Prediction Of Mild Cognitive Impairment Conversion Research Articles

Attention-Guided Hybrid Network for Dementia Diagnosis With Structural MR Images.

Deep-learning methods (especially convolutional neural networks) using structural magnetic resonance imaging (sMRI) data have been successfully applied to computer-aided diagnosis (CAD) of Alzheimer's disease (AD) and its prodromal stage [i.e., mild cognitive impairment (MCI)]. As it is practically challenging to capture local and subtle disease-associated abnormalities directly from the whole-brain sMRI, most of those deep-learning approaches empirically preselect disease-associated sMRI brain regions for model construction. Considering that such isolated selection of potentially informative brain locations might be suboptimal, very few methods have been proposed to perform disease-associated discriminative region localization and disease diagnosis in a unified deep-learning framework. However, those methods based on task-oriented discriminative localization still suffer from two common limitations, that is: 1) identified brain locations are strictly consistent across all subjects, which ignores the unique anatomical characteristics of each brain and 2) only limited local regions/patches are used for model training, which does not fully utilize the global structural information provided by the whole-brain sMRI. In this article, we propose an attention-guided deep-learning framework to extract multilevel discriminative sMRI features for dementia diagnosis. Specifically, we first design a backbone fully convolutional network to automatically localize the discriminative brain regions in a weakly supervised manner. Using the identified disease-related regions as spatial attention guidance, we further develop a hybrid network to jointly learn and fuse multilevel sMRI features for CAD model construction. Our proposed method was evaluated on three public datasets (i.e., ADNI-1, ADNI-2, and AIBL), showing superior performance compared with several state-of-the-art methods in both tasks of AD diagnosis and MCI conversion prediction.

A novel conversion prediction method of MCI to AD based on longitudinal dynamic morphological features using ADNI structural MRIs

Mild cognitive impairment (MCI) is a pre-existing state of Alzheimer's disease (AD). An accurate prediction on the conversion from MCI to AD is of vital clinical significance for potential prevention and treatment of AD. Longitudinal studies received widespread attention for investigating the disease progression, though most studies did not sufficiently utilize the evolution information. In this paper, we proposed a cerebral similarity network with more progression information to predict the conversion from MCI to AD efficiently. First, we defined the new dynamic morphological feature to mine longitudinal information sufficiently. Second, based on the multiple dynamic morphological features the cerebral similarity network was constructed by sparse regression algorithm with optimized parameters to obtain better prediction performance. Then, leave-one-out cross-validation and support vector machine (SVM) were employed for the training and evaluation of the classifiers. The proposed methodology obtained a high accuracy of 92.31% (Sensitivity = 100%, Specificity = 82.86%) in a three-year ahead prediction of MCI to AD conversion. Experiment results suggest the effectiveness of the dynamic morphological feature, serving asa more sensitive biomarker in the prediction of MCI conversion.

Identification of Alzheimer’s Disease on the Basis of a Voxel-Wise Approach

Robust prediction of Alzheimer’s disease (AD) helps in the early diagnosis of AD and may support the treatment of AD patients. In this study, for early detection of AD and prediction of mild cognitive impairment (MCI) conversion, we develop an automatic computer-aided diagnosis (CAD) framework based on a merit-based feature selection method through a whole-brain voxel-wise analysis using baseline magnetic resonance imaging (MRI) data. We also explore the impact of different MRI spatial resolution on the voxel-wise metric AD classification and MCI conversion prediction. We assessed the proposed CAD framework using the whole-brain voxel-wise MRI features of 507 J-ADNI participants (146 healthy controls [HCs], 102 individuals with stable MCI [sMCI], 112 with progressive MCI [pMCI], and 147 with AD) among four clinically relevant pairs of diagnostic groups at different imaging resolutions (i.e., 2, 4, 8, and 16 mm). Using a support vector machine classifier through a 10-fold cross-validation strategy at a spatial resolution of 2 mm, the proposed CAD framework yielded classification accuracies of 91.13%, 74.77%, 81.12%, and 81.78% in identifying AD/healthy control, sMCI/pMCI, sMCI/AD, and pMCI/HC, respectively. The experimental results show that a lower spatial resolution (i.e., 2 mm) may provide more robust information to trace the neuronal loss-related brain atrophy in AD.

Contourlet-based hippocampal magnetic resonance imaging texture features for multivariant classification and prediction of Alzheimer's disease.

