Stable Mild Cognitive Impairment Research Articles

Multi-auxiliary domain transfer learning for diagnosis of MCI conversion.

In the early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) has a higher risk of progression to AD, so the prediction of whether an MCI subject will progress to AD (known as progressive MCI, PMCI) or not (known as stable MCI, SMCI) within a certain period is particularly important in practice. It is known that such a task could benefit from jointly learning-related auxiliary tasks such as differentiating AD from PMCI or PMCI from normal control (NC) in order to take full advantage of their shared commonality. However, few existing methods along this line fully consider the correlations between the target and auxiliary tasks according to the clinical practice of AD pathology for diagnosis. To deal with this problem, in this paper, treating each task domain as a different one, we borrow the idea from transfer learning and propose a novel multi-auxiliary domain transfer learning (MaDTL) method, which explicitly utilizes the correlations between the target domain (task) and multi-auxiliary domains (tasks) according to the clinical practice. Specifically, the proposed MaDTL method incorporates two key modules. The first one is a multi-auxiliary domain transfer-based feature selection (MaDTFS) model, which can select a discriminative feature subset shared by the target domain and the multi-auxiliary domains. In the MaDTFS model, to combine more training data from multi-auxiliary domains and simultaneously suppress the negative effects resulting from the irrelevant parts of multi-auxiliary domains, we proposed a sparse group correlation Lasso that includes a proposed group correlation Lasso penalty (i.e., [Formula: see text]) and a proposed correlation Lasso penalty (i.e., [Formula: see text]). The second module in MaDTL is a multi-auxiliary domain transfer-based classification (MaDTC) model that improves the voting with linear weighting-based ensemble learning. This model extends the constraints of the linear weighting method so that it can simultaneously combine training data from multi-auxiliary domains and achieve a robust classifier by minimizing negative effects from the irrelevant part of multi-auxiliary domains. Experimental results on 409 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database with the baseline magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) data validate the effectiveness of the proposed method by significantly improving the classification accuracy to 80.37% for the identification of MCI-to-AD conversion, outperforming the state-of-the-art methods.

Relation between Alpha-Synuclein and Core CSF Biomarkers of Alzheimer's Disease.

Background: Alzheimer’s disease (AD) is characterized by the presence of β-amyloid plaques and neurofibrillary tangles, while Lewy body dementia (LBD) is characterized by α-synuclein (α-syn) inclusions. Some authors examine α-syn protein in the neurodegeneration process of AD and propose to consider cerebrospinal fluid (CSF) α-syn as a possible additional biomarker to the so-called “core” of AD. Objective: To determine whether there is a correlation between α-syn levels and “core” AD biomarkers in patients with mild cognitive impairment (MCI). Materials and methods: In total, 81 patients in the early stages of MCI were selected from the outpatient dementia consultation in Alicante General Hospital. Using a cross-sectional case–control design, patients were analyzed in four groups: stable MCI (MCIs; n = 25), MCI due to AD (MCI-AD; n = 32), MCI due to LBD (MCI-LBD; n = 24) and a control group of patients with acute or chronic headache (Ctrl; n = 18). Correlation between CSF protein levels in the different groups was assessed by the Rho Spearman test. Results: We found positive correlations between T-tau protein and α-syn (ρ = 0.418; p value < 0.05) and p-tau181p and α-syn (ρ = 0.571; p value < 0.05) exclusively in the MCI-AD group. Conclusion: The correlation found between α-syn and tau proteins in the first stages of AD support the involvement of α-syn in the pathogenesis of AD. This result may have clinical and diagnostic implications, as well as help to apply the new concept of “precision medicine” in patients with MCI.

Biomarker Extraction Based on Subspace Learning for the Prediction of Mild Cognitive Impairment Conversion.

