Whole-brain analysis reveals increased neuroanatomical asymmetries in dementia for hippocampus and amygdala

Association of birthweight and risk of incident dementia: a prospective cohort study

Given the epidemiological studies investigating the relationship between birthweight and dementia are limited. Our study aimed to explore the association between birthweight and the risk of dementia, cognitive function, and brain structure. We included 275,648 participants from the UK Biobank, categorizing birthweight into quartiles (Q1 ≤ 2.95 kg; Q2 > 2.95 kg, ≤ 3.32 kg; Q3 > 3.32 kg, ≤ 3.66 kg; Q4 > 3.66 kg), with Q3 as the reference. Cox regression models and restricted cubic splines estimated the relationship between birthweight and the risk of all causes of dementia (ACD), Alzheimer's disease (AD), and vascular dementia (VD). Multivariable linear regression models assessed the relationship between birthweight, cognitive function, and MRI biomarkers. Over a median follow-up of 13.0 years, 3103 incident dementia cases were recorded. In the fully adjusted model, compared to Q3 (> 3.32 kg, ≤ 3.66 kg), lower birthweight in Q1 (≤ 2.95 kg) was significantly associated with increased risk of ACD (HR = 1.18, 95%CI 1.06-1.30, P = 0.001) and VD (HR = 1.32, 95%CI 1.07-1.62, P = 0.010), but no significant association with AD was found. Continuous birthweight showed a U-shaped nonlinear association with dementia. Lower birthweight was associated with worse performance in cognitive tasks, including reaction time, fluid intelligence, numeric, and prospective memory. Additionally, certain brain structure indices were identified, including brain atrophy and reductions in area, thickness, and volume of regional subcortical areas. Our study emphasizes the association between lower birthweight and increased dementia risk, correlating cognitive function and MRI biomarkers of brain structure, suggesting that in utero or early-life exposures might impact cognitive health in adulthood.

A multiscale characterization of cortical shape asymmetries in early psychosis

Psychosis has often been linked to abnormal cortical asymmetry, but prior results have been inconsistent. Here, we applied a novel spectral shape analysis to characterize cortical shape asymmetries in patients with early psychosis across different spatial scales. We used the Human Connectome Project for Early Psychosis dataset (aged 16-35), comprising 56 healthy controls (37 males, 19 females) and 112 patients with early psychosis (68 males, 44 females). We quantified shape variations of each hemisphere over different spatial frequencies and applied a general linear model to compare differences between healthy controls and patients with early psychosis. We further used canonical correlation analysis to examine associations between shape asymmetries and clinical symptoms. Cortical shape asymmetries, spanning wavelengths from about 22 to 75 mm, were significantly different between healthy controls and patients with early psychosis (Cohen's d = 0.28-0.51), with patients showing greater asymmetry in cortical shape than controls. A single canonical mode linked the asymmetry measures to symptoms (canonical correlation analysis r = 0.45), such that higher cortical asymmetry was correlated with more severe excitement symptoms and less severe emotional distress. Significant group differences in the asymmetries of traditional morphological measures of cortical thickness, surface area, and gyrification, at either global or regional levels, were not identified. Cortical shape asymmetries are more sensitive than other morphological asymmetries in capturing abnormalities in patients with early psychosis. These abnormalities are expressed at coarse spatial scales and are correlated with specific symptom domains.

Examining Frontal Lobe Asymmetry and Its Potential Role in Aggressive Behaviors in Early Alzheimer's Disease

Background

Neuropsychiatric symptoms (NPS) in patients with dementia lead to caregiver burdens and worsen the patient's prognosis. Although many neuroimaging studies have been conducted, the etiology of NPS remains complex. We hypothesize that brain structural asymmetry could play a role in the appearance of NPS.

Objective

This study explores the relationship between NPS and brain asymmetry in patients with Alzheimer's disease (AD).

Methods

Demographic and MRI data for 121 mild AD cases were extracted from a multicenter Japanese database. Brain asymmetry was assessed by comparing the volumes of gray matter in the left and right brain regions. NPS was evaluated using the Neuropsychiatric Inventory (NPI). Subsequently, a comprehensive assessment of the correlation between brain asymmetry and NPS was conducted.

Results

Among each NPS, aggressive NPS showed a significant correlation with asymmetry in the frontal lobe, indicative of right-side atrophy (r = 0.235, p = 0.009). This correlation remained statistically significant even after adjustments for multiple comparisons (p < 0.01). Post-hoc analysis further confirmed this association (p < 0.05). In contrast, no significant correlations were found for other NPS subtypes, including affective and apathetic symptoms.

Conclusions

The study suggests frontal lobe asymmetry, particularly relative atrophy in the right hemisphere, may be linked to aggressive behaviors in early AD. These findings shed light on the neurobiological underpinnings of NPS, contributing to the development of potential interventions.

DeepHipp: accurate segmentation of hippocampus using 3D dense-block based on attention mechanism

BACKGROUND

The hippocampus is a key area of the brain responsible for learning, memory, and other abilities. Accurately segmenting the hippocampus and precisely calculating the volume of the hippocampus is of great significance for predicting Alzheimer's disease and amnesia. Most of the segmentation algorithms currently involved are based on templates, such as the more popular FreeSufer.

METHODS

This study proposes Deephipp, a deep learning network based on a 3D dense block using an attention mechanism for accurate segmentation of the hippocampus. DeepHipp is based on the following novelties: (i) DeepHipp adopts powerful data augmentation schemes to enhance the segmentation ability. (ii) DeepHipp is designed to incorporate 3D dense-block to capture multiple-scale features of the hippocampus. (iii) DeepHipp creatively uses the attention mechanism in the field of hippocampal image segmentation, extracting useful hippocampus information in a massive feature map, and improving the accuracy and sensitivity of the model.

CONCLUSIONS

We describe the illustrative results and show extensive qualitative and quantitative comparisons with other methods. Our achievement demonstrates that the accuracy of DeepHipp can reach 83.63%, which is superior to most existing methods in terms of accuracy and efficiency of hippocampus segmentation. It is noticeable that deep learning can potentially lead to an effective segmentation of medical images.

Atrophy of specific amygdala subfields in subjects converting to mild cognitive impairment

Introduction

Accumulating evidence indicates that the amygdala exhibits early signs of Alzheimer's disease (AD) pathology. However, it is still unknown whether the atrophy of distinct subfields of the amygdala also participates in the transition from healthy cognition to mild cognitive impairment (MCI).

Methods

Our sample was derived from the AD Neuroimaging Initiative 3 and consisted of 97 cognitively healthy (HC) individuals, sorted into two groups based on their clinical follow-up: 75 who remained stable (s-HC) and 22 who converted to MCI within 48 months (c-HC). Anatomical magnetic resonance (MR) images were analyzed using a semi-automatic approach that combines probabilistic methods and a priori information from ex vivo MR images and histology to segment and obtain quantitative structural metrics for different amygdala subfields in each participant. Spearman's correlations were performed between MR measures and baseline and longitudinal neuropsychological measures. We also included anatomical measurements of the whole amygdala, the hippocampus, a key target of AD-related pathology, and the whole cortical thickness as a test of spatial specificity.

Results

Compared with s-HC individuals, c-HC subjects showed a reduced right amygdala volume, whereas no significant difference was observed for hippocampal volumes or changes in cortical thickness. In the amygdala subfields, we observed selected atrophy patterns in the basolateral nuclear complex, anterior amygdala area, and transitional area. Macro-structural alterations in these subfields correlated with variations of global indices of cognitive performance (measured at baseline and the 48-month follow-up), suggesting that amygdala changes shape the cognitive progression to MCI.