The study is aimed to assess whether the addition of contourlet-based hippocampal magnetic resonance imaging (MRI) texture features to multivariant models improves the classification of Alzheimer's disease (AD) and the prediction of mild cognitive impairment (MCI) conversion, and to evaluate whether Gaussian process (GP) and partial least squares (PLS) are feasible in developing multivariant models in this context. Clinical and MRI data of 58 patients with probable AD, 147 with MCI, and 94 normal controls (NCs) were collected. Baseline contourlet-based hippocampal MRI texture features, medical histories, symptoms, neuropsychological tests, volume-based morphometric (VBM) parameters based on MRI, and regional CMgl measurement based on fluorine-18 fluorodeoxyglucose-positron emission tomography were included to develop GP and PLS models to classify different groups of subjects. GPR1 model, which incorporated MRI texture features and was based on GPG, performed better in classifying different groups of subjects than GPR2 model, which used the same algorithm and had the same data as GPR1 except that MRI texture features were excluded. PLS model, which included the same variables as GPR1 but was based on the PLS algorithm, performed best among the three models. GPR1 accurately predicted 82.2% (51/62) of MCI convertors confirmed during the 2-year follow-up period, while this figure was 53 (85.5%) for PLS model. GPR1 and PLS models accurately predicted 58 (79.5%) vs. 61 (83.6%) of 73 patients with stable MCI, respectively. For seven patients with MCI who converted to NCs, PLS model accurately predicted all cases (100%), while GPR1 predicted six (85.7%) cases. The addition of contourlet-based MRI texture features to multivariant models can effectively improve the classification of AD and the prediction of MCI conversion to AD. Both GPR and LPS models performed well in the classification and predictive process, with the latter having significantly higher classification and predictive accuracies. Advances in knowledge: We combined contourlet-based hippocampal MRI texture features, medical histories, symptoms, neuropsychological tests, volume-based morphometric (VBM) parameters, and regional CMgl measurement to develop models using GP and PLS algorithms to classify AD patients.

MCI Conversion Prediction Based on Transfer Learning

Amnestic mild cognitive impairment (MCI) commonly represents an intermediate stage situated in the spectrum between normal age-related cognitive decline and dementia. Predicting of MCI conversion to Alzheimer’s Disease (AD) plays critical roles in early diagnosis and disease-modifying therapies. We analyzed baseline 3T MRI scans in 337 MCI patients from the ADNI-GO and ANDI-2 cohorts. The subjects were divided into MCI non-converters (MCInc) and MCI converters (MCIc). To evaluate conversion rates, we aim to first extract intermediate representations of structural MRI (sMRI) by a pre-trained convolutional neural network (CNN) model, then combine principal component analysis (PCA) and sequential feature selection (SFS) for feature selection, and finally adopt support vector machine (SVM) for prediction. The method attained an accuracy of 77.58%, a sensitivity of 90.48%, a specificity of 76.42%, which may be useful and practical for clinical diagnosis.

Morphological Biomarker Differentiating MCI Converters from Nonconverters: Longitudinal Evidence Based on Hemispheric Asymmetry.

Identifying subjects with mild cognitive impairment (MCI) who may probably progress to Alzheimer's disease (AD) is important for better understanding the disease mechanisms and facilitating early treatments. In addition to the direct volumetric and thickness measurement based on high-resolution magnetic resonance imaging (MRI), hemispheric asymmetry could be a potential index to detect morphological variations in MCI patients with a high risk of conversion to AD. The present study collected a set of longitudinal MRI data from 53 MCI converters and nonconverters and investigated the asymmetry differences between groups. Asymmetry variation was observed in the medial temporal lobe, especially in the entorhinal cortex, between converters and nonconverters 3 years before the former developed AD. The proposed asymmetry analysis was observed to be sensitive to detect morphological changes between groups as compared to the methods of voxel-based morphometry (VBM) and thickness measurement. Hemispheric asymmetry in specific brain regions as a neuroimaging biomarker can provide helpful information for prediction of MCI conversion.

Temporal Correlation Structure Learning for MCI Conversion Prediction.

In Alzheimer's research, Mild Cognitive Impairment (MCI) is an important intermediate stage between normal aging and Alzheimer's. How to distinguish MCI samples that finally convert to AD from those do not is an essential problem in the prevention and diagnosis of Alzheimer's. Traditional methods use various classification models to distinguish MCI converters from non-converters, while the performance is usually limited by the small number of available data. Moreover, previous methods only use the data at baseline time for training but ignore the longitudinal information at other time points along the disease progression. To tackle with these problems, we propose a novel deep learning framework that uncovers the temporal correlation structure between adjacent time points in the disease progression. We also construct a generative framework to learn the inherent data distribution so as to produce more reliable data to strengthen the training process. Extensive experiments on the ADNI cohort validate the superiority of our model.