Accurate recognition of progressive mild cognitive impairment (MCI) is helpful to reduce the risk of developing Alzheimer's disease (AD). However, it is still challenging to extract effective biomarkers from multivariate brain structural magnetic resonance imaging (MRI) features to accurately differentiate the progressive MCI from stable MCI. We develop novel biomarkers by combining subspace learning methods with the information of AD as well as normal control (NC) subjects for the prediction of MCI conversion using multivariate structural MRI data. Specifically, we first learn two projection matrices to map multivariate structural MRI data into a common label subspace for AD and NC subjects, where the original data structure and the one-to-one correspondence between multiple variables are kept as much as possible. Afterwards, the multivariate structural MRI features of MCI subjects are mapped into a common subspace according to the projection matrices. We then perform the self-weighted operation and weighted fusion on the features in common subspace to extract the novel biomarkers for MCI subjects. The proposed biomarkers are tested on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Experimental results indicate that our proposed biomarkers outperform the competing biomarkers on the discrimination between progressive MCI and stable MCI. And the improvement from the proposed biomarkers is not limited to a particular classifier. Moreover, the results also confirm that the information of AD and NC subjects is conducive to predicting conversion from MCI to AD. In conclusion, we find a good representation of brain features from high-dimensional MRI data, which exhibits promising performance for predicting conversion from MCI to AD.

Synaptic Molecular and Neurophysiological Markers Are Independent Predictors of Progression in Alzheimer's Disease.

Background:Cerebrospinal fluid (CSF) neurogranin and quantitative electroencephalography (qEEG) are potential molecular and functional markers of synaptic pathology in Alzheimer’s disease (AD). Synaptic markers have emerged as candidate prognostic indicators of AD since synaptic degeneration was shown to be an early event and the best correlate of cognitive deficits in patients along the disease continuum.Objective:The present study investigated the association between CSF neurogranin and qEEG measures as well as their potential to predict clinical deterioration in mild cognitive impairment (MCI) patients.Methods:Patients diagnosed with MCI (n = 99) underwent CSF conventional AD biomarkers and neurogranin analysis and resting-state EEG recordings. The study population was further stratified into stable (n = 41) and progressive MCI (n = 31), based on the progression to AD dementia during two years follow-up. qEEG analysis included computation of global field power and global field synchronization in four conventional frequency bands.Results:CSF neurogranin levels were associated with theta power and synchronization in the progressive MCI group. CSF neurogranin and qEEG measures were significant predictors of progression to AD dementia, independent of baseline amyloid status in MCI patients. A combination of CSF neurogranin with global EEG power in theta and global EEG synchronization in beta band exhibited the highest classification accuracy as compared to either of these markers alone.Conclusion:qEEG and CSF neurogranin are independent predictors of progression to AD dementia in MCI patients. Molecular and neurophysiological synaptic markers may have additive value in a multimodal diagnostic and prognostic approach to dementia.

The Transition of Mild Cognitive Impairment Over Time: An AV45- and FDG-PET Study of Reversion and Conversion Phenomena.

Mild cognitive impairment (MCI) is a state between normal cognition and dementia. However, MCI diagnosis does not necessarily guarantee the progression to dementia. Since no previous study investigated brain positron emission tomography (PET) imaging of MCI-- to-normal reversion, we provided PET imaging of MCI- to-normal reversion using the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We applied comprehensive neuropsychological criteria (NP criteria), consisting of memory, language, and attention/executive function domains, to include patients with a baseline diagnosis of MCI (n=613). According to the criteria, the year 1 status of the patients was categorized into three groups (reversion: n=105, stable MCI: n=422, conversion: n=86). Demographic, neuropsychological, genetic, CSF, and cognition biomarker variables were compared between the groups. Additionally, after adjustment for confounding variables, the deposition pattern of amyloid-β and cerebral glucose metabolism were compared between three groups via AV45- and FDG-PET modalities, respectively. MCI reversion rate was 17.1% during one year of follow-up. The reversion group had the lowest frequency of APOE ε4+ subjects, the highest CSF level of amyloid-β, and the lowest CSF levels of t-tau and p-tau. Neuropsychological assessments were also suggestive of better cognitive performance in the reversion group. Patients with reversion to normal state had higher glucose metabolism in bilateral angular and left middle/inferior temporal gyri, when compared to those with stable MCI state. Meanwhile, lower amyloid-β deposition at baseline was observed in the frontal and parietal regions of the reverted subjects. On the other hand, the conversion group showed lower cerebral glucose metabolism in bilateral angular and bilateral middle/inferior temporal gyri compared to the stable MCI group, whereas the amyloid-β accumulation was similar between the groups. This longitudinal study provides novel insight regarding the application of PET imaging in predicting MCI transition over time.