Discussion

Our results provide anatomical evidence for the early involvement of the amygdala in the preclinical stages of AD.

Highlights

Amygdala's atrophy marks elderly progression to mild cognitive impairment (MCI).Amygdala's was observed within the basolateral and amygdaloid complexes.Macro-structural alterations were associated with cognitive decline.No atrophy was found in the hippocampus and cortex.

NORHA: A NORmal Hippocampal Asymmetry Deviation Index Based on One-Class Novelty Detection and 3D Shape Features

Radiologists routinely analyze hippocampal asymmetries in magnetic resonance (MR) images as a biomarker for neurodegenerative conditions like epilepsy and Alzheimer's Disease. However, current clinical tools rely on either subjective evaluations, basic volume measurements, or disease-specific models that fail to capture more complex differences in normal shape. In this paper, we overcome these limitations by introducing NORHA, a novel NORmal Hippocampal Asymmetry deviation index that uses machine learning novelty detection to objectively quantify it from MR scans. NORHA is based on a One-Class Support Vector Machine model learned from a set of morphological features extracted from automatically segmented hippocampi of healthy subjects. Hence, in test time, the model automatically measures how far a new unseen sample falls with respect to the feature space of normal individuals. This avoids biases produced by standard classification models, which require being trained using diseased cases and therefore learning to characterize changes produced only by the ones. We evaluated our new index in multiple clinical use cases using public and private MRI datasets comprising control individuals and subjects with different levels of dementia or epilepsy. The index reported high values for subjects with unilateral atrophies and remained low for controls or individuals with mild or severe symmetric bilateral changes. It also showed high AUC values for discriminating individuals with hippocampal sclerosis, further emphasizing its ability to characterize unilateral abnormalities. Finally, a positive correlation between NORHA and the functional cognitive test CDR-SB was observed, highlighting its promising application as a biomarker for dementia.

Mesiotemporal Volumetry, Cortical Thickness, and Neuropsychological Deficits in the Long-term Course of Limbic Encephalitis

BACKGROUND AND OBJECTIVES

Limbic encephalitis (LE) is an autoimmune disease often associated with temporal lobe epilepsy and subacute memory deficits. It is categorized into serologic subgroups, which differ in clinical progress, therapy response, and prognosis. Using longitudinal MRI analysis, we hypothesized that mesiotemporal and cortical atrophy rates would reveal serotype-specific patterns and reflect disease severity.

METHODS

In this longitudinal case-control study, all individuals with antibody-positive (glutamic acid decarboxylase 65 [GAD], leucine-rich glioma-inactivated protein 1 [LGI1], contactin-associated protein 2 [CASPR2], and N-methyl-d-aspartate receptor [NMDAR]) nonparaneoplastic LE according to Graus' diagnostic criteria treated between 2005 and 2019 at the University Hospital Bonn were enrolled. A longitudinal healthy cohort was included as the control group. Subcortical segmentation and cortical reconstruction of T1-weighted MRI were performed using the longitudinal framework in FreeSurfer. We applied linear mixed models to examine mesiotemporal volumes and cortical thickness longitudinally.

RESULTS

Two hundred fifty-seven MRI scans from 59 individuals with LE (34 female, age at disease onset [mean ± SD] 42.5 ± 20.4 years; GAD: n = 30, 135 scans; LGI1: n = 15, 55 scans; CASPR2: n = 9, 37 scans; and NMDAR: n = 5, 30 scans) were included. The healthy control group consisted of 128 scans from 41 individuals (22 female, age at first scan [mean ± SD] 37.7 ± 14.6 years). The amygdalar volume at disease onset was significantly higher in individuals with LE (p ≤ 0.048 for all antibody subgroups) compared with that in healthy controls and decreased over time in all antibody subgroups, except in the GAD subgroup. We observed a significantly higher hippocampal atrophy rate in all antibody subgroups compared with that in healthy controls (all p ≤ 0.002), except in the GAD subgroup. Cortical atrophy rates exceeded normal aging in individuals with impaired verbal memory, while those who were not impaired did not differ significantly from healthy controls.

DISCUSSION

Our data depict higher mesiotemporal volumes in the early disease stage, most likely due to edematous swelling, followed by volume regression and atrophy/hippocampal sclerosis in the late disease stage. Our study reveals a continuous and pathophysiologically meaningful trajectory of mesiotemporal volumetry across all serogroups and provides evidence that LE should be considered a network disorder in which extratemporal involvement is an important determinant of disease severity.

Towards better interpretable and generalizable AD detection using collective artificial intelligence

Alzheimer's Disease is the most common cause of dementia. Accurate diagnosis and prognosis of this disease are essential to design an appropriate treatment plan, increasing the life expectancy of the patient. Intense research has been conducted on the use of machine learning to identify Alzheimer's Disease from neuroimaging data, such as structural magnetic resonance imaging. In recent years, advances of deep learning in computer vision suggest a new research direction for this problem. Current deep learning-based approaches in this field, however, have a number of drawbacks, including the interpretability of model decisions, a lack of generalizability information and a lower performance compared to traditional machine learning techniques. In this paper, we design a two-stage framework to overcome these limitations. In the first stage, an ensemble of 125 U-Nets is used to grade the input image, producing a 3D map that reflects the disease severity at voxel-level. This map can help to localize abnormal brain areas caused by the disease. In the second stage, we model a graph per individual using the generated grading map and other information about the subject. We propose to use a graph convolutional neural network classifier for the final classification. As a result, our framework demonstrates comparative performance to the state-of-the-art methods in different datasets for both diagnosis and prognosis. We also demonstrate that the use of a large ensemble of U-Nets offers a better generalization capacity for our framework.

Functional re-organization of hippocampal-cortical gradients during naturalistic memory processes

The functional organization of the hippocampus mirrors that of the cortex, changing smoothly along connectivity gradients and abruptly at inter-areal boundaries. Hippocampal-dependent cognitive processes require flexible integration of these hippocampal gradients into functionally related cortical networks. To understand the cognitive relevance of this functional embedding, we acquired fMRI data while participants viewed brief news clips, either containing or lacking recently familiarized cues. Participants were 188 healthy mid-life adults and 31 adults with mild cognitive impairment (MCI) or Alzheimer's disease (AD). We employed a recently developed technique - connectivity gradientography - to study gradually changing patterns of voxel to whole brain functional connectivity and their sudden transitions. We observed that functional connectivity gradients of the anterior hippocampus map onto connectivity gradients across the default mode network during these naturalistic stimuli. The presence of familiar cues in the news clips accentuates a stepwise transition across the boundary from the anterior to the posterior hippocampus. This functional transition is shifted in the posterior direction in the left hippocampus of individuals with MCI or AD. These findings shed new light on the functional integration of hippocampal connectivity gradients into large-scale cortical networks, how these adapt with memory context and how these change in the presence of neurodegenerative disease.

Hippocampus shape characterization with 3D Zernike transformation in clinical Alzheimer's disease progression

Alzheimer's disease (AD) is a neurodegenerative disease and the most common cause of dementia among older adults. Mild cognitive impairment (MCI) is considered a transitional phase between healthy cognitive aging and dementia. Progressive brain volume reduction/atrophy, particularly of the hippocampus, is associated with the transition from normal to MCI, and then to AD. We aimed to develop methods to characterize the shape of hippocampus and explore its potential as an imaging marker to monitor clinical AD progression. We implemented a 3D Zernike transformation to characterize the shape changes of hippocampus in 428 older subjects with high-quality T1 -weighted volumetric brain scans from the Alzheimer's Disease Neuroimaging Initiative data set (151 normal, 258 MCI, and 19 AD). Over 2 years, 15 cognitively normal subjects converted to MCI, and 42 subjects with MCI converted to AD. We found a significant correlation between hippocampal volume changes and Zernike shape metrics. Before a clinical diagnosis of AD, the shapes of the left and right hippocampi changed slowly. After AD diagnosis, both volume and shape changed rapidly but were uncorrelated to each other. During the transition from a clinical diagnosis of MCI to AD, the shape of the left and right hippocampi changed in a correlated manner but became uncorrelated after AD diagnosis. Finally, the pace of hippocampus shape change was associated with its shape and the subject's age and disease condition. In conclusion, the hippocampus shape features characterized with 3D Zernike transformation, in complement to volume measures, may serve as a novel imaging marker to monitor clinical AD progression.

