Definition and analysis of gray matter atrophy subtypes in mild cognitive impairment based on data-driven methods.

In recent studies of Alzheimer's disease (AD), it has increasing attentions in identifying mild cognitive impairment (MCI) converters (MCI-C) from MCI non-converters (MCI-NC). Note that MCI is a prodromal stage of AD, with possibility to convert to AD. Most traditional methods for MCI conversion prediction learn information only from MCI subjects (including MCI-C and MCI-NC), not from other related subjects, e.g., AD and normal controls (NC), which can actually aid the classification between MCI-C and MCI-NC. In this paper, we propose a novel domain-transfer learning method for MCI conversion prediction. Different from most existing methods, we classify MCI-C and MCI-NC with aid from the domain knowledge learned with AD and NC subjects as auxiliary domain to further improve the classification performance. Our method contains two key components: (1) the cross-domain kernel learning for transferring auxiliary domain knowledge, and (2) the adapted support vector machine (SVM) decision function construction for cross-domain and auxiliary domain knowledge fusion. Experimental results on the Alzheimer's Disease neuroimaging initiative (ADNI) database show that the proposed method can significantly improve the classification performance between MCI-C and MCI-NC, with aid of domain knowledge learned from AD and NC subjects.

A rapid increase in the number of patients with Alzheimer's disease (AD) is expected over the next decades. Accordingly, there is a critical need for early-stage AD detection methods that can enable effective treatment strategies. In this study, we consider the ability of episodic-memory measures to predict mild cognitive impairment (MCI) to AD conversion and thus, detect early-stage AD. For our analysis, we studied 307 participants with MCI across four years using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Using a binary logistic regression, we compared episodic-memory tests to each other and to prominent neuroimaging methods in MCI converter (MCI participants who developed AD) and MCI non-converter groups (MCI participants who did not develop AD). We also combined variables to test the accuracy of mixed-predictor models. Our results indicated that the best predictors of MCI to AD conversion were the following: a combined episodic-memory and neuroimaging model in year one (59.8%), the Rey Auditory Verbal Learning Test in year two (71.7%), a mixed episodic-memory predictor model in year three (77.7%) and the Logical Memory Test in year four (77.2%) of ADNI. Overall, we found that individual episodic-memory measure and mixed models performed similarly when predicting MCI to AD conversion. Comparatively, individual neuroimaging measures predicted MCI conversion worse than chance. Accordingly, our results indicate that episodic-memory tests could be instrumental in detecting early-stage AD and enabling effective treatment.

(Reprinted with permission from American Psychiatric Association, http://psychiatryonline.org/guidelines).

Graphical, voxel, and region-based analysis has become a popular approach to studying neurodegenerative disorders such as Alzheimer’s disease (AD) and its prodromal stage [mild cognitive impairment (MCI)]. These methods have been used previously for classification or discrimination of AD in subjects in a prodromal stage called stable MCI (MCIs), which does not convert to AD but remains stable over a period of time, and converting MCI (MCIc), which converts to AD, but the results reported across similar studies are often inconsistent. Furthermore, the classification accuracy for MCIs vs. MCIc is limited. In this study, we propose combining different neuroimaging modalities (sMRI, FDG-PET, AV45-PET, DTI, and rs-fMRI) with the apolipoprotein-E genotype to form a multimodal system for the discrimination of AD, and to increase the classification accuracy. Initially, we used two well-known analyses to extract features from each neuroimage for the discrimination of AD: whole-brain parcelation analysis (or region-based analysis), and voxel-wise analysis (or voxel-based morphometry). We also investigated graphical analysis (nodal and group) for all six binary classification groups (AD vs. HC, MCIs vs. MCIc, AD vs. MCIc, AD vs. MCIs, HC vs. MCIc, and HC vs. MCIs). Data for a total of 129 subjects (33 AD, 30 MCIs, 31 MCIc, and 35 HCs) for each imaging modality were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) homepage. These data also include two APOE genotype data points for the subjects. Moreover, we used the 2-mm AICHA atlas with the NiftyReg registration toolbox to extract 384 brain regions from each PET (FDG and AV45) and sMRI image. For the rs-fMRI images, we used the DPARSF toolbox in MATLAB for the automatic extraction of data and the results for REHO, ALFF, and fALFF. We also used the pyClusterROI script for the automatic parcelation of each rs-fMRI image into 200 brain regions. For the DTI images, we used the FSL (Version 6.0) toolbox for the extraction of fractional anisotropy (FA) images to calculate a tract-based spatial statistic. Moreover, we used the PANDA toolbox to obtain 50 white-matter-region-parcellated FA images on the basis of the 2-mm JHU-ICBM-labeled template atlas. To integrate the different modalities and different complementary information into one form, and to optimize the classifier, we used the multiple kernel learning (MKL) framework. The obtained results indicated that our multimodal approach yields a significant improvement in accuracy over any single modality alone. The areas under the curve obtained by the proposed method were 97.78, 96.94, 95.56, 96.25, 96.67, and 96.59% for AD vs. HC, MCIs vs. MCIc, AD vs. MCIc, AD vs. MCIs, HC vs. MCIc, and HC vs. MCIs binary classification, respectively. Our proposed multimodal method improved the classification result for MCIs vs. MCIc groups compared with the unimodal classification results. Our study found that the (left/right) precentral region was present in all six binary classification groups (this region can be considered the most significant region). Furthermore, using nodal network topology, we found that FDG, AV45-PET, and rs-fMRI were the most important neuroimages, and showed many affected regions relative to other modalities. We also compared our results with recently published results.

