaluate the classification outcomes. AdaBoost fared better than the other algorithms and obtained a phenomenal accuracy of 98.61%, precision of 99.00%, and recall and F1 scores of 98.00% each.

Determination of affected brain regions at various stages of Alzheimer's disease

The objective of study was to explore those brain areas that were affected at each stage during the progression of Alzheimer's disease (AD). Six affected brain areas were explored at mild cognitive impairment, four at first stage and six at each of second and third stage of Alzheimer's disease. The common brain regions among these stages were cuneus, precuneus, calcarine cortex, middle frontal gyrus, superior frontal gyrus, and frontal superior medial gyrus. The fMRI data at the resting state of 18 AD patients who were converted from MCI to stage 3 of Alzheimer's were taken from ADNI public source database. Among these patients, there were ten males and eight females. Independent component analysis was used to explore affected brain regions and an algorithm based on deep learning convolutional neural network was proposed for binary classification among the stages of Alzheimer's disease. The proposed CNN model delivered 94.6 % accuracy for separating stage 1 of Alzheimer's disease from mild cognitive impairment. 96.7 % accuracy was acquired to distinguish stage 2 of Alzheimer's disease from mild cognitive impairment, and stage 3 of Alzheimer's disease was separated from mild cognitive impairment with an accuracy of 97.8 %.

Ensemble Model for Diagnostic Classification of Alzheimer's Disease Based on Brain Anatomical Magnetic Resonance Imaging

Alzheimer's is one of the fast-growing diseases among people worldwide leading to brain atrophy. Neuroimaging reveals extensive information about the brain's anatomy and enables the identification of diagnostic features. Artificial intelligence (AI) in neuroimaging has the potential to significantly enhance the treatment process for Alzheimer's disease (AD). The objective of this study is two-fold: (1) to compare existing Machine Learning (ML) algorithms for the classification of AD. (2) To propose an effective ensemble-based model for the same and to perform its comparative analysis. In this study, data from the Alzheimer's Diseases Neuroimaging Initiative (ADNI), an online repository, is utilized for experimentation consisting of 2125 neuroimages of Alzheimer's disease (n = 975), mild cognitive impairment (n = 538) and cognitive normal (n = 612). For classification, the framework incorporates a Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), and K-Nearest Neighbor (K-NN) followed by some variations of Support Vector Machine (SVM), such as SVM (RBF kernel), SVM (Polynomial Kernel), and SVM (Sigmoid kernel), as well as Gradient Boost (GB), Extreme Gradient Boosting (XGB) and Multi-layer Perceptron Neural Network (MLP-NN). Afterwards, an Ensemble Based Generic Kernel is presented where Master-Slave architecture is combined to attain better performance. The proposed model is an ensemble of Extreme Gradient Boosting, Decision Tree and SVM_Polynomial kernel (XGB + DT + SVM). At last, the proposed method is evaluated using cross-validation using statistical techniques along with other ML models. The presented ensemble model (XGB + DT + SVM) outperformed existing state-of-the-art algorithms with an accuracy of 89.77%. The efficiency of all the models was optimized using Grid-based tuning, and the results obtained after such process showed significant improvement. XGB + DT + SVM with optimized parameters outperformed all other models with an efficiency of 95.75%. The implication of the proposed ensemble-based learning approach clearly shows the best results compared to other ML models. This experimental comparative analysis improved understanding of the above-defined methods and enhanced their scope and significance in the early detection of Alzheimer's disease.

GA-MADRID: design and validation of a machine learning tool for the diagnosis of Alzheimer’s disease and frontotemporal dementia using genetic algorithms

Artificial Intelligence aids early diagnosis and development of new treatments, which is key to slow down the progress of the diseases, which to date have no cure. The patients’ evaluation is carried out through diagnostic techniques such as clinical assessments neuroimaging techniques, which provide high-dimensionality data. In this work, a computational tool is presented that deals with the data provided by the clinical diagnostic techniques. This is a Python-based framework implemented with a modular design and fully extendable. It integrates (i) data processing and management of missing values and outliers; (ii) implementation of an evolutionary feature engineering approach, developed as a Python package, called PyWinEA using Mono-objective and Multi-objetive Genetic Algorithms (NSGAII); (iii) a module for designing predictive models based on a wide range of machine learning algorithms; (iv) a multiclass decision stage based on evolutionary grammars and Bayesian networks. Developed under the eXplainable Artificial Intelligence and open science perspective, this framework provides promising advances and opens the door to the understanding of neurodegenerative diseases from a data-centric point of view. In this work, we have successfully evaluated the potential of the framework for early and automated diagnosis with neuroimages and neurocognitive assessments from patients with Alzheimer’s disease (AD) and frontotemporal dementia (FTD).

Graphical abstract

Structural Correlates of Overt Sentence Reading in Mild Cognitive Impairment and Mild-to-Moderate Alzheimer's Disease

BACKGROUND

Overt sentence reading in mild cognitive impairment (MCI) and mild-tomoderate Alzheimer's disease (AD) has been associated with slowness of speech, characterized by a higher number of pauses, shorter speech units and slower speech rate and attributed to reduced working memory/ attention and language capacity.

OBJECTIVE

This preliminary case-control study investigates whether the temporal organization of speech is associated with the volume of brain regions involved in overt sentence reading and explores the discriminative ability of temporal speech parameters and standard volumetric MRI measures for the classification of MCI and AD.

METHODS

Individuals with MCI, mild-to-moderate AD, and healthy controls (HC) had a structural MRI scan and read aloud sentences varying in cognitive-linguistic demand (length). The association between speech features and regional brain volumes was examined by linear mixed-effect modeling. Genetic programming was used to explore the discriminative ability of temporal and MRI features.

RESULTS

Longer sentences, slower speech rate, and a higher number of pauses and shorter interpausal units were associated with reduced volumes of the reading network. Speech-based classifiers performed similarly to the MRI-based classifiers for MCI-HC (67% vs. 68%) and slightly better for AD-HC (80% vs. 64%) and AD-MCI (82% vs. 59%). Adding the speech features to the MRI features slightly improved the performance of MRI-based classification for AD-HC and MCI-HC but not HC-MCI.

CONCLUSION

The temporal organization of speech in overt sentence reading reflects underlying volume reductions. It may represent a sensitive marker for early assessment of structural changes and cognitive- linguistic deficits associated with healthy aging, MCI, and AD.

Extracting ROI-Based Contourlet Subband Energy Feature From the sMRI Image for Alzheimer's Disease Classification

Structural magnetic resonance imaging (sMRI)-based Alzheimer's disease (AD) classification and its prodromal stage-mild cognitive impairment (MCI) classification have attracted many attentions and been widely investigated in recent years. Owing to the high dimensionality, representation of the sMRI image becomes a difficult issue in AD classification. Furthermore, regions of interest (ROI) reflected in the sMRI image are not characterized properly by spatial analysis techniques, which has been a main cause of weakening the discriminating ability of the extracted spatial feature. In this study, we propose a ROI-based contourlet subband energy (ROICSE) feature to represent the sMRI image in the frequency domain for AD classification. Specifically, a preprocessed sMRI image is first segmented into 90 ROIs by a constructed brain mask. Instead of extracting features from the 90 ROIs in the spatial domain, the contourlet transform is performed on each of these ROIs to obtain their energy subbands. And then for an ROI, a subband energy (SE) feature vector is constructed to capture its energy distribution and contour information. Afterwards, SE feature vectors of the 90 ROIs are concatenated to form a ROICSE feature of the sMRI image. Finally, support vector machine (SVM) classifier is used to classify 880 subjects from ADNI and OASIS databases. Experimental results show that the ROICSE approach outperforms six other state-of-the-art methods, demonstrating that energy and contour information of the ROI are important to capture differences between the sMRI images of AD and HC subjects. Meanwhile, brain regions related to AD can also be found using the ROICSE feature, indicating that the ROICSE feature can be a promising assistant imaging marker for the AD diagnosis via the sMRI image. Code and Sample IDs of this paper can be downloaded at https://github.com/NWPU-903PR/ROICSE.git.