Subcortical brain structures and the risk of dementia in the Rotterdam Study

INTRODUCTION

Volumetric and morphological changes in subcortical brain structures are present in persons with dementia, but it is unknown if these changes occur prior to diagnosis.

METHODS

Between 2005 and 2016, 5522 Rotterdam Study participants (mean age: 64.4) underwent cerebral magnetic resonance imaging (MRI) and were followed for development of dementia until 2018. Volume and shape measures were obtained for seven subcortical structures.

RESULTS

During 12 years of follow-up, 272 dementia cases occurred. Mean volumes of thalamus (hazard ratio [HR] per standard deviation [SD] decrease 1.94, 95% confidence interval [CI]: 1.55-2.43), amygdala (HR 1.66, 95% CI: 1.44-1.92), and hippocampus (HR 1.64, 95% CI: 1.43-1.88) were strongly associated with dementia risk. Associations for accumbens, pallidum, and caudate volumes were less pronounced. Shape analyses identified regional surface changes in the amygdala, limbic thalamus, and caudate.

DISCUSSION

Structure of the amygdala, thalamus, hippocampus, and caudate is associated with risk of dementia in a large population-based cohort of older adults.

A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images

Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (N_rmC) but, it still requires a lot of work to be done for MCI/ N_rmC and MCI/AD, which would help in detecting AD at its early stage.

Coupling Between Hippocampal Parenchymal Fraction and Cortical Grey Matter Atrophy at Different Stages of Cognitive Decline

BACKGROUND

Hippocampal atrophy is a significant brain marker of pathology in Alzheimer's disease (AD). The hippocampal parenchymal fraction (HPF) was recently developed to better assess the hippocampal volumetric integrity, and it has been shown to be a sensitive measure of hippocampal atrophy in AD.

OBJECTIVE

To investigate the clinical relevance of hippocampal volumetric integrity as measured by the HPF and the coupling between the HPF and brain atrophy during AD progression.

METHODS

We included data from 143 cognitively normal (CN), 101 mild cognitive impairment (MCI), and 125 AD participants. We examined group differences in the HPF, associations between HPF and cognitive ability, and coupling between the HPF and cortical grey matter volume in the CN, MCI, and AD groups.

RESULTS

We observed progressive decreases in HPF from CN to MCI and from MCI to AD, and increases in the asymmetry of HPF, with the lowest asymmetry index (AI) in the CN group and the highest AI in the AD group. There was a significant association between HPF and cognitive ability across participants. The coupling between HPF and cortical regions was observed in bilateral hippocampus, parahippocampal gyrus, temporal, frontal, and occipital regions, thalamus, and amygdala in CN, MCI, and AD groups, with a greater involvement of temporal, occipital, frontal, and subcortical regions in MCI and AD patients, especially in AD patients.

CONCLUSION

This study provides novel evidence for the neuroanatomical basis of cognitive decline and brain atrophy during AD progression, which may have important clinical implications for the prognosis of AD.

Longitudinal Assessment of Intravoxel Incoherent Motion Diffusion-Weighted MRI Metrics in Cognitive Decline

BACKGROUND

Advanced diffusion-based MRI biomarkers may provide insight into microstructural and perfusion changes associated with neurodegeneration and cognitive decline.

PURPOSE

To assess longitudinal microstructural and perfusion changes using apparent diffusion coefficient (ADC) and intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) parameters in cognitively impaired (CI) and healthy control (HC) groups.

STUDY TYPE

Prospective/longitudinal.

POPULATION

Twelve CI patients (75% female) and 13 HC subjects (69% female).

FIELD STRENGTH/SEQUENCE

3 T; Spin-Echo-IVIM-DWI.

ASSESSMENT

Two MRI scans were performed with a 12-month interval. ADC and IVIM-DWI metrics (diffusion coefficient [D] and perfusion fraction [f]) were generated from monoexponential and biexponential fits, respectively. Additionally, voxel-based correlations were evaluated between change in Montreal Cognitive Assessment (ΔMoCA) and baseline imaging parameters.

STATISTICAL TESTS

Analysis of covariance with sex and age as covariates was performed for main effects of group and time (false discovery rate [FDR] corrected) with post hoc comparisons using Bonferroni correction. Partial-η² and Hedges' g were used for effect-size analysis. Spearman's correlations (FDR corrected) were used for the relationship between ΔMoCA score and imaging. P < 0.05 was considered statistically significant.

RESULTS

Significant differences were found for the main effects of group (HC vs. CI) and time. For group effects, higher ADC, IVIM-D, and IVIM-f were observed in the CI group compared to HC (ADC: 1.23 ± 0.08^. 10^-3 vs. 1.09 ± 0.07^. 10^-3  mm² /sec; IVIM-D: 0.82 ± 0.01^. 10^-3 vs. 0.73 ± 0.01^. 10^-3  mm² /sec; and IVIM-f: 0.317 ± 0.008 vs. 0.253 ± 0.009). Significantly higher ADC, IVIM-D, and IVIM-f values were observed in the CI group after 12 months (ADC: 1.45 ± 0.05^. 10^-3 vs. 1.50 ± 0.07^. 10^-3  mm² /sec; IVIM-D: 0.87 ± 0.01^. 10^-3 vs. 0.94 ± 0.02^. 10^-3  mm² /sec; and IVIM-f: 0.303 ± 0.007 vs. 0.332 ± 0.008), but not in the HC group at large effect size. ADC, IVIM-D, and IVIM-f negatively correlated with ΔMoCA score (ρ = -0.49, -0.51, and -0.50, respectively).

DATA CONCLUSION

These findings demonstrate that longitudinal differences between CI and HC cohorts can be measured using IVIM-based metrics.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY STAGE: 2.

Brain white matter hyperintensity lesion characterization in 3D T2 fluid-attenuated inversion recovery magnetic resonance images: Shape, texture, and their correlations with potential growth

Analyses of age-related white matter hyperintensity (WMH) lesions manifested in T2 fluid-attenuated inversion recovery (FLAIR) magnetic resonance images (MRI) have been mostly on understanding the size and location of the WMH lesions and rarely on the morphological characterization of the lesions. This work extends our prior analyses of the morphological characteristics and texture of WMH from 2D to 3D based on 3D T2 FLAIR images. 3D Zernike transformation was used to characterize WMH shape; a fuzzy logic method was used to characterize the lesion texture. We then clustered 3D WMH lesions into groups based on their 3D shape and texture features. A potential growth index (PGI) to assess dynamic changes in WMH lesions was developed based on the image texture features of the WMH lesion penumbra. WMH lesions with various sizes were segmented from brain images of 32 cognitively normal older adults. The WMH lesions were divided into two groups based on their size. Analyses of Variance (ANOVAs) showed significant differences in PGI among WMH shape clusters (P = 1.57 × 10-3 for small lesions; P = 3.14 × 10-2 for large lesions). Significant differences in PGI were also found among WMH texture group clusters (P = 1.79 × 10-6). In conclusion, we presented a novel approach to characterize the morphology of 3D WMH lesions and explored the potential to assess the dynamic morphological changes of WMH lesions using PGI.