Differential Role for Hippocampal Subfields in Alzheimer's Disease Progression Revealed with Deep Learning.

Mild cognitive impairment (MCI) is often considered the precursor of Alzheimer's disease. However, MCI is associated with substantially variable progression rates, which are not well understood. Attempts to identify the mechanisms that underlie MCI progression have often focused on the hippocampus but have mostly overlooked its intricate structure and subdivisions. Here, we utilized deep learning to delineate the contribution of hippocampal subfields to MCI progression. We propose a dense convolutional neural network architecture that differentiates stable and progressive MCI based on hippocampal morphometry with an accuracy of 75.85%. A novel implementation of occlusion analysis revealed marked differences in the contribution of hippocampal subfields to the performance of the model, with presubiculum, CA1, subiculum, and molecular layer showing the most central role. Moreover, the analysis reveals that 10.5% of the volume of the hippocampus was redundant in the differentiation between stable and progressive MCI.

Specific White Matter Tracts and Diffusion Properties Predict Conversion From Mild Cognitive Impairment to Alzheimer's Disease.

Identifying biomarkers that can assess the risk of developing Alzheimer’s Disease (AD) remains a significant challenge. In this study, we investigated the integrity levels of brain white matter in 34 patients with mild cognitive impairment (MCI) who later converted to AD and 53 stable MCI patients. We used diffusion tensor imaging (DTI) and automated fiber quantification to obtain the diffusion properties of 20 major white matter tracts. To identify which tracts and diffusion measures are most relevant to AD conversion, we used support vector machines (SVMs) to classify the AD conversion and non-conversion MCI patients based on the diffusion properties of each tract individually. We found that diffusivity measures from seven white matter tracts were predictive of AD conversion with axial diffusivity being the most predictive diffusion measure. Additional analyses revealed that white matter changes in the central and parahippocampal terminal regions of the right cingulate hippocampal bundle, central regions of the right inferior frontal occipital fasciculus, and posterior and anterior regions of the left inferior longitudinal fasciculus were the best predictors of conversion from MCI to AD. An SVM based on these white matter tract regions achieved an accuracy of 0.75. These findings provide additional potential biomarkers of AD risk in MCI patients.

Amyloid and tau positive mild cognitive impairment: clinical and biomarker characteristics of dementia progression.