Comparing data-driven and hypothesis-driven MRI-based predictors of cognitive impairment in individuals from the Atherosclerosis Risk in Communities (ARIC) study

INTRODUCTION

A data-driven index of dementia risk based on magnetic resonance imaging (MRI), the Alzheimer's Disease Pattern Similarity (AD-PS) score, was estimated for participants in the Atherosclerosis Risk in Communities (ARIC) study.

METHODS

AD-PS scores were generated for 839 cognitively non-impaired individuals with a mean follow-up of 4.86 years. The scores and a hypothesis-driven volumetric measure based on several brain regions susceptible to AD were compared as predictors of incident cognitive impairment in different settings.

RESULTS

Logistic regression analyses suggest the data-driven AD-PS scores to be more predictive of incident cognitive impairment than its counterpart. Both biomarkers were more predictive of incident cognitive impairment in participants who were White, female, and apolipoprotein E gene (APOE) ε4 carriers. Random forest analyses including predictors from different domains ranked the AD-PS scores as the most relevant MRI predictor of cognitive impairment.

CONCLUSIONS

Overall, the AD-PS scores were the stronger MRI-derived predictors of incident cognitive impairment in cognitively non-impaired individuals.

Advances in computerized MRI‐based biomarkers in Alzheimer’s disease

The use of neuroimaging examinations is crucial in Alzheimer’s disease (AD), in both research and clinical settings. Over the years, magnetic resonance imaging (MRI)–based computer‐aided diagnosis has been shown to be helpful for early screening and predicting cognitive decline. Meanwhile, an increasing number of studies have adopted machine learning for the classification of AD, with promising results. In this review article, we focus on computerized MRI‐based biomarkers of AD by reviewing representative studies that used computerized techniques to identify AD patients and predict cognitive progression. We categorized these studies based on the following applications: (1) identifying AD from normal control; (2) identifying AD from other dementia types, including vascular dementia, dementia with Lewy bodies, and frontotemporal dementia; and (3) predicting conversion from NC to mild cognitive impairment (MCI) and from MCI to AD. This systematic review could act as a state‐of‐the‐art overview of this emerging field as well as a basis for designing future studies.

Folded concave penalized learning of high-dimensional MRI data in Parkinson's disease

BACKGROUND

Brain MRI is a promising technique for Parkinson's disease (PD) biomarker development. Its analysis, however, is hindered by the high-dimensional nature of the data, particularly when the sample size is relatively small.

NEW METHOD

This study introduces a folded concave penalized machine learning scheme with spatial coupling fused penalty (fused FCP) to build biomarkers for PD directly from whole-brain voxel-wise MRI data. The penalized maximum likelihood estimation problem of the model is solved by local linear approximation.

RESULTS

The proposed approach is evaluated on synthetic and Parkinson's Progression Marker Initiative (PPMI) data. It achieves good AUC scores, accuracy in classification, and biomarker identification with a relatively small sample size, and the results are robust for different tuning parameter choices. On the PPMI data, the proposed method discovers over 80 % of large regions of interest (ROIs) identified by the voxel-wise method, as well as potential new ROIs.

COMPARISON WITH EXISTING METHODS

The fused FCP approach is compared with L1, fused-L1, and FCP method using three popular machine learning algorithms, logistic regression, support vector machine, and linear discriminant analysis, as well as the voxel-wise method, on both synthetic and PPMI datasets. The fused FCP method demonstrated better accuracy in separating PD from controls than L1 and fused-L1 methods, and similar performance when compared with FCP method. In addition, the fused FCP method showed better ROI identification.

CONCLUSIONS

The fused FCP method can be an effective approach for MRI biomarker discovery in PD and other studies using high dimensionality data/low sample sizes.

A critical review of the epidemiological evidence of effects of air pollution on dementia, cognitive function and cognitive decline in adult population

Dementia is arguably the most pressing public health challenge of our age. Since dementia does not have a cure, identifying risk factors that can be controlled has become paramount to reduce the personal, societal and economic burden of dementia. The relationship between exposure to air pollution and effects on cognitive function, cognitive decline and dementia has stimulated increasing scientific interest in the past few years. This review of the literature critically examines the available epidemiological evidence of associations between exposure to ambient air pollutants, cognitive performance, acceleration of cognitive decline, risk of developing dementia, neuroimaging and neurological biomarker studies, following Bradford Hill guidelines for causality. The evidence reviewed has been consistent in reporting associations between chronic exposure to air pollution and reduced global cognition, as well as impairment in specific cognitive domains including visuo-spatial abilities. Cognitive decline and dementia incidence have also been consistently associated with exposure to air pollution. The neuro-imaging studies reviewed report associations between exposure to air pollution and white matter volume reduction. Other reported effects include reduction in gray matter, larger ventricular volume, and smaller corpus callosum. Findings relating to ischemic (white matter hyperintensities/silent cerebral infarcts) and hemorrhagic (cerebral microbleeds) markers of cerebral small vessel disease have been heterogeneous, as have observations on hippocampal volume and air pollution. The few studies available on neuro-inflammation tend to report associations with exposure to air pollution. Several effect modifiers have been suggested in the literature, but more replication studies are required. Traditional confounding factors have been controlled or adjusted for in most of the reviewed studies. Additional confounding factors have also been considered, but the inclusion of these has varied among the different studies. Despite all the efforts to adjust for confounding factors, residual confounding cannot be completely ruled out, especially since the factors affecting cognition and dementia are not yet fully understood. The available evidence meets many of the Bradford Hill guidelines for causality. The reported associations between a range of air pollutants and effects on cognitive function in older people, including the acceleration of cognitive decline and the induction of dementia, are likely to be causal in nature. However, the diversity of study designs, air pollutants and endpoints examined precludes the attribution of these adverse effects to a single class of pollutant and makes meta-analysis inappropriate.

Morphometric and Functional Brain Connectivity Differentiates Chess Masters From Amateur Players

A common task in brain image analysis includes diagnosis of a certain medical condition wherein groups of healthy controls and diseased subjects are analyzed and compared. On the other hand, for two groups of healthy participants with different proficiency in a certain skill, a distinctive analysis of the brain function remains a challenging problem. In this study, we develop new computational tools to explore the functional and anatomical differences that could exist between the brain of healthy individuals identified on the basis of different levels of task experience/proficiency. Toward this end, we look at a dataset of amateur and professional chess players, where we utilize resting-state functional magnetic resonance images to generate functional connectivity (FC) information. In addition, we utilize T1-weighted magnetic resonance imaging to estimate morphometric connectivity (MC) information. We combine functional and anatomical features into a new connectivity matrix, which we term as the functional morphometric similarity connectome (FMSC). Since, both the FC and MC information is susceptible to redundancy, the size of this information is reduced using statistical feature selection. We employ off-the-shelf machine learning classifier, support vector machine, for both single- and multi-modality classifications. From our experiments, we establish that the saliency and ventral attention network of the brain is functionally and anatomically different between two groups of healthy subjects (chess players). We argue that, since chess involves many aspects of higher order cognition such as systematic thinking and spatial reasoning and the identified network is task-positive to cognition tasks requiring a response, our results are valid and supporting the feasibility of the proposed computational pipeline. Moreover, we quantitatively validate an existing neuroscience hypothesis that learning a certain skill could cause a change in the brain (functional connectivity and anatomy) and this can be tested via our novel FMSC algorithm.