Predicting future cognitive decline from non-brain and multimodal brain imaging data in healthy and pathological aging

Previous literature has focused on predicting a diagnostic label from structural brain imaging. Since subtle changes in the brain precede a cognitive decline in healthy and pathological aging, our study predicts future decline as a continuous trajectory instead. Here, we tested whether baseline multimodal neuroimaging data improve the prediction of future cognitive decline in healthy and pathological aging. Nonbrain data (demographics, clinical, and neuropsychological scores), structural MRI, and functional connectivity data from OASIS-3 (N = 662; age = 46-96 years) were entered into cross-validated multitarget random forest models to predict future cognitive decline (measured by CDR and MMSE), on average 5.8 years into the future. The analysis was preregistered, and all analysis code is publicly available. Combining non-brain with structural data improved the continuous prediction of future cognitive decline (best test-set performance: R2 = 0.42). Cognitive performance, daily functioning, and subcortical volume drove the performance of our model. Including functional connectivity did not improve predictive accuracy. In the future, the prognosis of age-related cognitive decline may enable earlier and more effective individualized cognitive, pharmacological, and behavioral interventions.

Disease-Image-Specific Learning for Diagnosis-Oriented Neuroimage Synthesis With Incomplete Multi-Modality Data

Incomplete data problem is commonly existing in classification tasks with multi-source data, particularly the disease diagnosis with multi-modality neuroimages, to track which, some methods have been proposed to utilize all available subjects by imputing missing neuroimages. However, these methods usually treat image synthesis and disease diagnosis as two standalone tasks, thus ignoring the specificity conveyed in different modalities, i.e., different modalities may highlight different disease-relevant regions in the brain. To this end, we propose a disease-image-specific deep learning (DSDL) framework for joint neuroimage synthesis and disease diagnosis using incomplete multi-modality neuroimages. Specifically, with each whole-brain scan as input, we first design a Disease-image-Specific Network (DSNet) with a spatial cosine module to implicitly model the disease-image specificity. We then develop a Feature-consistency Generative Adversarial Network (FGAN) to impute missing neuroimages, where feature maps (generated by DSNet) of a synthetic image and its respective real image are encouraged to be consistent while preserving the disease-image-specific information. Since our FGAN is correlated with DSNet, missing neuroimages can be synthesized in a diagnosis-oriented manner. Experimental results on three datasets suggest that our method can not only generate reasonable neuroimages, but also achieve state-of-the-art performance in both tasks of Alzheimer's disease identification and mild cognitive impairment conversion prediction.

Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity

Neuroimaging‐driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model‐agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes. Results showed that the proposed brain age vector accurately reflected disorder‐specific abnormal aging patterns related to the medial temporal and the striatum for prodromal AD (sMCI vs. pMCI) and PD (healthy controls [HC] vs. prodromal PD), respectively, and demonstrated outstanding performance in early disease screening, with area under the curves of 83.39% and 72.28% in detecting pMCI and prodromal PD, respectively. In conclusion, the proposed brain age vector effectively improves spatial specificity of brain aging measurement and enables individual screening of neurodegenerative diseases.

Fitting Contralateral Neuroanatomical Asymmetry into the Amyloid Cascade Hypothesis

Alzheimer's Disease (AD) is the most common cause of dementia. Due to the progressive nature of the neurodegeneration associated with the disease, it is of clinical interest to achieve an early diagnosis of AD. In this study, we analyzed the viability of asymmetry-related measures as potential biomarkers to facilitate the early diagnosis of AD. These measures were obtained from MAPER-segmented MP-RAGE MRI studies available at the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and by analyzing these studies at the level of individual segmented regions. The temporal evolution of these measures was obtained and then analyzed by generating spline regression models. Data imputation was performed where missing information prevented the temporal analysis of each measure from being realized, using additional information provided by ADNI for each patient. The temporal evolution of these measures was compared to the evolution of other commonly used markers for the diagnosis of AD, such as cognitive function, concentrations of Phosphorylated-Tau, Amyloid-β, and structural MRI volumetry. The results of the regression models showed that asymmetry measures, in particular regions such as the parahippocampal gyrus, differentiated themselves temporally before most of the other evaluated biomarkers. Further studies are suggested to corroborate these results.

Polygenic score for Alzheimer’s disease identifies differential atrophy in hippocampal subfield volumes

Hippocampal subfield atrophy is a prime structural change in the brain, associated with cognitive aging and neurodegenerative diseases such as Alzheimer’s disease. Recent developments in genome-wide association studies (GWAS) have identified genetic loci that characterize the risk of hippocampal volume loss based on the processes of normal and abnormal aging. Polygenic risk scores are the genetic proxies mimicking the genetic role of the pre-existing vulnerabilities of the underlying mechanisms influencing these changes. Discriminating the genetic predispositions of hippocampal subfield atrophy between cognitive aging and neurodegenerative diseases will be helpful in understanding the disease etiology. In this study, we evaluated the polygenic risk of Alzheimer’s disease (AD PGRS) for hippocampal subfield atrophy in 1,086 individuals (319 cognitively normal (CN), 591 mild cognitively impaired (MCI), and 176 Alzheimer’s disease dementia (ADD)). Our results showed a stronger association of AD PGRS effect on the left hemisphere than on the right hemisphere for all the hippocampal subfield volumes in a mixed clinical population (CN+MCI+ADD). The subfields CA1, CA4, hippocampal tail, subiculum, presubiculum, molecular layer, GC-ML-DG, and HATA showed stronger AD PGRS associations with the MCI+ADD group than with the CN group. The subfields CA3, parasubiculum, and fimbria showed moderately higher AD PGRS associations with the MCI+ADD group than with the CN group. Our findings suggest that the eight subfield regions, which were strongly associated with AD PGRS are likely involved in the early stage ADD and a specific focus on the left hemisphere could enhance the early prediction of ADD.

Comparing Medial Temporal Atrophy Between Early-Onset Semantic Dementia and Early-Onset Alzheimer's Disease Using Voxel-Based Morphometry: A Multicenter MRI Study

BACKGROUND

Early-onset Semantic dementia (EOSD) and early-onset Alzheimer's disease (EOAD) are often difficult to clinically differentiate in the early stages of the diseases because of the overlaps of clinical symptoms such as language symptoms. We compared the degree of atrophy in medial temporal structures between the two types of dementia using the voxel-based specific regional analysis system for Alzheimer's disease (VSRAD).

METHODS

The participants included 29 (age: 61.7±4.5 years) and 39 (age: 60.2±4.9 years) patients with EOSD and EOAD, respectively. The degree of atrophy in medial temporal structures was quantified using the VSRAD for magnetic resonance imaging data. Receiver operating characteristic (ROC) analysis was performed to distinguish patients with EOSD and EOAD using the mean Z score (Z-score) in bilateral medial temporal structures and the absolute value (laterality score) of the laterality of Z-score (| right-left |) for indicating the degree of asymmetrical atrophy in medial temporal structures.

RESULTS

The EOSD group had significantly higher Z and laterality scores than the EOAD group (Zscores: mean ± standard deviation: 3.74±1.05 vs. 1.56±0.81, respectively; P<0.001; laterality score: mean ± standard deviation: 2.35±1.23 vs. 0.68±0.51, respectively; P<0.001). In ROC analysis, the sensitivity and specificity to differentiate EOSD from EOAD by a Z-score of 2.29 were 97% and 85%, respectively and by the laterality score of 1.05 were 93% and 85%, respectively.