Background:According to the amyloid, tau, neurodegeneration research framework classification, amyloid and tau positive (A+T+) mild cognitive impairment (MCI) individuals are defined as prodromal Alzheimer disease. This study was designed to compare the clinical and biomarker features between A+T+MCI individuals who progressed to progressive MCI (pMCI) and those who remained stable MCI (sMCI), and to identify relevant baseline clinical biomarker and features that could be used to predict progression to dementia within 2 years.Methods:We stratified 197 A+T+MCI individuals into pMCI (n = 64) and sMCI (n = 133) over 2 years. Demographics and cognitive assessment scores, cerebrospinal fluid (CSF), and neuroimaging biomarkers (18F-florbetapir positron emission tomography mean standardized uptake value ratios [SUVR] and structural magnetic resonance imaging [MRI]) were compared between pMCI and sMCI at baseline, 12- and 24-month follow-up. Logistic regression models then were used to evaluate clinical baseline and biomarker features that predicted dementia progression in A+T+MCI.Results:pMCI individuals had higher mean 18F-florbetapir SUVR, CSF total-tau (t-tau), and p-tau181P than those in sMCI individuals. pMCI individuals performed poorer in cognitive assessments, both global and domain specific (memory, executive, language, attention, and visuospatial skills) than sMCI. At baseline, there were significant differences in regions of interest of structural MRI between the two groups, including bilateral amygdala, hippocampus and entorhinal, bilateral inferior lateral ventricle, left superior and middle temporal, left posterior and caudal anterior cingulate (P < 0.05). Baseline CSF t-tau levels and cognitive scores of Montreal cognitive assessment, functional assessment questionnaire, and everyday cognition by the patient's study partner language domain could predict progression to dementia in A+T+MCI within 2 years.Conclusions:In future clinical trials, specific CSF and cognitive measures that predict dementia progression in A+T+MCI might be useful risk factors for assessing the risk of dementia progression.

Inter-Cohort Validation of SuStaIn Model for Alzheimer's Disease.

Alzheimer’s disease (AD) is a neurodegenerative disorder which spans several years from preclinical manifestations to dementia. In recent years, interest in the application of machine learning (ML) algorithms to personalized medicine has grown considerably, and a major challenge that such models face is the transferability from the research settings to clinical practice. The objective of this work was to demonstrate the transferability of the Subtype and Stage Inference (SuStaIn) model from well-characterized research data set, employed as training set, to independent less-structured and heterogeneous test sets representative of the clinical setting. The training set was composed of MRI data of 1043 subjects from the Alzheimer’s disease Neuroimaging Initiative (ADNI), and the test set was composed of data from 767 subjects from OASIS, Pharma-Cog, and ViTA clinical datasets. Both sets included subjects covering the entire spectrum of AD, and for both sets volumes of relevant brain regions were derived from T1-3D MRI scans processed with Freesurfer v5.3 cross-sectional stream. In order to assess the predictive value of the model, subpopulations of subjects with stable mild cognitive impairment (MCI) and MCIs that progressed to AD dementia (pMCI) were identified in both sets. SuStaIn identified three disease subtypes, of which the most prevalent corresponded to the typical atrophy pattern of AD. The other SuStaIn subtypes exhibited similarities with the previously defined hippocampal sparing and limbic predominant atrophy patterns of AD. Subject subtyping proved to be consistent in time for all cohorts and the staging provided by the model was correlated with cognitive performance. Classification of subjects on the basis of a combination of SuStaIn subtype and stage, mini mental state examination and amyloid-β1-42 cerebrospinal fluid concentration was proven to predict conversion from MCI to AD dementia on par with other novel statistical algorithms, with ROC curves that were not statistically different for the training and test sets and with area under curve respectively equal to 0.77 and 0.76. This study proves the transferability of a SuStaIn model for AD from research data to less-structured clinical cohorts, and indicates transferability to the clinical setting.

Enhanced detection of cortical atrophy in Alzheimer's disease using structural MRI with anatomically constrained longitudinal registration.

Cortical atrophy is a defining feature of Alzheimer's disease (AD), often detectable before symptoms arise. In surface‐based analyses, studies have commonly focused on cortical thinning while overlooking the impact of loss in surface area. To capture the impact of both cortical thinning and surface area loss, we used anatomically constrained Multimodal Surface Matching (aMSM), a recently developed tool for mapping change in surface area. We examined cortical atrophy over 2 years in cognitively normal subjects and subjects with diagnoses of stable mild cognitive impairment, mild cognitive impairment that converted to AD, and AD. Magnetic resonance imaging scans were segmented and registered to a common atlas using previously described techniques (FreeSurfer and ciftify), then longitudinally registered with aMSM. Changes in cortical thickness, surface area, and volume were mapped within each diagnostic group, and groups were compared statistically. Changes in thickness and surface area detected atrophy at similar levels of significance, though regions of atrophy somewhat differed. Furthermore, we found that surface area maps offered greater consistency across scanners (3.0 vs. 1.5 T). Comparisons to the FreeSurfer longitudinal pipeline and parcellation‐based (region‐of‐interest) analysis suggest that aMSM may allow more robust detection of atrophy, particularly in earlier disease stages and using smaller sample sizes.