A sequential tree-based classifier for personalized biomarker testing of Alzheimer's disease risk

ABSTRACTUsing baseline biomarkers to predict the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD) has considerable clinical interest in recent years. The existing studies have several limitations, including unsatisfactory accuracy due to MCI heterogeneity, use of conventional classification models that require biomarkers to be measured all at once instead of sequentially and as needed, and use of raw numerical measurement of the biomarkers instead of discretized levels that are more robust to measurement errors and provide convenience for clinical utilization. To tackle these limitations, we propose a novel sequence tree-based classifier (STC) for predicting the conversion of MCI to AD. Different from conventional classification models, STC achieves a sequential, as-needed use of biomarkers and a three-category classification (high-risk converter, low-risk converter, and inconclusive diagnosis) by finding an optimal sequence of biomarkers and two-sided cutoffs of each biomarker that satisfy pre-specified accuracy requirements while minimizing the proportion of inconclusive diagnosis. STC is also a personalized approach, as it allows patient characteristic variables to be included to help identify patient-specific cutoffs for each biomarker. We apply STC to two important clinical applications using the data from the worldwide Alzheimer's Disease Neuroimaging Initiative project: prediction of MCI conversion and patient selection for AD-related clinical trials.

Domain Transfer Learning for MCI Conversion Prediction.

Machine learning methods have successfully been used to predict the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD), by classifying MCI converters (MCI-C) from MCI nonconverters (MCI-NC). However, most existing methods construct classifiers using data from one particular target domain (e.g., MCI), and ignore data in other related domains (e.g., AD and normal control (NC)) that may provide valuable information to improve MCI conversion prediction performance. To address is limitation, we develop a novel domain transfer learning method for MCI conversion prediction, which can use data from both the target domain (i.e., MCI) and auxiliary domains (i.e., AD and NC). Specifically, the proposed method consists of three key components: 1) a domain transfer feature selection component that selects the most informative feature-subset from both target domain and auxiliary domains from different imaging modalities; 2) a domain transfer sample selection component that selects the most informative sample-subset from the same target and auxiliary domains from different data modalities; and 3) a domain transfer support vector machine classification component that fuses the selected features and samples to separate MCI-C and MCI-NC patients. We evaluate our method on 202 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) that have MRI, FDG-PET, and CSF data. The experimental results show the proposed method can classify MCI-C patients from MCI-NC patients with an accuracy of 79.4%, with the aid of additional domain knowledge learned from AD and NC.

Multimodal manifold-regularized transfer learning for MCI conversion prediction.

As the early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) has high chance to convert to AD. Effective prediction of such conversion from MCI to AD is of great importance for early diagnosis of AD and also for evaluating AD risk pre-symptomatically. Unlike most previous methods that used only the samples from a target domain to train a classifier, in this paper, we propose a novel multimodal manifold-regularized transfer learning (M2TL) method that jointly utilizes samples from another domain (e.g., AD vs. normal controls (NC)) as well as unlabeled samples to boost the performance ofthe MCI conversion prediction. Specifically, the proposed M2TL method includes two key components. The first one is a kernel-based maximum mean discrepancy criterion, which helps eliminate the potential negative effect induced by the distributional difference between the auxiliary domain (i.e., AD and NC) and the target domain (i.e., MCI converters (MCI-C) and MCI non-converters (MCI-NC)). The second one is a semi-supervised multimodal manifold-regularized least squares classification method, where the target-domain samples, the auxiliary-domain samples, and the unlabeled samples can be jointly used for training our classifier. Furthermore, with the integration of a group sparsity constraint into our objective function, the proposed M2TL has a capability of selecting the informative samples to build a robust classifier. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database validate the effectiveness of the proposed method by significantly improving the classification accuracy of 80.1% for MCI conversion prediction, and also outperforming the state-of-the-art methods.