Prediction of Alzheimer's disease in mild cognitive impairment: A prospective study in Taiwan

We evaluated the relationship between white matter (WM) tract disintegration and gray matter (GM) atrophy in patients with Alzheimer's disease (AD), mild cognitive impairment (MCI) and controls, using diffusion tensor imaging (DTI) and an optimized voxel-based analysis. Two hundred thirty one individuals (61 controls, 116 MCI and 54 AD) were included. Voxel-based WM tract statistics was used to obtain whole-brain maps of WM bundles for FA. Voxel-based morphometry (VBM) was conducted to detect regions of gray matter (GM) atrophy in the AD, MCI group relative to the control group. FA maps were processed to make voxel-wise comparison of tract based analysis in whole brain between each the two groups. The relationship between locations of abnormalities in the WM and GM were examined. Patients with AD showed significant GM atrophy in posterior cingulate gyrus (BA31, 32) to the precuneus, the middle temporal lobe (BA19), the superior frontal (BA9) to the anterior cingulate (BA 32), the medial frontal lobe (BA 11, BA25), the hippocampus, the parahippocampal gyrus (BA30/34) and the insula, and WM tract disintegrity of the uncinate fasciculus, posterior cingulate fasciculus and fornix compared with the control and MCI groups. These abnormalities in the AD group were caused by either structural changes in GM atrophy or neural dysfunction due to functional disconnections in the WM tract. The GM atrophy resulting from WM tract disintegration or GM atrophy itself may be the first step in the AD process, resulting in anatomically congruent correlations between WM disintegration and regional GM atrophy. Using tract based spatial statistics and voxel based analysis, both of which are useful in investigating GM and WM changes in individuals with neurodegenerative disorders.

Medial temporal lobe atrophy scores translated to clinical practice: Editorial comment on ‘Influence of age, disease onset and ApoE4 on visual medial temporal lobe atrophy cut‐offs'

With the recent advances in the treatment of Alzheimer's disease (AD) over the last decade, the focus has increasingly shifted to accurate detection of the earliest phase of illness. The intermediate state between normal aging and established AD is commonly known as mild cognitive impairment (MCI). Not all patients with MCI progress to AD and hence there is a need to reliably predict which patients with MCI will progress. The current inability of clinical criteria to accurately identify this at-risk group is fuelling the emerging interest in biomarkers to potentially supplement or replace clinical approaches. Biomarkers have the potential to clearly reflect the progressive deterioration that is present even in the earliest stages of AD--a useful feature for demonstrating the effectiveness or otherwise of a particular dementia drug. This paper will review the evidence regarding the use of cerebrospinal fluid, neuroimaging and blood biomarkers, as well as combination biomarkers, from the two standpoints of predicting MCI conversion to AD and monitoring disease progression at the MCI stage, so as to recommend which biomarkers can reasonably be included in early dementia trials, and how they can best be used.

How far is arterial spin labeling MRI from a clinical reality? Insights from arterial spin labeling comparative studies in Alzheimer's disease and other neurological disorders.