A predictive framework based on brain volume trajectories enabling early detection of Alzheimer's disease.

We present a framework for constructing predictive models of cognitive decline from longitudinal MRI examinations, based on mixed effects models and machine learning. We apply the framework to detect conversion from cognitively normal (CN) to mild cognitive impairment (MCI) and from MCI to Alzheimer's disease (AD), using a large collection of subjects sourced from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Australian Imaging, Biomarkers and Lifestyle Flagship Study of Aging (AIBL). We extract subcortical segmentation and cortical parcellation from corresponding T1-weighted images using FreeSurfer v.6.0, select bilateral 3D regions of interest relevant to neurodegeneration/dementia, and fit their longitudinal volume trajectories using linear mixed effects models. Features describing these model-based trajectories are then used to train an ensemble of machine learning classifiers to distinguish stable CN from converters to MCI, and stable MCI from converters to AD. On separate test sets the models achieved an average of accuracy/precision/recall score of 69/73/60% for converted to MCI and 75/74/77% for converted to AD, illustrating the framework's ability to extract predictive imaging-based biomarkers from routine T1-weighted MRI acquisitions.

Different Inflammatory Signatures in Alzheimer's Disease and Frontotemporal Dementia Cerebrospinal Fluid.

Background:Neuroinflammatory processes are common in neurodegenerative diseases such as Alzheimer’s disease (AD) and frontotemporal dementia (FTD), but current knowledge is limited as to whether cerebrospinal fluid (CSF) levels of neuroinflammatory proteins are altered in these diseases.Objective:To identify and characterize neuroinflammatory signatures in CSF from patients with AD, mild cognitive impairment (MCI), and FTD.Methods:We used proximity extension assay and ANOVA to measure and compare levels of 92 inflammatory proteins in CSF from 42 patients with AD, 29 with MCI due to AD (MCI/AD), 22 with stable MCI, 42 with FTD, and 49 control subjects, correcting for age, gender, collection unit, and multiple testing.Results:Levels of matrix metalloproteinase-10 (MMP-10) were increased in AD, MCI/AD, and FTD compared with controls (AD: fold change [FC] = 1.32, 95% confidence interval [CI] 1.14–1.53, q = 0.018; MCI/AD: FC = 1.53, 95% CI 1.20–1.94, q = 0.045; and FTD: FC = 1.42, 95% CI 1.10–1.83, q = 0.020). MMP-10 and eleven additional proteins were increased in MCI/AD, compared with MCI (q < 0.05). In FTD, 36 proteins were decreased, while none was decreased in AD or MCI/AD, compared with controls (q < 0.05).Conclusion:In this cross-sectional multi-center study, we found distinct patterns of CSF inflammatory marker levels in FTD and in both early and established AD, suggesting differing neuroinflammatory processes in the two disorders.