CONCLUSION

EOSD leads to more severe and asymmetrical atrophy in medial temporal structures than EOAD. The VSRAD may be useful to distinguish between these dementias that have several clinically similar symptoms.

Hippocampal representations for deep learning on Alzheimer's disease

Deep learning offers a powerful approach for analyzing hippocampal changes in Alzheimer's disease (AD) without relying on handcrafted features. Nevertheless, an input format needs to be selected to pass the image information to the neural network, which has wide ramifications for the analysis, but has not been evaluated yet. We compare five hippocampal representations (and their respective tailored network architectures) that span from raw images to geometric representations like meshes and point clouds. We performed a thorough evaluation for the prediction of AD diagnosis and time-to-dementia prediction with experiments on an independent test dataset. In addition, we evaluated the ease of interpretability for each representation-network pair. Our results show that choosing an appropriate representation of the hippocampus for predicting Alzheimer's disease with deep learning is crucial, since it impacts performance and ease of interpretation.

Efficacy and Mechanism of Moxibustion Treatment on Mild Cognitive Impairment Patients: An fMRI Study Using ALFF

Background

Mild Cognitive Impairment (MCI), as a high risk of Alzheimer’s disease (AD), represents a state of cognitive function between normal aging and dementia. Moxibustion may effectively delay the progression of AD, while there is a lack of studies on the treatments in MCI. This study aimed to evaluate the effect of moxibustion treatment revealed by the amplitude of low-frequency fluctuation (ALFF) in MCI.

Method

We enrolled 30 MCI patients and 30 matched healthy controls (HCs) in this study. We used ALFF to compare the difference between MCI and HCs at baseline and the regulation of spontaneous neural activity in MCI patients by moxibustion. The Mini-Mental State Examination and Montreal Cognitive Assessment scores were used to evaluate cognitive function.

Results

Compared with HCs, the ALFF values significantly decreased in the right temporal poles: middle temporal gyrus (TPOmid), right inferior temporal gyrus, left middle cingulate gyrus, and increased in the left hippocampus, left middle temporal gyrus, right lingual gyrus, and right middle occipital gyrus in MCI patients. After moxibustion treatment, the ALFF values notably increased in the left precuneus, left thalamus, right temporal poles: middle temporal gyrus, right middle frontal gyrus, right inferior temporal gyrus, right putamen, right hippocampus, and right fusiform gyrus, while decreased in the bilateral lingual gyrus in MCI patients. The Mini-Mental State Examination and Montreal Cognitive Assessment scores increased after moxibustion treatment, and the increase in Mini-Mental State Examination score was positively correlated with the increase of ALFF value in the right TPOmid, the right insula, and the left superior temporal gyrus.

Conclusion

Moxibustion treatment might improve the cognitive function of MCI patients by modulating the brain activities within the default mode network, visual network, and subcortical network with a trend of increased ALFF values and functional asymmetry of the hippocampus. These results indicate that moxibustion holds great potential in the treatment of MCI.

Shape description and volumetry of hippocampus and amygdala in temporal lobe epilepsy - A beneficial combination with a clinical perspective

Shape-based markers have entered the field of morphometric neuroimaging analysis as a second mainstay alongside conventional volumetric approaches. We aimed to assess the added value of shape description for the analysis of lesional and autoimmune temporal lobe epilepsy (TLE) focusing on hippocampus and amygdala. We retrospectively investigated MRI and clinical data from 65 patients with lesional TLE (hippocampal sclerosis (HS) and astrogliosis) and from 62 patients with limbic encephalitis (LE) with serologically proven autoantibodies. Surface reconstruction and volumetric segmentation were performed with FreeSurfer. For the shape analysis, we used BrainPrint, a tool that utilizes eigenvalues of the Laplace-Beltrami operator on triangular meshes to calculate intra-subject asymmetry. Psychometric tests of memory performance were ascertained, to evaluate clinical relevance of the shape descriptor. The potential benefit of shape in addition to volumetric information for classification was assessed by five-fold repeated cross validation and logistic regression. For the LE group, the best performing classification model consisted of a combination of volume and shape asymmetry (mean AUC = 0.728), the logistic regression model was significantly improved considering both modalities instead of just volume asymmetry. For lesional TLE, the best model only considered volumetric information (mean AUC = 0.867). Shape asymmetry of the hippocampus was largely associated with verbal memory performance only in LE patients (OR = 1.07, p = 0.02). For lesional TLE, shape description is robust, but redundant when compared to volumetric approaches. For LE, in contrast, shape asymmetry as a complementary modality significantly improves the detection of subtle morphometric changes and is further associated with memory performance, which underscores the clinical relevance of shape asymmetry as a novel imaging biomarker.

The individuality of shape asymmetries of the human cerebral cortex

Asymmetries of the cerebral cortex are found across diverse phyla and are particularly pronounced in humans, with important implications for brain function and disease. However, many prior studies have confounded asymmetries due to size with those due to shape. Here, we introduce a novel approach to characterize asymmetries of the whole cortical shape, independent of size, across different spatial frequencies using magnetic resonance imaging data in three independent datasets. We find that cortical shape asymmetry is highly individualized and robust, akin to a cortical fingerprint, and identifies individuals more accurately than size-based descriptors, such as cortical thickness and surface area, or measures of inter-regional functional coupling of brain activity. Individual identifiability is optimal at coarse spatial scales (~37 mm wavelength), and shape asymmetries show scale-specific associations with sex and cognition, but not handedness. While unihemispheric cortical shape shows significant heritability at coarse scales (~65 mm wavelength), shape asymmetries are determined primarily by subject-specific environmental effects. Thus, coarse-scale shape asymmetries are highly personalized, sexually dimorphic, linked to individual differences in cognition, and are primarily driven by stochastic environmental influences.

Data-Driven Analyses of Longitudinal Hippocampal Imaging Trajectories: Discrimination and Biomarker Prediction of Change Classes

BACKGROUND

Hippocampal atrophy is a well-known biomarker of neurodegeneration, such as that observed in Alzheimer's disease (AD). Although distributions of hippocampal volume trajectories for asymptomatic individuals often reveal substantial heterogeneity, it is unclear whether interpretable trajectory classes can be objectively detected and used for prediction analyses.

OBJECTIVE

To detect and predict hippocampal trajectory classes in a computationally competitive context using established AD-related risk factors/biomarkers.

METHODS

We used biomarker/risk factor and longitudinal MRI data in asymptomatic adults from the AD Neuroimaging Initiative (n = 351; Mean = 75 years; 48.7% female). First, we applied latent class growth analyses to left (LHC) and right (RHC) hippocampal trajectory distributions to identify distinct classes. Second, using random forest analyses, we tested 38 multi-modal biomarkers/risk factors for their relative importance in discriminating the lower (potentially elevated atrophy risk) from the higher (potentially reduced risk) class.

RESULTS

For both LHC and RHC trajectory distribution analyses, we observed three distinct trajectory classes. Three biomarkers/risk factors predicted membership in LHC and RHC lower classes: male sex, higher education, and lower plasma Aβ1-42. Four additional factors selectively predicted membership in the lower LHC class: lower plasma tau and Aβ1-40, higher depressive symptomology, and lower body mass index.

CONCLUSION

Data-driven analyses of LHC and RHC trajectories detected three classes underlying the heterogeneous distributions. Machine learning analyses determined three common and four unique biomarkers/risk factors discriminating the higher and lower LHC/RHC classes. Our sequential analytic approach produced evidence that the dynamics of preclinical hippocampal trajectories can be predicted by AD-related biomarkers/risk factors from multiple modalities.