Automated analysis of FDG PET as a tool for single-subject probabilistic prediction and detection of Alzheimer’s disease dementia

To introduce, evaluate and validate a voxel-based analysis method of ¹⁸F-FDG PET imaging for determining the probability of Alzheimer's disease (AD) in a particular individual. The subject groups for model derivation comprised 80 healthy subjects (HS), 36 patients with mild cognitive impairment (MCI) who converted to AD dementia within 18 months, 85 non-converter MCI patients who did not convert within 24 months, and 67 AD dementia patients with baseline FDG PET scan were recruited from the AD Neuroimaging Initiative (ADNI) database. Additionally, baseline FDG PET scans from 20 HS, 27 MCI and 21 AD dementia patients from our institutional cohort were included for model validation. The analysis technique was designed on the basis of the AD-related hypometabolic convergence index adapted for our laboratory-specific context (AD-PET index), and combined in a multivariable model with age and gender for AD dementia detection (AD score). A logistic regression analysis of different cortical PET indexes and clinical variables was applied to search for relevant predictive factors to include in the multivariable model for the prediction of MCI conversion to AD dementia (AD-Conv score). The resultant scores were stratified into sixtiles for probabilistic diagnosis. The area under the receiver operating characteristic curve (AUC) for the AD score detecting AD dementia in the ADNI database was 0.879, and the observed probability of AD dementia in the six defined groups ranged from 8% to 100% in a monotonic trend. For predicting MCI conversion to AD dementia, only the posterior cingulate index, Mini-Mental State Examination (MMSE) score and apolipoprotein E4 genotype (ApoE4) exhibited significant independent effects in the univariable and multivariable models. When only the latter two clinical variables were included in the model, the AUC was 0.742 (95% CI 0.646 - 0.838), but this increased to 0.804 (95% CI 0.714 - 0.894, bootstrap p=0.027) with the addition of the posterior cingulate index (AD-Conv score). Baseline clinical diagnosis of MCI showed 29.7% of converters after 18 months. The observed probability of conversion in relation to baseline AD-Conv score was 75% in the high probability group (sixtile 6), 34% in the medium probability group (merged sixtiles 4 and 5), 20% in the low probability group (sixtile 3) and 7.5% in the very low probability group (merged sixtiles 1 and 2). In the validation population, the AD score reached an AUC of 0.948 (95% CI 0.625 - 0.969) and the AD-Conv score reached 0.968 (95% CI 0.908 - 1.000), with AD patients and MCI converters included in the highest probability categories. Posterior cingulate hypometabolism, when combined in a multivariable model with age and gender as well as MMSE score and ApoE4 data, improved the determination of the likelihood of patients with MCI converting to AD dementia compared with clinical variables alone. The probabilistic model described here provides a new tool that may aid in the clinical diagnosis of AD and MCI conversion.

CSF and Brain Structural Imaging Markers of the Alzheimer's Pathological Cascade

Cerebral spinal fluid (CSF) and structural imaging markers are suggested as biomarkers amended to existing diagnostic criteria of mild cognitive impairment (MCI) and Alzheimer's disease (AD). But there is no clear instruction on which markers should be used at which stage of dementia. This study aimed to first investigate associations of the CSF markers as well as volumes and shapes of the hippocampus and lateral ventricles with MCI and AD at the baseline and secondly apply these baseline markers to predict MCI conversion in a two-year time using the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Our results suggested that the CSF markers, including Aβ42, t-tau, and p-tau, distinguished MCI or AD from NC, while the Aβ42 CSF marker contributed to the differentiation between MCI and AD. The hippocampal shapes performed better than the hippocampal volumes in classifying NC and MCI, NC and AD, as well as MCI and AD. Interestingly, the ventricular volumes were better than the ventricular shapes to distinguish MCI or AD from NC, while the ventricular shapes showed better accuracy than the ventricular volumes in classifying MCI and AD. As the CSF markers and the structural markers are complementary, the combination of them showed great improvements in the classification accuracies of MCI and AD. Moreover, the combination of these markers showed high sensitivity but low specificity for predicting conversion from MCI to AD in two years. Hence, it is feasible to employ a cross-sectional sample to investigate dynamic associations of the CSF and imaging markers with MCI and AD and to predict future MCI conversion. In particular, the volumetric information may be good for the early stage of AD, while morphological shapes should be considered as markers in the prediction of MCI conversion to AD together with the CSF markers.

Automated hippocampal shape analysis predicts the onset of dementia in mild cognitive impairment