The cingulum in very preterm infants relates to language and social-emotional impairment at 2 years of term-equivalent age

•

Maturation of specific WM tracts in preterm individuals differs from those of term controls.

•

The elastic net logistic regression model was used to identify altered white matter tracts in the preterm brain.

•

The alteration of the cingulum in the preterm at near-term correlate with neurodevelopmental scores at 18–22 months of age.

Background

Relative to full-term infants, very preterm infants exhibit disrupted white matter (WM) maturation and problems related to development, including motor, cognitive, social-emotional, and receptive and expressive language processing.

Objective

The present study aimed to determine whether regional abnormalities in the WM microstructure of very preterm infants, as defined relative to those of full-term infants at a near-term age, are associated with neurodevelopmental outcomes at the age of 18–22 months.

Methods

We prospectively enrolled 89 very preterm infants (birth weight < 1500 g) and 43 normal full-term control infants born between 2016 and 2018. All infants underwent a structural brain magnetic resonance imaging scan at near-term age. The diffusion tensor imaging (DTI) metrics of the whole-brain WM tracts were extracted based on the neonatal probabilistic WM pathway. The elastic net logistic regression model was used to identify altered WM tracts in the preterm brain. We evaluated the associations between the altered WM microstructure at near-term age and motor, cognitive, social-emotional, and receptive and expressive language developments at 18–22 months of age, as measured using the Bayley Scales of Infant Development, Third Edition.

Results

We found that the elastic net logistic regression model could classify preterm and full-term neonates with an accuracy of 87.9% (corrected p < 0.008) using the DTI metrics in the pathway of interest with a 10% threshold level. The fractional anisotropy (FA) values of the body and splenium of the corpus callosum, middle cerebellar peduncle, left and right uncinate fasciculi, and right portion of the pathway between the premotor and primary motor cortices (premotor-PMC), as well as the mean axial diffusivity (AD) values of the left cingulum, were identified as contributive features for classification. Increased adjusted AD values in the left cingulum pathway were significantly correlated with language scores after false discovery rate (FDR) correction (r = 0.217, p = 0.043). The expressive language and social-emotional composite scores showed a significant positive correlation with the AD values in the left cingulum pathway (r = 0.226 [p = 0.036] and r = 0.31 [p = 0.003], respectively) after FDR correction.

Conclusion

Our approach suggests that the cingulum pathways of very preterm infants differ from those of full-term infants and significantly contribute to the prediction of the subsequent development of the language and social-emotional domains. This finding could improve our understanding of how specific neural substrates influence neurodevelopment at later ages, and individual risk prediction, thus helping to inform early intervention strategies that address developmental delay.

Associations between texture of T1-weighted magnetic resonance imaging and radiographic pathologies in Alzheimer's disease

BACKGROUND AND PURPOSE

Texture analysis of magnetic resonance imaging (MRI) brain scans have been proposed as a promising tool in the early diagnosis of Alzheimer's disease (AD), but its biological correlates remain unknown. In this study, we examined the relationship between MRI texture features and AD pathology.

METHODS

The study included 150 participants who had a 3.0T T1-weighted image, amyloid-β positron emission tomography (PET), and tau PET within 3 months of each other. In each of six brain regions (hippocampus, precuneus, and entorhinal, middle temporal, posterior cingulate and superior frontal cortices), linear regression analyses adjusting for age and sex was performed to examine the effects of regional amyloid-β and tau burden on regional texture features. We also compared neuroimaging measures based on pathological severity using ANOVA.

RESULTS

In all regions, tau burden (p < 0.05), but not amyloid-β burden, were associated with a certain texture feature that varied with the region's cytoarchitecture. Specifically, autocorrelation and cluster shade were associated with tau burden in allocortical and periallocortical regions, whereas entropy and contrast were associated with tau burden in neocortical regions. Mean signal intensity of each region did not show any associations with AD pathology. The values of the region-specific textures also varied across groups of varying pathological severity.

CONCLUSIONS

Our results suggest that textures of T1-weighted MRI reflect changes in the brain that are associated with regional tau burden and the local cytoarchitecture. This study provides insight into how MRI texture can be used for detection of microstructural changes in AD.

Joint Multi-Modal Longitudinal Regression and Classification for Alzheimer's Disease Prediction

Alzheimer's disease (AD) is a serious neurodegenerative condition that affects millions of individuals across the world. As the average age of individuals in the United States and the world increases, the prevalence of AD will continue to grow. To address this public health problem, the research community has developed computational approaches to sift through various aspects of clinical data and uncover their insights, among which one of the most challenging problem is to determine the biological mechanisms that cause AD to develop. To study this problem, in this paper we present a novel Joint Multi-Modal Longitudinal Regression and Classification method and show how it can be used to identify the cognitive status of the participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort and the underlying biological mechanisms. By intelligently combining clinical data of various modalities (i.e., genetic information and brain scans) using a variety of regularizations that can identify AD-relevant biomarkers, we perform the regression and classification tasks simultaneously. Because the proposed objective is a non-smooth optimization problem that is difficult to solve in general, we derive an efficient iterative algorithm and rigorously prove its convergence. To validate our new method in predicting the cognitive scores of patients and their clinical diagnosis, we conduct comprehensive experiments on the ADNI cohort. Our promising results demonstrate the benefits and flexibility of the proposed method. We anticipate that our new method is of interest to clinical communities beyond AD research and have open-sourced the code of our method online.11 The code package for the proposed Joint Multi-Modal Longitudinal Regression and Classification model have been made publicly available online at https://github.com/minds-mines/jmmlrc.

Application of Generalized Split Linearized Bregman Iteration algorithm for Alzheimer's disease prediction

In this paper, we applied a novel method for the detection of Alzheimer's disease (AD) based on a structural magnetic resonance imaging (sMRI) dataset. Specifically, the method involved a new classification algorithm of machine learning, named Generalized Split Linearized Bregman Iteration (GSplit LBI). It combines logistic regression and structural sparsity regularizations. In the study, 57 AD patients and 47 normal controls (NCs) were enrolled. We first extracted the entire brain gray matter volume values of all subjects and then used GSplit LBI to build a predictive classification model with a 10-fold full cross-validation method. The model accuracy achieved 90.44%. To further verify which voxels in the dataset have greater impact on the prediction results, we ranked the weight parameters and obtained the top 6% of the model parameters. To verify the generalization of model prediction and the stability of feature selection, we performed a cross-test on the Alzheimer's Disease Neuroimaging Initiative (ADNI) and a Chinese dataset and achieved good performances on different cohorts. Conclusively, based on the sMRI dataset, our algorithm not only had good performance in a local cohort with high accuracy but also had good generalization of model prediction and stability of feature selection in different cohorts.

Predicting Longitudinal Outcomes of Alzheimer's Disease via a Tensor-Based Joint Classification and Regression Model

Alzheimer's disease (AD) is a serious neurodegenerative condition that affects millions of people across the world. Recently machine learning models have been used to predict the progression of AD, although they frequently do not take advantage of the longitudinal and structural components associated with multi-modal medical data. To address this, we present a new algorithm that uses the multi-block alternating direction method of multipliers to optimize a novel objective that combines multi-modal longitudinal clinical data of various modalities to simultaneously predict the cognitive scores and diagnoses of the participants in the Alzheimer's Disease Neuroimaging Initiative cohort. Our new model is designed to leverage the structure associated with clinical data that is not incorporated into standard machine learning optimization algorithms. This new approach shows state-of-the-art predictive performance and validates a collection of brain and genetic biomarkers that have been recorded previously in AD literature.