Mild Cognitive Impairment is a syndrome defined as cognitive decline greater than expected for an individual's age and education level but that does not interfere notably with activities of daily life. Prevalence in population-based epidemiological studies ranges from 3% to 19% in adults older than 65 years. Some people with mild cognitive impairment seem to remain stable or return to normal over time, but more than half progress to dementia within 5 years. Mild cognitive impairment can thus be regarded as a risk state for dementia, and its identification could lead to secondary prevention by controlling risk factors such as systolic hypertension. The amnestic subtype of mild cognitive impairment has a high risk of progression to Alzheimer's disease, and it could constitute a prodromal stage of this disorder. Other definitions and subtypes of mild cognitive impairment need to be studied as potential prodromes of Alzheimer's disease and other types of dementia. Our intention is firstly, share some concepts to consider Alzheimer's disease as a cruel illness that can reach all the elderly people around the world. Secondly, to analyze the different forms of presentation than can mask a clinical state. Which many times could end-up in dementia? And will soon destroy the whole psychic apparatus of a person. The present our observational study group in the four institutional medical centers, with ambulatory patients, who consult about a cognitive disease. We describe the evolution trough time, taking into account the pharmacological treatments. We included 850 patients with diagnosis the Mild Cognitive Disorder and 348 patients with diagnosis the Alzheimer's Disease (DSM IV-TR criteria). The importance of the early detection of memory disorder, as one of the first signs of alarm which give us the opportunity to intervene therapeutically in on time. We can recognize the Mild Cognitive Disorder as a clue which reveals a first therapeutic instance probably in efficacy in this cruel evolution towards dementia.Discussion:In the presence of a disorder of memory in the elderly people, with the possibility of evolving towards dementia, we prefer to begin drug therapy early, preventive character.

Neuroinflammation is a pathological hallmark of Alzheimer's disease, but its role in cognitive impairment and its course of development during the disease are largely unknown. To address these unknowns, we used positron emission tomography with (11)C-PBR28 to measure translocator protein 18 kDa (TSPO), a putative biomarker for inflammation. Patients with Alzheimer's disease, patients with mild cognitive impairment and older control subjects were also scanned with (11)C-Pittsburgh Compound B to measure amyloid burden. Twenty-nine amyloid-positive patients (19 Alzheimer's, 10 mild cognitive impairment) and 13 amyloid-negative control subjects were studied. The primary goal of this study was to determine whether TSPO binding is elevated in patients with Alzheimer's disease, and the secondary goal was to determine whether TSPO binding correlates with neuropsychological measures, grey matter volume, (11)C-Pittsburgh Compound B binding, or age of onset. Patients with Alzheimer's disease, but not those with mild cognitive impairment, had greater (11)C-PBR28 binding in cortical brain regions than controls. The largest differences were seen in the parietal and temporal cortices, with no difference in subcortical regions or cerebellum. (11)C-PBR28 binding inversely correlated with performance on Folstein Mini-Mental State Examination, Clinical Dementia Rating Scale Sum of Boxes, Logical Memory Immediate (Wechsler Memory Scale Third Edition), Trail Making part B and Block Design (Wechsler Adult Intelligence Scale Third Edition) tasks, with the largest correlations observed in the inferior parietal lobule. (11)C-PBR28 binding also inversely correlated with grey matter volume. Early-onset (<65 years) patients had greater (11)C-PBR28 binding than late-onset patients, and in parietal cortex and striatum (11)C-PBR28 binding correlated with lower age of onset. Partial volume corrected and uncorrected results were generally in agreement; however, the correlation between (11)C-PBR28 and (11)C-Pittsburgh Compound B binding was seen only after partial volume correction. The results suggest that neuroinflammation, indicated by increased (11)C-PBR28 binding to TSPO, occurs after conversion of mild cognitive impairment to Alzheimer's disease and worsens with disease progression. Greater inflammation may contribute to the precipitous disease course typically seen in early-onset patients. (11)C-PBR28 may be useful in longitudinal studies to mark the conversion from mild cognitive impairment or to assess response to experimental treatments of Alzheimer's disease.