Plasma glial fibrillary acidic protein detects Alzheimer pathology and predicts future conversion to Alzheimer dementia in patients with mild cognitive impairment

IntroductionPlasma glial fibrillary acidic protein (GFAP) is a marker of astroglial activation and astrocytosis. We assessed the ability of plasma GFAP to detect Alzheimer’s disease (AD) pathology in the form of AD-related amyloid-β (Aβ) pathology and conversion to AD dementia in a mild cognitive impairment (MCI) cohort.MethodOne hundred sixty MCI patients were followed for 4.7 years (average). AD pathology was defined using cerebrospinal fluid (CSF) Aβ42/40 and Aβ42/total tau (T-tau). Plasma GFAP was measured at baseline and follow-up using Simoa technology.ResultsBaseline plasma GFAP could detect abnormal CSF Aβ42/40 and CSF Aβ42/T-tau with an AUC of 0.79 (95% CI 0.72–0.86) and 0.80 (95% CI 0.72–0.86), respectively. When also including APOE ε4 status as a predictor, the accuracy of the model to detect abnormal CSF Aβ42/40 status improved (AUC = 0.86, p = 0.02). Plasma GFAP predicted subsequent conversion to AD dementia with an AUC of 0.84 (95% CI 0.77–0.91), which was not significantly improved when adding APOE ε4 or age as predictors to the model. Longitudinal GFAP slopes for Aβ-positive and MCI who progressed to dementia (AD or other) were significantly steeper than those for Aβ-negative (p = 0.007) and stable MCI (p < 0.0001), respectively.ConclusionPlasma GFAP can detect AD pathology in patients with MCI and predict conversion to AD dementia.

Spatial correlation maps of the hippocampus with cerebrospinal fluid biomarkers and cognition in Alzheimer's disease: A longitudinal study.

This study is an observational study that takes the existing longitudinal data from Alzheimer's disease Neuroimaging Initiative to examine the spatial correlation map of hippocampal subfield atrophy with CSF biomarkers and cognitive decline in the course of AD. This study included 421 healthy controls (HC), 557 patients of stable mild cognitive impairment (s‐MCI), 304 Alzheimer's Disease (AD) patients, and 241 subjects who converted to be AD from MCI (c‐MCI), and 6,525 MRI scans in a period from 2004 to 2019. Our findings revealed that all the hippocampal subfields showed their accelerated atrophy rate from cognitively normal aging to stable MCI and AD. The presubiculum, dentate gyrus, and fimbria showed greater atrophy beyond the whole hippocampus in the HC, s‐MCI, and AD groups and corresponded to a greater decline of memory and attention in the s‐MCI group. Moreover, the higher atrophy rates of the subiculum and CA2/3, CA4 were also associated with a greater decline in attention in the s‐MCI group. Interestingly, patients with c‐MCI showed that the presubiculum atrophy was associated with CSF tau levels and corresponded to the onset age of AD and a decline in attention in patients with c‐MCI. These spatial correlation findings of the hippocampus suggested that the hippocampal subfields may not be equally impacted by normal aging, MCI, and AD, and their atrophy was selectively associated with declines in specific cognitive domains. The presubiculum atrophy was highlighted as a surrogate marker for the AD prognosis along with tau pathology and attention decline.

An Explainable 3D Residual Self-Attention Deep Neural Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI.

Computer-aided early diagnosis of Alzheimer's disease (AD) and its prodromal form mild cognitive impairment (MCI) based on structure Magnetic Resonance Imaging (sMRI) has provided a cost-effective and objective way for early prevention and treatment of disease progression, leading to improved patient care. In this work, we have proposed a novel computer-aided approach for early diagnosis of AD by introducing an explainable 3D Residual Attention Deep Neural Network (3D ResAttNet) for end-to-end learning from sMRI scans. Different from the existing approaches, the novelty of our approach is three-fold: 1) A Residual Self-Attention Deep Neural Network has been proposed to capture local, global and spatial information of MR images to improve diagnostic performance; 2) An explainable method using Gradient-based Localization Class Activation mapping (Grad-CAM) has been introduced to improve the interpretability of the proposed method; 3) This work has provided a full end-to-end learning solution for automated disease diagnosis. Our proposed 3D ResAttNet method has been evaluated on a large cohort of subjects from real datasets for two changeling classification tasks (i.e. Alzheimer's disease (AD) vs. Normal cohort (NC) and progressive MCI (pMCI) vs. stable MCI (sMCI)). The experimental results show that the proposed approach has a competitive advantage over the state-of-the-art models in terms of accuracy performance and generalizability. The explainable mechanism in our approach is able to identify and highlight the contribution of the important brain parts (e.g., hippocampus, lateral ventricle and most parts of the cortex) for transparent decisions.