Particulate matter and episodic memory decline mediated by early neuroanatomic biomarkers of Alzheimer's disease

Evidence suggests exposure to particulate matter with aerodynamic diameter <2.5 μm (PM2.5) may increase the risk for Alzheimer's disease and related dementias. Whether PM2.5 alters brain structure and accelerates the preclinical neuropsychological processes remains unknown. Early decline of episodic memory is detectable in preclinical Alzheimer's disease. Therefore, we conducted a longitudinal study to examine whether PM2.5 affects the episodic memory decline, and also explored the potential mediating role of increased neuroanatomic risk of Alzheimer's disease associated with exposure. Participants included older females (n = 998; aged 73-87) enrolled in both the Women's Health Initiative Study of Cognitive Aging and the Women's Health Initiative Memory Study of Magnetic Resonance Imaging, with annual (1999-2010) episodic memory assessment by the California Verbal Learning Test, including measures of immediate free recall/new learning (List A Trials 1-3; List B) and delayed free recall (short- and long-delay), and up to two brain scans (MRI-1: 2005-06; MRI-2: 2009-10). Subjects were assigned Alzheimer's disease pattern similarity scores (a brain-MRI measured neuroanatomical risk for Alzheimer's disease), developed by supervised machine learning and validated with data from the Alzheimer's Disease Neuroimaging Initiative. Based on residential histories and environmental data on air monitoring and simulated atmospheric chemistry, we used a spatiotemporal model to estimate 3-year average PM2.5 exposure preceding MRI-1. In multilevel structural equation models, PM2.5 was associated with greater declines in immediate recall and new learning, but no association was found with decline in delayed-recall or composite scores. For each interquartile increment (2.81 μg/m3) of PM2.5, the annual decline rate was significantly accelerated by 19.3% [95% confidence interval (CI) = 1.9% to 36.2%] for Trials 1-3 and 14.8% (4.4% to 24.9%) for List B performance, adjusting for multiple potential confounders. Long-term PM2.5 exposure was associated with increased Alzheimer's disease pattern similarity scores, which accounted for 22.6% (95% CI: 1% to 68.9%) and 10.7% (95% CI: 1.0% to 30.3%) of the total adverse PM2.5 effects on Trials 1-3 and List B, respectively. The observed associations remained after excluding incident cases of dementia and stroke during the follow-up, or further adjusting for small-vessel ischaemic disease volumes. Our findings illustrate the continuum of PM2.5 neurotoxicity that contributes to early decline of immediate free recall/new learning at the preclinical stage, which is mediated by progressive atrophy of grey matter indicative of increased Alzheimer's disease risk, independent of cerebrovascular damage.

Magnetic resonance imaging texture predicts progression to dementia due to Alzheimer disease earlier than hippocampal volume

BACKGROUND

Early identification of people at risk of imminent progression to dementia due to Alzheimer disease is crucial for timely intervention and treatment. We investigated whether the texture of MRI brain scans could predict the progression of mild cognitive impairment (MCI) to Alzheimer disease earlier than volume.

METHODS

We constructed a development data set (121 people who were cognitively normal and 145 who had mild Alzheimer disease) and a validation data set (113 patients with stable MCI who did not progress to Alzheimer disease for 3 years; 40 with early MCI who progressed to Alzheimer disease after 12–36 months; and 41 with late MCI who progressed to Alzheimer disease within 12 months) from the Alzheimer’s Disease Neuroimaging Initiative. We analyzed the texture of the hippocampus, precuneus and posterior cingulate cortex using a grey-level co-occurrence matrix. We constructed texture and volume indices from the development data set using logistic regression. Using area under the curve (AUC) of receiver operator characteristics, we compared the accuracy of hippocampal volume, hippocampal texture and the composite texture of the hippocampus, precuneus and posterior cingulate cortex in predicting conversion from MCI to Alzheimer disease in the validation data set.

RESULTS

Compared with hippocampal volume, hippocampal texture (0.790 v. 0.739, p = 0.047) and composite texture (0.811 v. 0.739, p = 0.007) showed larger AUCs for conversion to Alzheimer disease from both early and late MCI. Hippocampal texture showed a marginally larger AUC than hippocampal volume in early MCI (0.795 v. 0.726, p = 0.060). Composite texture showed a larger AUC for conversion to Alzheimer disease than hippocampal volume in both early (0.817 v. 0.726, p = 0.027) and late MCI (0.805 v. 0.753, p = 0.019).

LIMITATIONS

This study was limited by the absence of histological data, and the pathology reflected by the texture measures remains to be validated.

CONCLUSION

Textures of the hippocampus, precuneus and posterior cingulate cortex predicted conversion from MCI to Alzheimer disease at an earlier time point and with higher accuracy than hippocampal volume.

Classification and Visualization of Alzheimer's Disease using Volumetric Convolutional Neural Network and Transfer Learning

Recently, deep-learning-based approaches have been proposed for the classification of neuroimaging data related to Alzheimer's disease (AD), and significant progress has been made. However, end-to-end learning that is capable of maximizing the impact of deep learning has yet to receive much attention due to the endemic challenge of neuroimaging caused by the scarcity of data. Thus, this study presents an approach meant to encourage the end-to-end learning of a volumetric convolutional neural network (CNN) model for four binary classification tasks (AD vs. normal control (NC), progressive mild cognitive impairment (pMCI) vs. NC, stable mild cognitive impairment (sMCI) vs. NC and pMCI vs. sMCI) based on magnetic resonance imaging (MRI) and visualizes its outcomes in terms of the decision of the CNNs without any human intervention. In the proposed approach, we use convolutional autoencoder (CAE)-based unsupervised learning for the AD vs. NC classification task, and supervised transfer learning is applied to solve the pMCI vs. sMCI classification task. To detect the most important biomarkers related to AD and pMCI, a gradient-based visualization method that approximates the spatial influence of the CNN model's decision was applied. To validate the contributions of this study, we conducted experiments on the ADNI database, and the results demonstrated that the proposed approach achieved the accuracies of 86.60% and 73.95% for the AD and pMCI classification tasks respectively, outperforming other network models. In the visualization results, the temporal and parietal lobes were identified as key regions for classification.

The Residual Center of Mass: An Image Descriptor for the Diagnosis of Alzheimer Disease

A crucial quest in neuroimaging is the discovery of image features (biomarkers) associated with neurodegenerative disorders. Recent works show that such biomarkers can be obtained by image analysis techniques. However, these techniques cannot be directly compared since they use different databases and validation protocols. In this paper, we present an extensive study of image descriptors for the diagnosis of Alzheimer Disease (AD) and introduce a new one, named Residual Center of Mass (RCM). The RCM descriptor explores image moments and other techniques to enhance brain regions and select discriminative features for the diagnosis of AD. For validation, a Support Vector Machine (SVM) is trained with the selected features to classify images from normal subjects and patients with AD. We show that RCM with SVM achieves the best accuracies on a considerable number of exams by 10-fold cross-validation - 95.1% on 507 FDG-PET scans and 90.3% on 1374 MRI scans.

Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification

Deep neural networks have led to state-of-the-art results in many medical imaging tasks including Alzheimer's disease (AD) detection based on structural magnetic resonance imaging (MRI) data. However, the network decisions are often perceived as being highly non-transparent, making it difficult to apply these algorithms in clinical routine. In this study, we propose using layer-wise relevance propagation (LRP) to visualize convolutional neural network decisions for AD based on MRI data. Similarly to other visualization methods, LRP produces a heatmap in the input space indicating the importance/relevance of each voxel contributing to the final classification outcome. In contrast to susceptibility maps produced by guided backpropagation ("Which change in voxels would change the outcome most?"), the LRP method is able to directly highlight positive contributions to the network classification in the input space. In particular, we show that (1) the LRP method is very specific for individuals ("Why does this person have AD?") with high inter-patient variability, (2) there is very little relevance for AD in healthy controls and (3) areas that exhibit a lot of relevance correlate well with what is known from literature. To quantify the latter, we compute size-corrected metrics of the summed relevance per brain area, e.g., relevance density or relevance gain. Although these metrics produce very individual "fingerprints" of relevance patterns for AD patients, a lot of importance is put on areas in the temporal lobe including the hippocampus. After discussing several limitations such as sensitivity toward the underlying model and computation parameters, we conclude that LRP might have a high potential to assist clinicians in explaining neural network decisions for diagnosing AD (and potentially other diseases) based on structural MRI data.