The present study compared four different structural magnetic resonance imaging (MRI) techniques used to measure gray matter atrophy in Alzheimer's disease (AD): manual and automated volumetry, cortical thickness (CT) and voxel-based morphometry (VBM)). These techniques are used interchangeably in AD research and thus far it is unclear which technique is superior in detecting abnormalities early in the disease process. We inquired whether these techniques show similar results in healthy controls (con), patients with amnestic mild cognitive impairment (MCI) and patients suffering from mild AD. In addition, we investigated whether atrophy of prefrontal cortex (PFC) or medial temporal lobe (MTL) regions is most indicative of (preclinical) AD. Three groups of older male participants were selected: 18 healthy participants without any memory impairment, 18 patients with amnestic MCI, and 18 patients with mild AD. Between-group differences were investigated in PFC and MTL regions. A manual and automatic tracing approach were applied to calculate gray matter volume. CT was furthermore calculated by Freesurfer as the average thickness of the cortical surface in each ROI. VBM was applied by using masks of atlas-based ROI's in FSL. Manually measured right parahippocampal gyrus (PHG) volumes can differentiate con and MCI. Con and AD can furthermore be distinguished by manually measured hippocampus and PHG volumes, and by automated measurements of hippocampus and entorhinal cortex (ERC). Manual segmentation techniques are also sensitive for changes in PFC areas showing abnormalities in inferior and orbital PFC (con /AD and MCI/AD). CT analysis showed differences between con and AD in ERC, right inferior prefrontal (IPFC) and left medial orbitofrontal cortex (OFC) regions. VBM-ROI analyses showed differences between con/AD and MCI/AD in hippocampus, IPFC and OPFC (Table 1). The present study demonstrates that manual volumetry and VBM are able to detect group differences in both PFC and MTL structures (con/AD and MCI/AD). Manual volumetry of the right PhG can furthermore differentiate between con and MCI. The present study confirms earlier theories that the MTL is most indicative of (preclinical) AD, showing abnormalities in all the investigated techniques.

In this work, we propose a novel subclass-based multi-task learning method for feature selection in computer-aided Alzheimer's Disease (AD) or Mild Cognitive Impairment (MCI) diagnosis. Unlike the previous methods that often assumed a unimodal data distribution, we take into account the underlying multipeak1 distribution of classes. The rationale for our approach is that it is highly likely for neuroimaging data to have multiple peaks or modes in distribution, e.g., mixture of Gaussians, due to the inter-subject variability. In this regard, we use a clustering method to discover the multipeak distributional characteristics and define subclasses based on the clustering results, in which each cluster covers a peak in the underlying multipeak distribution. Specifically, after performing clustering for each class, we encode the respective subclasses, i.e., clusters, with their unique codes. In encoding, we impose the subclasses of the same original class close to each other and those of different original classes distinct from each other. By setting the codes as new label vectors of our training samples, we formulate a multi-task learning problem in a ℓ2,1-penalized regression framework, through which we finally select features for classification. In our experimental results on the ADNI dataset, we validated the effectiveness of the proposed method by improving the classification accuracies by 1% (AD vs. Normal Control: NC), 3.25% (MCI vs. NC), 5.34% (AD vs. MCI), and 7.4% (MCI Converter: MCI-C vs. MCI Non-Converter: MCI-NC) compared to the competing single-task learning method. It is remarkable for the performance improvement in MCI-C vs. MCI-NC classification, which is the most important for early diagnosis and treatment. It is also noteworthy that with the strategy of modality-adaptive weights by means of a multi-kernel support vector machine, we maximally achieved the classification accuracies of 96.18% (AD vs. NC), 81.45% (MCI vs. NC), 73.21% (AD vs. MCI), and 74.04% (MCI-C vs. MCI-NC), respectively.

BackgroundAlzheimer's disease (AD) is a neurodegenerative condition for which there is currently no available medication that can stop its progression. Previous studies suggest that mild cognitive impairment (MCI) is a phase that precedes the disease. Therefore, a better understanding of the molecular mechanisms behind MCI conversion to AD is needed. MethodHere, we propose a machine learning-based approach to detect the key metabolites and proteins involved in MCI progression to AD using data from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery Study. Proteins and metabolites were evaluated separately in multiclass models (controls, MCI and AD) and together in MCI conversion models (MCI stable vs converter). Only features selected as relevant by 3/4 algorithms proposed were kept for downstream analysis. ResultsMulticlass models of metabolites highlighted nine features further validated in an independent cohort (0.726 mean balanced accuracy). Among these features, one metabolite, oleamide, was selected by all the algorithms. Further in-vitro experiments in rodents showed that disease-associated microglia excreted oleamide in vesicles. Multiclass models of proteins stood out with nine features, validated in an independent cohort (0.720 mean balanced accuracy). However, none of the proteins was selected by all the algorithms. Besides, to distinguish between MCI stable and converters, 14 key features were selected (0.872 AUC), including tTau, alpha-synuclein (SNCA), junctophilin-3 (JPH3), properdin (CFP) and peptidase inhibitor 15 (PI15) among others. ConclusionsThis omics integration approach highlighted a set of molecules associated with MCI conversion important in neuronal and glia inflammation pathways.

Identification of mild cognitive impairment subtypes predicting conversion to Alzheimer’s disease using multimodal data