Biological Features of Reversion from Mild Cognitive Impairment to Normal Cognition: A Study of Cerebrospinal Fluid Markers and Brain Volume.

Background:Mild cognitive impairment (MCI) is a transitional condition between normal cognition and dementia. Although a significant proportion of the population with MCI experience reversion to normal cognition, it is still poorly understood.Objective:This study was designed to extend the present evidence regarding the difference between stable and reverting MCI by including whole brain atrophy measures as possible parameters involved.Methods:405 patients diagnosed with MCI at baseline were selected. After one-year follow-up period, 337 patients (83.2%) were categorized as stable MCI and 68 patients (16.8%) reverted to cognitively normal status (reversion group). Several baseline biomarkers including cerebrospinal fluid (CSF) biomarkers of AD, including Aβ42, t-tau, and p-tau and MRI-based atrophy measurements were compared.Results:Participants with stable MCI demonstrated greater brain atrophy as well as lower Aβ and higher tau proteins in the CSF. The atrophy rate was found to be associated with CSF biomarkers merely in the stable group, after adjustment for confounding variables.Conclusion:These findings provide novel evidence regarding the biological perspective of the reversion phenomenon in individuals with MCI.

A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer\u2019s disease

Alzheimer’s disease (AD) is the most common type of dementia. Its diagnosis and progression detection have been intensively studied. Nevertheless, research studies often have little effect on clinical practice mainly due to the following reasons: (1) Most studies depend mainly on a single modality, especially neuroimaging; (2) diagnosis and progression detection are usually studied separately as two independent problems; and (3) current studies concentrate mainly on optimizing the performance of complex machine learning models, while disregarding their explainability. As a result, physicians struggle to interpret these models, and feel it is hard to trust them. In this paper, we carefully develop an accurate and interpretable AD diagnosis and progression detection model. This model provides physicians with accurate decisions along with a set of explanations for every decision. Specifically, the model integrates 11 modalities of 1048 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) real-world dataset: 294 cognitively normal, 254 stable mild cognitive impairment (MCI), 232 progressive MCI, and 268 AD. It is actually a two-layer model with random forest (RF) as classifier algorithm. In the first layer, the model carries out a multi-class classification for the early diagnosis of AD patients. In the second layer, the model applies binary classification to detect possible MCI-to-AD progression within three years from a baseline diagnosis. The performance of the model is optimized with key markers selected from a large set of biological and clinical measures. Regarding explainability, we provide, for each layer, global and instance-based explanations of the RF classifier by using the SHapley Additive exPlanations (SHAP) feature attribution framework. In addition, we implement 22 explainers based on decision trees and fuzzy rule-based systems to provide complementary justifications for every RF decision in each layer. Furthermore, these explanations are represented in natural language form to help physicians understand the predictions. The designed model achieves a cross-validation accuracy of 93.95% and an F1-score of 93.94% in the first layer, while it achieves a cross-validation accuracy of 87.08% and an F1-Score of 87.09% in the second layer. The resulting system is not only accurate, but also trustworthy, accountable, and medically applicable, thanks to the provided explanations which are broadly consistent with each other and with the AD medical literature. The proposed system can help to enhance the clinical understanding of AD diagnosis and progression processes by providing detailed insights into the effect of different modalities on the disease risk.