Dimensionality reduction of diffusion MRI measures for improved tractometry of the human brain

Various diffusion MRI (dMRI) measures have been proposed for characterising tissue microstructure over the last 15 years. Despite the growing number of experiments using different dMRI measures in assessments of white matter, there has been limited work on: 1) examining their covariance along specific pathways; and on 2) combining these different measures to study tissue microstructure. Indeed, it quickly becomes intractable for existing analysis pipelines to process multiple measurements at each voxel and at each vertex forming a streamline, highlighting the need for new ways to visualise or analyse such high-dimensional data. In a sample of 36 typically developing children aged 8–18 years, we profiled various commonly used dMRI measures across 22 brain pathways. Using a data-reduction approach, we identified two biologically-interpretable components that capture 80% of the variance in these dMRI measures. The first derived component captures properties related to hindrance and restriction in tissue microstructure, while the second component reflects characteristics related to tissue complexity and orientational dispersion. We then demonstrate that the components generated by this approach preserve the biological relevance of the original measurements by showing age-related effects across developmentally sensitive pathways. In summary, our findings demonstrate that dMRI analyses can benefit from dimensionality reduction techniques, to help disentangling the neurobiological underpinnings of white matter organisation.

Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer's dementia diagnosis using multi-measure rs-fMRI spatial patterns

Background

Early diagnosis of Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state.

Materials and methods

We used two rs-fMRI cohorts: the public Alzheimer’s disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer’s disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs.

Results

The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001).

Conclusion

From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis.

A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer's disease

Some forms of mild cognitive impairment (MCI) are the clinical precursors of Alzheimer's disease (AD), while other MCI types tend to remain stable over-time and do not progress to AD. To identify and choose effective and personalized strategies to prevent or slow the progression of AD, we need to develop objective measures that are able to discriminate the MCI patients who are at risk of AD from those MCI patients who have less risk to develop AD. Here, we present a novel deep learning architecture, based on dual learning and an ad hoc layer for 3D separable convolutions, which aims at identifying MCI patients who have a high likelihood of developing AD within 3 years. Our deep learning procedures combine structural magnetic resonance imaging (MRI), demographic, neuropsychological, and APOe4 genetic data as input measures. The most novel characteristics of our machine learning model compared to previous ones are the following: 1) our deep learning model is multi-tasking, in the sense that it jointly learns to simultaneously predict both MCI to AD conversion as well as AD vs. healthy controls classification, which facilitates relevant feature extraction for AD prognostication; 2) the neural network classifier employs fewer parameters than other deep learning architectures which significantly limits data-overfitting (we use ∼550,000 network parameters, which is orders of magnitude lower than other network designs); 3) both structural MRI images and their warp field characteristics, which quantify local volumetric changes in relation to the MRI template, were used as separate input streams to extract as much information as possible from the MRI data. All analyses were performed on a subset of the database made publicly available via the Alzheimer's Disease Neuroimaging Initiative (ADNI), (n = 785 participants, n = 192 AD patients, n = 409 MCI patients (including both MCI patients who convert to AD and MCI patients who do not covert to AD), and n = 184 healthy controls). The most predictive combination of inputs were the structural MRI images and the demographic, neuropsychological, and APOe4 data. In contrast, the warp field metrics were of little added predictive value. The algorithm was able to distinguish the MCI patients developing AD within 3 years from those patients with stable MCI over the same time-period with an area under the curve (AUC) of 0.925 and a 10-fold cross-validated accuracy of 86%, a sensitivity of 87.5%, and specificity of 85%. To our knowledge, this is the highest performance achieved so far using similar datasets. The same network provided an AUC of 1 and 100% accuracy, sensitivity, and specificity when classifying patients with AD from healthy controls. Our classification framework was also robust to the use of different co-registration templates and potentially irrelevant features/image portions. Our approach is flexible and can in principle integrate other imaging modalities, such as PET, and diverse other sets of clinical data. The convolutional framework is potentially applicable to any 3D image dataset and gives the flexibility to design a computer-aided diagnosis system targeting the prediction of several medical conditions and neuropsychiatric disorders via multi-modal imaging and tabular clinical data.

Prediction of Autopsy Verified Neuropathological Change of Alzheimer's Disease Using Machine Learning and MRI

Background: Alzheimer’s disease (AD) is the most common form of dementia. While neuropathological changes pathognomonic for AD have been defined, early detection of AD prior to cognitive impairment in the clinical setting is still lacking. Pioneer studies applying machine learning to magnetic-resonance imaging (MRI) data to predict mild cognitive impairment (MCI) or AD have yielded high accuracies, however, an algorithm predicting neuropathological change is still lacking. The objective of this study was to compute a prediction model supporting a more distinct diagnostic criterium for AD compared to clinical presentation, allowing identification of hallmark changes even before symptoms occur.

Methods: Autopsy verified neuropathological changes attributed to AD, as described by a combined score for Aβ-peptides, neurofibrillary tangles and neuritic plaques issued by the National Institute on Aging – Alzheimer’s Association (NIAA), the ABC score for AD, were predicted from structural MRI data with RandomForest (RF). MRI scans were performed at least 2 years prior to death. All subjects derive from the prospective Vienna Trans-Danube Aging (VITA) study that targeted all 1750 inhabitants of the age of 75 in the starting year of 2000 in two districts of Vienna and included irregular follow-ups until death, irrespective of clinical symptoms or diagnoses. For 68 subjects MRI as well as neuropathological data were available and 49 subjects (mean age at death: 82.8 ± 2.9, 29 female) with sufficient MRI data quality were enrolled for further statistical analysis using nested cross-validation (CV). The decoding data of the inner loop was used for variable selection and parameter optimization with a fivefold CV design, the new data of the outer loop was used for model validation with optimal settings in a fivefold CV design. The whole procedure was performed ten times and average accuracies with standard deviations were reported.

Results: The most informative ROIs included caudal and rostral anterior cingulate gyrus, entorhinal, fusiform and insular cortex and the subcortical ROIs anterior corpus callosum and the left vessel, a ROI comprising lacunar alterations in inferior putamen and pallidum. The resulting prediction models achieved an average accuracy for a three leveled NIAA AD score of 0.62 within the decoding sets and of 0.61 for validation sets. Higher accuracies of 0.77 for both sets, respectively, were achieved when predicting presence or absence of neuropathological change.

Conclusion: Computer-aided prediction of neuropathological change according to the categorical NIAA score in AD, that currently can only be assessed post-mortem, may facilitate a more distinct and definite categorization of AD dementia. Reliable detection of neuropathological hallmarks of AD would enable risk stratification at an earlier level than prediction of MCI or clinical AD symptoms and advance precision medicine in neuropsychiatry.