Deep transfer learning of structural magnetic resonance imaging fused with blood parameters improves brain age prediction

Machine learning has been applied to neuroimaging data for estimating brain age and capturing early cognitive impairment in neurodegenerative diseases. Blood parameters like neurofilament light chain are associated with aging. In order to improve brain age predictive accuracy, we constructed a model based on both brain structural magnetic resonance imaging (sMRI) and blood parameters. Healthy subjects (n = 93; 37 males; aged 50–85 years) were recruited. A deep learning network was firstly pretrained on a large set of MRI scans (n = 1,481; 659 males; aged 50–85 years) downloaded from multiple open‐source datasets, to provide weights on our recruited dataset. Evaluating the network on the recruited dataset resulted in mean absolute error (MAE) of 4.91 years and a high correlation (r = .67, p <.001) against chronological age. The sMRI data were then combined with five blood biochemical indicators including GLU, TG, TC, ApoA1 and ApoB, and 9 dementia‐associated biomarkers including ApoE genotype, HCY, NFL, TREM2, Aβ40, Aβ42, T‐tau, TIMP1, and VLDLR to construct a bilinear fusion model, which achieved a more accurate prediction of brain age (MAE, 3.96 years; r = .76, p <.001). Notably, the fusion model achieved better improvement in the group of older subjects (70–85 years). Extracted attention maps of the network showed that amygdala, pallidum, and olfactory were effective for age estimation. Mediation analysis further showed that brain structural features and blood parameters provided independent and significant impact. The constructed age prediction model may have promising potential in evaluation of brain health based on MRI and blood parameters.

Identifying individuals with Alzheimer's disease-like brains based on structural imaging in the Human Connectome Project Aging cohort

Given the difficulty in factoring out typical age effects from subtle Alzheimer's disease (AD) effects on brain structure, identification of very early, as well as younger preclinical “at‐risk” individuals has unique challenges. We examined whether age‐correction procedures could be used to better identify individuals at very early potential risk from adults who did not have any existing cognitive diagnosis. First, we obtained cross‐sectional age effects for each structural feature using data from a selected portion of the Human Connectome Project Aging (HCP‐A) cohort. After age detrending, we weighted AD structural deterioration with patterns quantified from data of the Alzheimer's Disease Neuroimaging Initiative. Support vector machine was then used to classify individuals with brains that most resembled atrophy in AD across the entire HCP‐A sample. Additionally, we iteratively adjusted the pipeline by removing individuals classified as AD‐like from the HCP‐A cohort to minimize atypical brain structural contributions to the age detrending. The classifier had a mean cross‐validation accuracy of 94.0% for AD recognition. It also could identify mild cognitive impairment with more severe AD‐specific biomarkers and worse cognition. In an independent HCP‐A cohort, 8.8% were identified as AD‐like, and they trended toward worse cognition. An “AD risk” score derived from the machine learning models also significantly correlated with cognition. This work provides a proof of concept for the potential to use structural brain imaging to identify asymptomatic individuals at young ages who show structural brain patterns similar to AD and are potentially at risk for a future clinical disorder.

Morphological classification and changes in dementia (Review)

The progressive functional decline that involves both cognitive and neuropsychiatric symptoms characteristic to dementia is one of the leading research topics. The risk for dementia is an intertwined mix between aging, genetic risk factors, and environmental influences. APOEε4, which is one of the apolipoprotein E (APOE) alleles, is the major genetic risk factor for late-onset of the most common form of dementia, Alzheimer's. Advances in machine learning have led to the development of artificial intelligence (AI) algorithms to help diagnose dementia by magnetic resonance imaging (MRI) in order to detect it in the preclinical stage. The basis of the determinations starts from the morphometry of cerebral atrophies. The present review focused on MRI techniques which are a leading tool in identifying cortical atrophy, white matter dysfunctionalities, cerebral vessel quality (as a factor for cognitive impairment) and metabolic asymmetries. In addition, a brief overview of Alzheimer's disease was presented and recent neuroimaging in the field of dementia with an emphasis on structural MR imaging and more powerful methods such as diffusion tensor imaging, quantitative susceptibility mapping, and magnetic transfer imaging were explored in order to propose a simple systematic approach for the diagnosis and treatment of dementia.

Social Networks and Cognitive Reserve: Network Structure Moderates the Association between Amygdalar Volume and Cognitive Outcomes

OBJECTIVE

The cognitive reserve hypothesis has been proposed as a key mechanism explaining the link between social networks and cognitive function but has rarely been empirically tested using neuroimaging data. This study examines whether social network attributes moderate the association between amygdalar volume and cognitive function.

METHODS

Data were from the Social Networks in Alzheimer Disease study (N=154) and Indiana Alzheimer's Disease Research Center. Social networks were measured using the PhenX Social Network Battery. Regional data from MRI (amygdalar volume; AV) were analyzed using FreeSurfer software. Cognitive function was measured using the Montreal Cognitive Assessment (MoCA) and consensus diagnosis. Linear regression analyses were conducted to test the moderating role of social networks on the association between AV and cognitive function.

RESULTS

Participants with greater ability to span multiple social roles and subgroups within their networks scored higher on the MoCA after adjusting for sociodemographic variables, depression, frequency of contact, and AV. Social networks moderated the association between AV and cognitive function.

CONCLUSIONS

Among participants who engaged in diverse and loosely connected social networks, the expected adverse cognitive effects of brain volume in regions implicated in socioemotional processing were attenuated. These findings suggest that cognitive stimulation achieved through social interaction with a diverse array of social relationships across multiple contexts may help promote cognitive reserve.

Personalised predictive modelling with brain-inspired spiking neural networks of longitudinal MRI neuroimaging data and the case study of dementia

BACKGROUND

Longitudinal neuroimaging provides spatiotemporal brain data (STBD) measurement that can be utilised to understand dynamic changes in brain structure and/or function underpinning cognitive activities. Making sense of such highly interactive information is challenging, given that the features manifest intricate temporal, causal relations between the spatially distributed neural sources in the brain.

METHODS

The current paper argues for the advancement of deep learning algorithms in brain-inspired spiking neural networks (SNN), capable of modelling structural data across time (longitudinal measurement) and space (anatomical components). The paper proposes a methodology and a computational architecture based on SNN for building personalised predictive models from longitudinal brain data to accurately detect, understand, and predict the dynamics of an individual's functional brain state. The methodology includes finding clusters of similar data to each individual, data interpolation, deep learning in a 3-dimensional brain-template structured SNN model, classification and prediction of individual outcome, visualisation of structural brain changes related to the predicted outcomes, interpretation of results, and individual and group predictive marker discovery.

RESULTS

To demonstrate the functionality of the proposed methodology, the paper presents experimental results on a longitudinal magnetic resonance imaging (MRI) dataset derived from 175 older adults of the internationally recognised community-based cohort Sydney Memory and Ageing Study (MAS) spanning 6 years of follow-up.

SIGNIFICANCE

The models were able to accurately classify and predict 2 years ahead of cognitive decline, such as mild cognitive impairment (MCI) and dementia with 95% and 91% accuracy, respectively. The proposed methodology also offers a 3-dimensional visualisation of the MRI models reflecting the dynamic patterns of regional changes in white matter hyperintensity (WMH) and brain volume over 6 years.

CONCLUSION

The method is efficient for personalised predictive modelling on a wide range of neuroimaging longitudinal data, including also demographic, genetic, and clinical data. As a case study, it resulted in finding predictive markers for MCI and dementia as dynamic brain patterns using MRI data.

Synergistic Effects of APOE and CLU May Increase the Risk of Alzheimer's Disease: Acceleration of Atrophy in the Volumes and Shapes of the Hippocampus and Amygdala

BACKGROUND

The volume loss of the hippocampus and amygdala in non-demented individuals has been reported to increase the risk of developing Alzheimer's disease (AD). Many neuroimaging genetics studies mainly focused on the individual effects of APOE and CLU on neuroimaging to understand their neural mechanisms, whereas their synergistic effects have been rarely studied.