The hippocampus is involved at the onset of the neuropathological pathways leading to Alzheimer's disease (AD). Individuals with mild cognitive impairment (MCI) are at increased risk of AD. Hippocampal volume has been shown to predict which MCI subjects will convert to AD. Our aim in the present study was to produce a fully automated prognostic procedure, scalable to high throughput clinical and research applications, for the prediction of MCI conversion to AD using 3D hippocampal morphology. We used an automated analysis for the extraction and mapping of the hippocampus from structural magnetic resonance scans to extract 3D hippocampal shape morphology, and we then applied machine learning classification to predict conversion from MCI to AD. We investigated the accuracy of prediction in 103 MCI subjects (mean age 74.1 years) from the longitudinal AddNeuroMed study. Our model correctly predicted MCI conversion to dementia within a year at an accuracy of 80% (sensitivity 77%, specificity 80%), a performance which is competitive with previous predictive models dependent on manual measurements. Categorization of MCI subjects based on hippocampal morphology revealed more rapid cognitive deterioration in MMSE scores ( p < 0.01) and CERAD verbal memory ( p < 0.01) in those subjects who were predicted to develop dementia relative to those predicted to remain stable. The pattern of atrophy associated with increased risk of conversion demonstrated initial degeneration in the anterior part of the cornus ammonis 1 (CA1) hippocampal subregion. We conclude that automated shape analysis generates sensitive measurements of early neurodegeneration which predates the onset of dementia and thus provides a prognostic biomarker for conversion of MCI to AD.

Morphological Factor Estimation via High‐Dimensional Reduction: Prediction of MCI Conversion to Probable AD

We propose a novel morphological factor estimate from structural MRI for disease state evaluation. We tested this methodology in the context of Alzheimer's disease (AD) with 349 subjects. The method consisted in (a) creating a reference MRI feature eigenspace using intensity and local volume change data from 149 healthy, young subjects; (b) projecting MRI data from 75 probable AD, 76 controls (CTRL), and 49 Mild Cognitive Impairment (MCI) in that space; (c) extracting high-dimensional discriminant functions; (d) calculating a single morphological factor based on various models. We used this methodology in leave-one-out experiments to (1) confirm the superiority of an inverse-squared model over other approaches; (2) obtain accuracy estimates for the discrimination of probable AD from CTRL (90%) and the prediction of conversion of MCI subjects to probable AD (79.4%).

Prediction of conversion from mild cognitive impairment to Alzheimer's disease dementia based upon biomarkers and neuropsychological test performance

The current study tested the accuracy of primary MRI and cerebrospinal fluid (CSF) biomarker candidates and neuropsychological tests for predicting the conversion from mild cognitive impairment (MCI) to Alzheimer's disease (AD) dementia. In a cross-validation paradigm, predictor models were estimated in the training set of AD (N = 81) and elderly control subjects (N = 101). A combination of CSF t-tau/Aβ1-4 ratio and MRI biomarkers or neuropsychological tests (free recall and trail making test B (TMT-B)) showed the best statistical fit in the AD vs. HC comparison, reaching a classification accuracy of up to 64% when applied to the prediction of MCI conversion (3.3-year observation interval, mean = 2.3 years). However, several single-predictor models showed a predictive accuracy of MCI conversion comparable to that of any multipredictor model. The best single predictors were right entorhinal cortex (prediction accuracy = 68.5% (95% CI (59.5, 77.4))) and TMT-B test (prediction accuracy 64.6% (95% CI (55.5, 73.4%))). In conclusion, short-term conversion to AD is predicted by single marker models to a comparable degree as by multimarker models in amnestic MCI subjects.

Diagnosing prodromal Alzheimer's disease: Role of CSF biochemical markers

Mild cognitive impairment (MCI) is an aetiologically heterogeneous syndrome. A correct prediction of MCI conversion to Alzheimer's disease (AD) represents a primary goal in routine clinical practice. Since the presence of pathological levels in ≥2 cerebrospinal fluid (CSF) biomarkers; amyloid protein (Aβ42), total tau (h-tau) and phospho-tau (p-tau) seems to reliably identifying MCI subjects converting to AD, we report our experience in a routine clinical setting. In the period from January 2001 to June 2003, 273 consecutive patients referred to our Memory Clinic for diagnostic assessment of cognitive impairment. Of them, 180 underwent a complete diagnostic evaluation including CSF dosage of fragment 1–42 of amyloid protein, total tau and phospho-tau (ELISA Method, Innogenetics, Gent, Belgium), after vascular or other secondary causes of dementia could be excluded. At baseline, 38% of the MCI subjects (20/55) showed pathological levels in ≥2 CSF biomarkers. After 1 year, 11 MCI patients converted to dementia, 33 remained stable, 11 showed a further progression of cognitive impairment still not fulfilling the diagnostic criteria for dementia. Of the 11 converters, 10 showed ≥2 pathological values CSF biomarkers and in all of them, p-tau was high. On the contrary, 29 out of 33 stable MCI (88%) showed no or one pathological CSF value. We confirm that pathological levels in ≥2 CSF biomarkers reliably predict MCI conversion to AD and correctly identify the stable form of MCI.