Topological Pattern Recognition of Severe Alzheimer's Disease via Regularized Supervised Learning of EEG Complexity

Alzheimer's disease (AD) is a progressive brain disorder with gradual memory loss that correlates to cognitive deficits in the elderly population. Recent studies have shown the potentials of machine learning algorithms to identify biomarkers and functional brain activity patterns across various AD stages using electroencephalography (EEG). In this study, we aim to discover the altered spatio-temporal patterns of EEG complexity associated with AD pathology in different severity levels. We employed the multiscale entropy (MSE), a complexity measure of time series signals, as the biomarkers to characterize the nonlinear complexity at multiple temporal scales. Two regularized logistic regression methods were applied to extracted MSE features to capture the topographic pattern of MSEs of AD cohorts compared to healthy baseline. Furthermore, canonical correlation analysis was performed to evaluate the multivariate correlation between EEG complexity and cognitive dysfunction measured by the Neuropsychiatric Inventory scores. 123 participants were recruited and each participant was examined in three sessions (length = 10 seconds) to collect resting-state EEG signals. MSE features were extracted across 20 time scale factors with pre-determined parameters (m = 2, r = 0.15). The results showed that comparing to logistic regression model, the regularized learning methods performed better for discriminating severe AD cohort from normal control, very mild and mild cohorts (test accuracy ~ 80%), as well as for selecting significant biomarkers arcoss the brain regions. It was found that temporal and occipitoparietal brain regions were more discriminative in regard to classifying severe AD cohort vs. normal controls, but more diverse and distributed patterns of EEG complexity in the brain were exhibited across individuals in early stages of AD.

Clinical and Electrophysiological Differences between Subjects with Dysphonetic Dyslexia and Non-Specific Reading Delay

Reading is essentially a two-channel function, requiring the integration of intact visual and auditory processes both peripheral and central. It is essential for normal reading that these component processes go forward automatically. Based on this model, Boder described three main subtypes of dyslexia: dysphonetic dyslexia (DD), dyseidetic, mixed and besides a fourth group defined non-specific reading delay (NSRD). The subtypes are identified by an algorithm that considers the reading quotient and the % of errors in the spelling test. Chiarenza and Bindelli have developed the Direct Test of Reading and Spelling (DTRS), a computerized, modified and validated version to the Italian language of the Boder test. The sample consisted of 169 subjects with DD and 36 children with NSRD. The diagnosis of dyslexia was made according to the DSM-V criteria. The DTRS was used to identify the dyslexia subtypes and the NSRD group. 2⁻5 min of artefact-free EEG (electroencephalogram), recorded at rest with eyes closed, according to 10⁻20 system were analyzed. Stability based Biomarkers identification methodology was applied to the DTRS and the quantitative EEG (QEEG). The reading quotients and the errors of the reading and spelling test were significantly different in the two groups. The DD group had significantly higher activity in delta and theta bands compared to NSRD group in the frontal, central and parietal areas bilaterally. The classification equation for the QEEG, both at the scalp and the sources levels, obtained an area under the robust Receiver Operating Curve (ROC) of 0.73. However, we obtained a discrimination equation for the DTRS items which did not participate in the Boder classification algorithm, with a specificity and sensitivity of 0.94 to discriminate DD from NSRD. These results demonstrate for the first time the existence of different neuropsychological and neurophysiological patterns between children with DD and children with NSRD. They may also provide clinicians and therapists warning signals deriving from the anamnesis and the results of the DTRS that should lead to an earlier diagnosis of reading delay, which is usually very late diagnosed and therefore, untreated until the secondary school level.

Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer's disease across imaging databases

INTRODUCTION

The main goal of this work is to investigate the feasibility of estimating an anatomical index that can be used as an Alzheimer's disease (AD) risk factor in the Women's Health Initiative Magnetic Resonance Imaging Study (WHIMS-MRI) using MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), a well-characterized imaging database of AD patients and cognitively normal subjects. We called this index AD Pattern Similarity (AD-PS) scores. To demonstrate the construct validity of the scores, we investigated their associations with several AD risk factors. The ADNI and WHIMS imaging databases were collected with different goals, populations and data acquisition protocols: it is important to demonstrate that the approach to estimating AD-PS scores can bridge these differences.

METHODS

MRI data from both studies were processed using high-dimensional warping methods. High-dimensional classifiers were then estimated using the ADNI MRI data. Next, the classifiers were applied to baseline and follow-up WHIMS-MRI GM data to generate the GM AD-PS scores. To study the validity of the scores we investigated associations between GM AD-PS scores at baseline (Scan 1) and their longitudinal changes (Scan 2 -Scan 1) with: 1) age, cognitive scores, white matter small vessel ischemic disease (WM SVID) volume at baseline and 2) age, cognitive scores, WM SVID volume longitudinal changes respectively. In addition, we investigated their associations with time until classification of independently adjudicated status in WHIMS-MRI.

RESULTS

Higher GM AD-PS scores from WHIMS-MRI baseline data were associated with older age, lower cognitive scores, and higher WM SVID volume. Longitudinal changes in GM AD-PS scores (Scan 2 - Scan 1) were also associated with age and changes in WM SVID volumes and cognitive test scores. Increases in the GM AD-PS scores predicted decreases in cognitive scores and increases in WM SVID volume. GM AD-PS scores and their longitudinal changes also were associated with time until classification of cognitive impairment. Finally, receiver operating characteristic curves showed that baseline GM AD-PS scores of cognitively normal participants carried information about future cognitive status determined during follow-up.

DISCUSSION

We applied a high-dimensional machine learning approach to estimate a novel AD risk factor for WHIMS-MRI study participants using ADNI data. The GM AD-PS scores showed strong associations with incident cognitive impairment and cross-sectional and longitudinal associations with age, cognitive function, cognitive status and WM SVID volume lending support to the ongoing validation of the GM AD-PS score.

SMAC: Spatial multi-category angle-based classifier for high-dimensional neuroimaging data

With the development of advanced imaging techniques, scientists are interested in identifying imaging biomarkers that are related to different subtypes or transitional stages of various cancers, neuropsychiatric diseases, and neurodegenerative diseases, among many others. In this paper, we propose a novel spatial multi-category angle-based classifier (SMAC) for the efficient identification of such imaging biomarkers. The proposed SMAC not only utilizes the spatial structure of high-dimensional imaging data but also handles both binary and multi-category classification problems. We introduce an efficient algorithm based on an alternative direction method of multipliers to solve the large-scale optimization problem for SMAC. Both our simulation and real data experiments demonstrate the usefulness of SMAC.

Random Forests Based Group Importance Scores and Their Statistical Interpretation: Application for Alzheimer's Disease

Machine learning approaches have been increasingly used in the neuroimaging field for the design of computer-aided diagnosis systems. In this paper, we focus on the ability of these methods to provide interpretable information about the brain regions that are the most informative about the disease or condition of interest. In particular, we investigate the benefit of group-based, instead of voxel-based, analyses in the context of Random Forests. Assuming a prior division of the voxels into non overlapping groups (defined by an atlas), we propose several procedures to derive group importances from individual voxel importances derived from Random Forests models. We then adapt several permutation schemes to turn group importance scores into more interpretable statistical scores that allow to determine the truly relevant groups in the importance rankings. The good behaviour of these methods is first assessed on artificial datasets. Then, they are applied on our own dataset of FDG-PET scans to identify the brain regions involved in the prognosis of Alzheimer's disease.

Histogram-Based Features Selection and Volume of Interest Ranking for Brain PET Image Classification

Positron emission tomography (PET) is a molecular medical imaging modality which is commonly used for neurodegenerative diseases diagnosis. Computer-aided diagnosis, based on medical image analysis, could help quantitative evaluation of brain diseases such as Alzheimer's disease (AD). A novel method of ranking the effectiveness of brain volume of interest (VOI) to separate healthy control from AD brains PET images is presented in this paper. Brain images are first mapped into anatomical VOIs using an atlas. Histogram-based features are then extracted and used to select and rank VOIs according to the area under curve (AUC) parameter, which produces a hierarchy of the ability of VOIs to separate between groups of subjects. The top-ranked VOIs are then input into a support vector machine classifier. The developed method is evaluated on a local database image and compared to the known selection feature methods. Results show that using AUC outperforms classification results in the case of a two group separation.