OBJECTIVE

To assess whether APOE and CLU have synergetic effects, we investigated the epistatic interaction and combined effects of the two genetic variants on morphological degeneration of hippocampus and amygdala in the non-demented elderly at baseline and 2-year follow-up.

METHODS

Besides the widely-used volume indicator, the surface-based morphometry method was also adopted in this study to evaluate shape alterations.

RESULTS

Our results showed a synergistic effect of homozygosity for the CLU risk allele C in rs11136000 and APOEɛ4 on the hippocampal and amygdalar volumes during a 2-year follow-up. Moreover, the combined effects of APOEɛ4 and CLU C were stronger than either of the individual effects in the atrophy progress of the amygdala.

CONCLUSION

These findings indicate that brain morphological changes are caused by more than one gene variant, which may help us to better understand the complex endogenous mechanism of AD.

Diffusion-informed spatial smoothing of fMRI data in white matter using spectral graph filters

Brain activation mapping using functional magnetic resonance imaging (fMRI) has been extensively studied in brain gray matter (GM), whereas in large disregarded for probing white matter (WM). This unbalanced treatment has been in part due to controversies in relation to the nature of the blood oxygenation level-dependent (BOLD) contrast in WM and its detectability. However, an accumulating body of studies has provided solid evidence of the functional significance of the BOLD signal in WM and has revealed that it exhibits anisotropic spatio-temporal correlations and structure-specific fluctuations concomitant with those of the cortical BOLD signal. In this work, we present an anisotropic spatial filtering scheme for smoothing fMRI data in WM that accounts for known spatial constraints on the BOLD signal in WM. In particular, the spatial correlation structure of the BOLD signal in WM is highly anisotropic and closely linked to local axonal structure in terms of shape and orientation, suggesting that isotropic Gaussian filters conventionally used for smoothing fMRI data are inadequate for denoising the BOLD signal in WM. The fundamental element in the proposed method is a graph-based description of WM that encodes the underlying anisotropy observed across WM, derived from diffusion-weighted MRI data. Based on this representation, and leveraging graph signal processing principles, we design subject-specific spatial filters that adapt to a subject's unique WM structure at each position in the WM that they are applied at. We use the proposed filters to spatially smooth fMRI data in WM, as an alternative to the conventional practice of using isotropic Gaussian filters. We test the proposed filtering approach on two sets of simulated phantoms, showcasing its greater sensitivity and specificity for the detection of slender anisotropic activations, compared to that achieved with isotropic Gaussian filters. We also present WM activation mapping results on the Human Connectome Project's 100-unrelated subject dataset, across seven functional tasks, showing that the proposed method enables the detection of streamline-like activations within axonal bundles.

Signal and Texture Features from T2 Maps for the Prediction of Mild Cognitive Impairment to Alzheimer's Disease Progression

Early detection of Alzheimer's disease (AD) is crucial to preserve cognitive functions and provide the opportunity for patients to enter clinical trials. In recent years, some studies have reported that features related to the signal and texture of MRI images can be an effective biomarker of AD. To test these claims, a study was conducted using T2 maps, a sequence not previously studied, of 40 patients with mild cognitive impairment (MCI) from the Alzheimer's Disease Neuroimaging Initiative database, who either progressed to AD (18) or remained stable (22). From these maps, the mean value and absolute difference of 37 signal and texture imaging features for 40 contralateral pairs of regions were measured. We used seven machine learning methods to analyze whether, by adding these imaging features to the neuropsychological studies currently used for diagnosis, we could more accurately identify patients who will progress to AD. The predictive models improved with the addition of signal and texture features. Additionally, features related to the signal and texture of the images were much more relevant than volumetric ones. Our results suggest that contralateral signal and texture features should be further investigated as potential biomarkers for the prediction of AD.

Crossed Cerebellar Diaschisis in Alzheimer's Disease Detected by Arterial Spin-labelling Perfusion MRI

BACKGROUND

Crossed cerebellar diaschisis (CCD) is a phenomenon with depressed metabolism and hypoperfusion in the cerebellum. Using arterial spin-labelling perfusion weighted magnetic resonance imaging (ASL PWI), we investigated the frequency of CCD in patients with Alzheimer's disease (AD) and differences between patients with and without CCD.

PATIENTS AND METHODS

In patients with AD who underwent a standardized magnetic resonance imaging including ASL PWI cerebral blood flow was evaluated in the cerebellum, and brain segmentation/volumetry was performed using mdbrain (mediaire GmbH, Berlin, Germany) and FSL FIRST (Functional Magnetic Resonance Imaging of the Brain Software Library).

RESULTS

In total, 65 patients were included, and 22 (33.8%) patients were assessed as being CCD-positive. Patients with CCD had a significantly smaller whole brain volume (862.8±49.9 vs. 893.7±62.7 ml, p=0.049) as well as white matter volume (352.9±28.0 vs. 374.3±30.7, p=0.008) in comparison to patients without CCD.

CONCLUSION

It was possible to detect CCD by ASL PWI in approximately one-third of patients with AD and was associated with smaller whole brain and white matter volume.

Structural Changes in Thalamic Nuclei Across Prodromal and Clinical Alzheimer's Disease

BACKGROUND

Increasing evidence suggests that thalamic nuclei may atrophy in Alzheimer's disease (AD). We hypothesized that there will be significant atrophy of limbic thalamic nuclei associated with declining memory and cognition across the AD continuum.

OBJECTIVE

The objective of this work was to characterize volume differences in thalamic nuclei in subjects with early and late mild cognitive impairment (MCI) as well as AD when compared to healthy control (HC) subjects using a novel MRI-based thalamic segmentation technique (THOMAS).

METHODS

MPRAGE data from the ADNI database were used in this study (n = 540). Healthy control (n = 125), early MCI (n = 212), late MCI (n = 114), and AD subjects (n = 89) were selected, and their MRI data were parcellated to determine the volumes of 11 thalamic nuclei for each subject. Volumes across the different clinical subgroups were compared using ANCOVA.

RESULTS

There were significant differences in thalamic nuclei volumes between HC, late MCI, and AD subjects. The anteroventral, mediodorsal, pulvinar, medial geniculate, and centromedian nuclei were significantly smaller in subjects with late MCI and AD when compared to HC subjects. Furthermore, the mediodorsal, pulvinar, and medial geniculate nuclei were significantly smaller in early MCI when compared to HC subjects.

CONCLUSION

This work highlights nucleus specific atrophy within the thalamus in subjects with early and late MCI and AD. This is consistent with the hypothesis that memory and cognitive changes in AD are mediated by damage to a large-scale integrated neural network that extends beyond the medial temporal lobes.