Cognitive and MRI trajectories for prediction of Alzheimer\u2019s disease

The concept of Mild Cognitive Impairment (MCI) is used to describe the early stages of Alzheimer’s disease (AD), and identification and treatment before further decline is an important clinical task. We selected longitudinal data from the ADNI database to investigate how well normal function (HC, n= 134) vs. conversion to MCI (cMCI, n= 134) and stable MCI (sMCI, n=333) vs. conversion to AD (cAD, n= 333) could be predicted from cognitive tests, and whether the predictions improve by adding information from magnetic resonance imaging (MRI) examinations. Features representing trajectories of change in the selected cognitive and MRI measures were derived from mixed effects models and used to train ensemble machine learning models to classify the pairs of subgroups based on a subset of the data set. Evaluation in an independent test set showed that the predictions for HC vs. cMCI improved substantially when MRI features were added, with an increase in F_1-score from 60 to 77%. The F_1-scores for sMCI vs. cAD were 77% without and 78% with inclusion of MRI features. The results are in-line with findings showing that cognitive changes tend to manifest themselves several years after the Alzheimer’s disease is well-established in the brain.

Hippocampal shape and asymmetry analysis by cascaded convolutional neural networks for Alzheimer's disease diagnosis.

Hippocampal atrophy is often considered as one of the important biomarkers for early diagnosis of Alzheimer's disease (AD), which is an irreversible neurodegenerative disorder. Traditional methods for hippocampus analysis usually computed the shape and volume features from structural Magnetic Resonance Image (sMRI) for the computer-aided diagnosis of AD as well as its prodromal stage, i.e., mild cognitive impairment (MCI). Motivated by the success of deep learning, this paper proposes a deep learning method with the multi-channel cascaded convolutional neural networks (CNNs) to gradually learn the combined hierarchical representations of hippocampal shapes and asymmetries from the binary hippocampal masks for AD classification. First, image segmentation is performed to generate the bilateral hippocampus binary masks for each subject and the mask difference is obtained by subtracting them. Second, multi-channel 3D CNNs are individually constructed on the hippocampus masks and mask differences to extract features of hippocampal shapes and asymmetries for classification. Third, a 2D CNN is cascaded on the 3D CNNs to learn high-level correlation features. Finally, the features learned by multi-channel and cascaded CNNs are combined with a fully connected layer followed by a softmax classifier for disease classification. The proposed method can gradually learn the combined hierarchical features of hippocampal shapes and asymmetries to enhance the classification. Our method is verified on the baseline sMRIs from 807 subjects including 194AD patients, 397 MCI (164 progressive MCI (pMCI) + 233 stable MCI (sMCI)), and 216 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Experimental results demonstrate that the proposed method achieves an AUC (Area Under the ROC Curve) of 88.4%, 74.6% and 71.9% for AD vs. NC, MCI vs. NC and pMCI vs. sMCI classifications, respectively. It proves the promising classification performance and also shows that both hippocampal shape and asymmetry are helpful for AD diagnosis.

A Survey on Classification Algorithms of Brain Images in Alzheimer’s Disease Based on Feature Extraction Techniques

Alzheimer’s disease (AD) is one of the most serious neurological disorders for elderly people. AD affected patient experiences severe memory loss. One of the main reasons for memory loss in AD patients is atrophy in the hippocampus, amygdala, etc. Due to the enormous growth of AD patients and the paucity of proper diagnostic tools, detection and classification of AD are considered as a challenging research area. Before a Cognitively normal (CN) person develops symptoms of AD, he may pass through an intermediate stage, commonly known as Mild Cognitive Impairment (MCI). MCI is having two stages, namely StableMCI (SMCI) and Progressive MCI (PMCI). In SMCI, a patient remains stable, whereas, in the case of PMCI, a person gradually develops few symptoms of AD. Several research works are in progress on the detection and classification of AD based on changes in the brain. In this paper, we have analyzed few existing state-of-art works for AD detection and classification, based on different feature extraction approaches. We have summarized the existing research articles with detailed observations. We have also compared the performance and research issues in each of the feature extraction mechanisms and observed that the AD classification using the wavelet transform-based feature extraction approaches might achieve convincing results.