The impact of epilepsy surgery on the structural connectome and its relation to outcome

Background

Temporal lobe surgical resection brings seizure remission in up to 80% of patients, with long-term complete seizure freedom in 41%. However, it is unclear how surgery impacts on the structural white matter network, and how the network changes relate to seizure outcome.

Methods

We used white matter fibre tractography on preoperative diffusion MRI to generate a structural white matter network, and postoperative T1-weighted MRI to retrospectively infer the impact of surgical resection on this network. We then applied graph theory and machine learning to investigate the properties of change between the preoperative and predicted postoperative networks.

Results

Temporal lobe surgery had a modest impact on global network efficiency, despite the disruption caused. This was due to alternative shortest paths in the network leading to widespread increases in betweenness centrality post-surgery. Measurements of network change could retrospectively predict seizure outcomes with 79% accuracy and 65% specificity, which is twice as high as the empirical distribution. Fifteen connections which changed due to surgery were identified as useful for prediction of outcome, eight of which connected to the ipsilateral temporal pole.

Conclusion

Our results suggest that the use of network change metrics may have clinical value for predicting seizure outcome. This approach could be used to prospectively predict outcomes given a suggested resection mask using preoperative data only.

A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages

Neuroimaging has made it possible to measure pathological brain changes associated with Alzheimer's disease (AD) in vivo. Over the past decade, these measures have been increasingly integrated into imaging signatures of AD by means of classification frameworks, offering promising tools for individualized diagnosis and prognosis. We reviewed neuroimaging-based studies for AD and mild cognitive impairment classification, selected after online database searches in Google Scholar and PubMed (January, 1985-June, 2016). We categorized these studies based on the following neuroimaging modalities (and sub-categorized based on features extracted as a post-processing step from these modalities): i) structural magnetic resonance imaging [MRI] (tissue density, cortical surface, and hippocampal measurements), ii) functional MRI (functional coherence of different brain regions, and the strength of the functional connectivity), iii) diffusion tensor imaging (patterns along the white matter fibers), iv) fluorodeoxyglucose positron emission tomography (FDG-PET) (metabolic rate of cerebral glucose), and v) amyloid-PET (amyloid burden). The studies reviewed indicate that the classification frameworks formulated on the basis of these features show promise for individualized diagnosis and prediction of clinical progression. Finally, we provided a detailed account of AD classification challenges and addressed some future research directions.

Revealing cancer subtypes with higher-order correlations applied to imaging and omics data

Background

Patient stratification to identify subtypes with different disease manifestations, severity, and expected survival time is a critical task in cancer diagnosis and treatment. While stratification approaches using various biomarkers (including high-throughput gene expression measurements) for patient-to-patient comparisons have been successful in elucidating previously unseen subtypes, there remains an untapped potential of incorporating various genotypic and phenotypic data to discover novel or improved groupings.

Methods

Here, we present HOCUS, a unified analytical framework for patient stratification that uses a community detection technique to extract subtypes out of sparse patient measurements. HOCUS constructs a patient-to-patient network from similarities in the data and iteratively groups and reconstructs the network into higher order clusters. We investigate the merits of using higher-order correlations to cluster samples of cancer patients in terms of their associations with survival outcomes.

Results

In an initial test of the method, the approach identifies cancer subtypes in mutation data of glioblastoma, ovarian, breast, prostate, and bladder cancers. In several cases, HOCUS provides an improvement over using the molecular features directly to compare samples. Application of HOCUS to glioblastoma images reveals a size and location classification of tumors that improves over human expert-based stratification.

Conclusions

Subtypes based on higher order features can reveal comparable or distinct groupings. The distinct solutions can provide biologically- and treatment-relevant solutions that are just as significant as solutions based on the original data.

Electronic supplementary material

The online version of this article (doi:10.1186/s12920-017-0256-3) contains supplementary material, which is available to authorized users.

Prediction and classification of Alzheimer disease based on quantification of MRI deformation

Detecting early morphological changes in the brain and making early diagnosis are important for Alzheimer's disease (AD). High resolution magnetic resonance imaging can be used to help diagnosis and prediction of the disease. In this paper, we proposed a machine learning method to discriminate patients with AD or mild cognitive impairment (MCI) from healthy elderly and to predict the AD conversion in MCI patients by computing and analyzing the regional morphological differences of brain between groups. Distance between each pair of subjects was quantified from a symmetric diffeomorphic registration, followed by an embedding algorithm and a learning approach for classification. The proposed method obtained accuracy of 96.5% in differentiating mild AD from healthy elderly with the whole-brain gray matter or temporal lobe as region of interest (ROI), 91.74% in differentiating progressive MCI from healthy elderly and 88.99% in classifying progressive MCI versus stable MCI with amygdala or hippocampus as ROI. This deformation-based method has made full use of the pair-wise macroscopic shape difference between groups and consequently increased the power for discrimination.

Folded concave penalized learning in identifying multimodal MRI marker for Parkinson's disease

BACKGROUND

Brain MRI holds promise to gauge different aspects of Parkinson's disease (PD)-related pathological changes. Its analysis, however, is hindered by the high-dimensional nature of the data.

NEW METHOD

This study introduces folded concave penalized (FCP) sparse logistic regression to identify biomarkers for PD from a large number of potential factors. The proposed statistical procedures target the challenges of high-dimensionality with limited data samples acquired. The maximization problem associated with the sparse logistic regression model is solved by local linear approximation. The proposed procedures then are applied to the empirical analysis of multimodal MRI data.

RESULTS

From 45 features, the proposed approach identified 15 MRI markers and the UPSIT, which are known to be clinically relevant to PD. By combining the MRI and clinical markers, we can enhance substantially the specificity and sensitivity of the model, as indicated by the ROC curves.

COMPARISON TO EXISTING METHODS

We compare the folded concave penalized learning scheme with both the Lasso penalized scheme and the principle component analysis-based feature selection (PCA) in the Parkinson's biomarker identification problem that takes into account both the clinical features and MRI markers. The folded concave penalty method demonstrates a substantially better clinical potential than both the Lasso and PCA in terms of specificity and sensitivity.

CONCLUSIONS

For the first time, we applied the FCP learning method to MRI biomarker discovery in PD. The proposed approach successfully identified MRI markers that are clinically relevant. Combining these biomarkers with clinical features can substantially enhance performance.

Multivariate pattern analysis strategies in detection of remitted major depressive disorder using resting state functional connectivity

Understanding abnormal resting-state functional connectivity of distributed brain networks may aid in probing and targeting mechanisms involved in major depressive disorder (MDD). To date, few studies have used resting state functional magnetic resonance imaging (rs-fMRI) to attempt to discriminate individuals with MDD from individuals without MDD, and to our knowledge no investigations have examined a remitted (r) population. In this study, we examined the efficiency of support vector machine (SVM) classifier to successfully discriminate rMDD individuals from healthy controls (HCs) in a narrow early-adult age range. We empirically evaluated four feature selection methods including multivariate Least Absolute Shrinkage and Selection Operator (LASSO) and Elastic Net feature selection algorithms. Our results showed that SVM classification with Elastic Net feature selection achieved the highest classification accuracy of 76.1% (sensitivity of 81.5% and specificity of 68.9%) by leave-one-out cross-validation across subjects from a dataset consisting of 38 rMDD individuals and 29 healthy controls. The highest discriminating functional connections were between the left amygdala, left posterior cingulate cortex, bilateral dorso-lateral prefrontal cortex, and right ventral striatum. These appear to be key nodes in the etiopathophysiology of MDD, within and between default mode, salience and cognitive control networks. This technique demonstrates early promise for using rs-fMRI connectivity as a putative neurobiological marker capable of distinguishing between individuals with and without rMDD. These methods may be extended to periods of risk prior to illness onset, thereby allowing for earlier diagnosis, prevention, and intervention.

Evaluation of machine learning algorithms for treatment outcome prediction in patients with epilepsy based on structural connectome data

The objective of this study is to evaluate machine learning algorithms aimed at predicting surgical treatment outcomes in groups of patients with temporal lobe epilepsy (TLE) using only the structural brain connectome. Specifically, the brain connectome is reconstructed using white matter fiber tracts from presurgical diffusion tensor imaging. To achieve our objective, a two-stage connectome-based prediction framework is developed that gradually selects a small number of abnormal network connections that contribute to the surgical treatment outcome, and in each stage a linear kernel operation is used to further improve the accuracy of the learned classifier. Using a 10-fold cross validation strategy, the first stage in the connectome-based framework is able to separate patients with TLE from normal controls with 80% accuracy, and second stage in the connectome-based framework is able to correctly predict the surgical treatment outcome of patients with TLE with 70% accuracy. Compared to existing state-of-the-art methods that use VBM data, the proposed two-stage connectome-based prediction framework is a suitable alternative with comparable prediction performance. Our results additionally show that machine learning algorithms that exclusively use structural connectome data can predict treatment outcomes in epilepsy with similar accuracy compared with "expert-based" clinical decision. In summary, using the unprecedented information provided in the brain connectome, machine learning algorithms may uncover pathological changes in brain network organization and improve outcome forecasting in the context of epilepsy.

2014 Update of the Alzheimer's Disease Neuroimaging Initiative: A review of papers published since its inception

The Alzheimer's Disease Neuroimaging Initiative (ADNI) is an ongoing, longitudinal, multicenter study designed to develop clinical, imaging, genetic, and biochemical biomarkers for the early detection and tracking of Alzheimer's disease (AD). The initial study, ADNI-1, enrolled 400 subjects with early mild cognitive impairment (MCI), 200 with early AD, and 200 cognitively normal elderly controls. ADNI-1 was extended by a 2-year Grand Opportunities grant in 2009 and by a competitive renewal, ADNI-2, which enrolled an additional 550 participants and will run until 2015. This article reviews all papers published since the inception of the initiative and summarizes the results to the end of 2013. The major accomplishments of ADNI have been as follows: (1) the development of standardized methods for clinical tests, magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF) biomarkers in a multicenter setting; (2) elucidation of the patterns and rates of change of imaging and CSF biomarker measurements in control subjects, MCI patients, and AD patients. CSF biomarkers are largely consistent with disease trajectories predicted by β-amyloid cascade (Hardy, J Alzheimer's Dis 2006;9(Suppl 3):151-3) and tau-mediated neurodegeneration hypotheses for AD, whereas brain atrophy and hypometabolism levels show predicted patterns but exhibit differing rates of change depending on region and disease severity; (3) the assessment of alternative methods of diagnostic categorization. Currently, the best classifiers select and combine optimum features from multiple modalities, including MRI, [(18)F]-fluorodeoxyglucose-PET, amyloid PET, CSF biomarkers, and clinical tests; (4) the development of blood biomarkers for AD as potentially noninvasive and low-cost alternatives to CSF biomarkers for AD diagnosis and the assessment of α-syn as an additional biomarker; (5) the development of methods for the early detection of AD. CSF biomarkers, β-amyloid 42 and tau, as well as amyloid PET may reflect the earliest steps in AD pathology in mildly symptomatic or even nonsymptomatic subjects and are leading candidates for the detection of AD in its preclinical stages; (6) the improvement of clinical trial efficiency through the identification of subjects most likely to undergo imminent future clinical decline and the use of more sensitive outcome measures to reduce sample sizes. Multimodal methods incorporating APOE status and longitudinal MRI proved most highly predictive of future decline. Refinements of clinical tests used as outcome measures such as clinical dementia rating-sum of boxes further reduced sample sizes; (7) the pioneering of genome-wide association studies that leverage quantitative imaging and biomarker phenotypes, including longitudinal data, to confirm recently identified loci, CR1, CLU, and PICALM and to identify novel AD risk loci; (8) worldwide impact through the establishment of ADNI-like programs in Japan, Australia, Argentina, Taiwan, China, Korea, Europe, and Italy; (9) understanding the biology and pathobiology of normal aging, MCI, and AD through integration of ADNI biomarker and clinical data to stimulate research that will resolve controversies about competing hypotheses on the etiopathogenesis of AD, thereby advancing efforts to find disease-modifying drugs for AD; and (10) the establishment of infrastructure to allow sharing of all raw and processed data without embargo to interested scientific investigators throughout the world.

Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects

Mild cognitive impairment (MCI) is a transitional stage between age-related cognitive decline and Alzheimer's disease (AD). For the effective treatment of AD, it would be important to identify MCI patients at high risk for conversion to AD. In this study, we present a novel magnetic resonance imaging (MRI)-based method for predicting the MCI-to-AD conversion from one to three years before the clinical diagnosis. First, we developed a novel MRI biomarker of MCI-to-AD conversion using semi-supervised learning and then integrated it with age and cognitive measures about the subjects using a supervised learning algorithm resulting in what we call the aggregate biomarker. The novel characteristics of the methods for learning the biomarkers are as follows: 1) We used a semi-supervised learning method (low density separation) for the construction of MRI biomarker as opposed to more typical supervised methods; 2) We performed a feature selection on MRI data from AD subjects and normal controls without using data from MCI subjects via regularized logistic regression; 3) We removed the aging effects from the MRI data before the classifier training to prevent possible confounding between AD and age related atrophies; and 4) We constructed the aggregate biomarker by first learning a separate MRI biomarker and then combining it with age and cognitive measures about the MCI subjects at the baseline by applying a random forest classifier. We experimentally demonstrated the added value of these novel characteristics in predicting the MCI-to-AD conversion on data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. With the ADNI data, the MRI biomarker achieved a 10-fold cross-validated area under the receiver operating characteristic curve (AUC) of 0.7661 in discriminating progressive MCI patients (pMCI) from stable MCI patients (sMCI). Our aggregate biomarker based on MRI data together with baseline cognitive measurements and age achieved a 10-fold cross-validated AUC score of 0.9020 in discriminating pMCI from sMCI. The results presented in this study demonstrate the potential of the suggested approach for early AD diagnosis and an important role of MRI in the MCI-to-AD conversion prediction. However, it is evident based on our results that combining MRI data with cognitive test results improved the accuracy of the MCI-to-AD conversion prediction.

Predicting growth conditions from internal metabolic fluxes in an in-silico model of E. coli

A widely studied problem in systems biology is to predict bacterial phenotype from growth conditions, using mechanistic models such as flux balance analysis (FBA). However, the inverse prediction of growth conditions from phenotype is rarely considered. Here we develop a computational framework to carry out this inverse prediction on a computational model of bacterial metabolism. We use FBA to calculate bacterial phenotypes from growth conditions in E. coli, and then we assess how accurately we can predict the original growth conditions from the phenotypes. Prediction is carried out via regularized multinomial regression. Our analysis provides several important physiological and statistical insights. First, we show that by analyzing metabolic end products we can consistently predict growth conditions. Second, prediction is reliable even in the presence of small amounts of impurities. Third, flux through a relatively small number of reactions per growth source (∼10) is sufficient for accurate prediction. Fourth, combining the predictions from two separate models, one trained only on carbon sources and one only on nitrogen sources, performs better than models trained to perform joint prediction. Finally, that separate predictions perform better than a more sophisticated joint prediction scheme suggests that carbon and nitrogen utilization pathways, despite jointly affecting cellular growth, may be fairly decoupled in terms of their dependence on specific assortments of molecular precursors.