Cardiac-induced cerebral pulsatility, brain structure, and cognition in middle and older-aged adults

Changes of cardiac-induced regional pulsatility can be associated with specific regions of brain volumetric changes, and these are related with cognitive alterations. Thus, mapping of cardiac pulsatility over the entire brain can be helpful to assess these relationships. A total of 108 subjects (age: 66.5 ± 8.4 years, 68 females, 52 healthy controls, 11 subjective cognitive decline, 17 impaired without complaints, 19 MCI and 9 AD) participated. The pulsatility map was obtained directly from resting-state functional MRI time-series data at 3T. Regional brain volumes were segmented from anatomical MRI. Multidomain neuropsychological battery was performed to test memory, language, attention and visuospatial construction. The Montreal Cognitive Assessment (MoCA) was also administered. The sparse partial least square (SPLS) method, which is desirable for better interpreting high-dimensional variables, was applied for the relationship between the entire brain voxels of pulsatility and 45 segmented brain volumes. A multiple holdout SPLS framework was used to optimize sparsity for assessing the pulsatility-volume relationship model and to test the reliability by fitting the models to 9 different splits of the data. We found statistically significant associations between subsets of pulsatility voxels and subsets of segmented brain volumes by rejecting the omnibus null hypothesis (any of 9 splits has p < 0.0056 (=0.05/9) with the Bonferroni correction). The pulsatility was positively associated with the lateral ventricle, choroid plexus, inferior lateral ventricle, and 3rd ventricle and negatively associated with hippocampus, ventral DC, and thalamus volumes for the first pulsatility-volume relationship. The pulsatility had an additional negative relationship with the amygdala and brain stem volumes for the second pulsatility-volume relationship. The spatial distribution of correlated pulsatility was observed in major feeding arteries to the brain regions, ventricles, and sagittal sinus. The indirect mediating pathways through the volumetric changes were statistically significant between the pulsatility and multiple cognitive measures (p < 0.01). Thus, the cerebral pulsatility, along with volumetric measurements, could be a potential marker for better understanding of pathophysiology and monitoring disease progression in age-related neurodegenerative disorders.

Detection Gap of Right-Asymmetric Neuronal Degeneration by CERAD Test Battery in Alzheimer's Disease

Objectives: Asymmetric disease characteristics on neuroimaging are common in structural and functional imaging of neurodegenerative diseases, particularly in Alzheimer‘s disease (AD). However, a standardized clinical evaluation of asymmetric neuronal degeneration and its impact on clinical findings has only sporadically been investigated for F-18-fluorodeoxyglucose positron emission tomography (F-18-FDG-PET). This study aimed to evaluate the impact of lateralized neuronal degeneration on the detection of AD by detailed clinical testing. Furthermore, we compared associations between clinical evaluation and lateralized neuronal degeneration between FDG-PET hypometabolism and hippocampal atrophy. Finally, we investigated if specific subtests show associations with lateralized neuronal degeneration.

Methods: One-hundred and forty-six patients with a clinical diagnosis of AD (age 71 ± 8) were investigated by FDG-PET and the “Consortium to Establish a Registry for Alzheimer’s disease” (CERAD) test battery. For assessment of neuronal degeneration, FDG-PET hypometabolism in brain regions typically affected in AD were graded by visual (3D-surface projections) and semiquantitative analysis. Asymmetry of the hippocampus (left-right) in magnetic resonance tomography (MRI) was rated visually by the Scheltens scale. Measures of asymmetry were calculated to quantify lateralized neuronal degeneration and asymmetry scores were subsequently correlated with CERAD.

Results: Asymmetry with left-dominant neuronal degeneration to FDG-PET was an independent predictor of cognitive impairment (visual: β = −0.288, p < 0.001; semiquantitative: β = −0.451, p < 0.001) when controlled for age, gender, years of education and total burden of neuronal degeneration, whereas hippocampal asymmetry to MRI was not (β = −0.034; p = 0.731). Direct comparison of CERAD-PET associations in cases with right- and left-lateralized neuronal degeneration estimated a detection gap of 2.7 years for right-lateralized cases. Left-hemispheric neuronal degeneration was significantly associated with the total CERAD score and multiple subscores, whereas only MMSE (semiquantitative: β = 0.429, p < 0.001) and constructional praxis (semiquantitative: β = 0.292, p = 0.008) showed significant associations with right-hemispheric neuronal degeneration.

Conclusions: Asymmetry of deteriorated cerebral glucose metabolism has a significant impact on the coupling between neuronal degeneration and cognitive function. Right dominant neuronal degeneration shows a delayed detection by global CERAD testing and requires evaluation of specific subdomains of cognitive testing.

Asymmetric thinning of the cerebral cortex across the adult lifespan is accelerated in Alzheimer's disease

Aging and Alzheimer's disease (AD) are associated with progressive brain disorganization. Although structural asymmetry is an organizing feature of the cerebral cortex it is unknown whether continuous age- and AD-related cortical degradation alters cortical asymmetry. Here, in multiple longitudinal adult lifespan cohorts we show that higher-order cortical regions exhibiting pronounced asymmetry at age ~20 also show progressive asymmetry-loss across the adult lifespan. Hence, accelerated thinning of the (previously) thicker homotopic hemisphere is a feature of aging. This organizational principle showed high consistency across cohorts in the Lifebrain consortium, and both the topological patterns and temporal dynamics of asymmetry-loss were markedly similar across replicating samples. Asymmetry-change was further accelerated in AD. Results suggest a system-wide dedifferentiation of the adaptive asymmetric organization of heteromodal cortex in aging and AD.

Sex-Dependent End-of-Life Mental and Vascular Scenarios for Compensatory Mechanisms in Mice with Normal and AD-Neurodegenerative Aging

Life expectancy decreases with aging, with cardiovascular, mental health, and neurodegenerative disorders strongly contributing to the total disability-adjusted life years. Interestingly, the morbidity/mortality paradox points to females having a worse healthy life expectancy. Since bidirectional interactions between cardiovascular and Alzheimer’s diseases (AD) have been reported, the study of this emerging field is promising. In the present work, we further explored the cardiovascular–brain interactions in mice survivors of two cohorts of non-transgenic and 3xTg-AD mice, including both sexes, to investigate the frailty/survival through their life span. Survival, monitored from birth, showed exceptionally worse mortality rates in females than males, independently of the genotype. This mortality selection provided a “survivors” cohort that could unveil brain–cardiovascular interaction mechanisms relevant for normal and neurodegenerative aging processes restricted to long-lived animals. The results show sex-dependent distinct physical (worse in 3xTg-AD males), neuropsychiatric-like and cognitive phenotypes (worse in 3xTg-AD females), and hypothalamic–pituitary–adrenal (HPA) axis activation (higher in females), with higher cerebral blood flow and improved cardiovascular phenotype in 3xTg-AD female mice survivors. The present study provides an experimental scenario to study the suggested potential compensatory hemodynamic mechanisms in end-of-life dementia, which is sex-dependent and can be a target for pharmacological and non-pharmacological interventions.

Brain Asymmetry Detection and Machine Learning Classification for Diagnosis of Early Dementia

Early identification of degenerative processes in the human brain is considered essential for providing proper care and treatment. This may involve detecting structural and functional cerebral changes such as changes in the degree of asymmetry between the left and right hemispheres. Changes can be detected by computational algorithms and used for the early diagnosis of dementia and its stages (amnestic early mild cognitive impairment (EMCI), Alzheimer’s Disease (AD)), and can help to monitor the progress of the disease. In this vein, the paper proposes a data processing pipeline that can be implemented on commodity hardware. It uses features of brain asymmetries, extracted from MRI of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, for the analysis of structural changes, and machine learning classification of the pathology. The experiments provide promising results, distinguishing between subjects with normal cognition (NC) and patients with early or progressive dementia. Supervised machine learning algorithms and convolutional neural networks tested are reaching an accuracy of 92.5% and 75.0% for NC vs. EMCI, and 93.0% and 90.5% for NC vs. AD, respectively. The proposed pipeline offers a promising low-cost alternative for the classification of dementia and can be potentially useful to other brain degenerative disorders that are accompanied by changes in the brain asymmetries.

Digging Signatures in 13-Month-Old 3xTg-AD Mice for Alzheimer's Disease and Its Disruption by Isolation Despite Social Life Since They Were Born

The severity of this pandemic's scenarios will leave significant psychological traces in low resistant and resilient individuals. Increased incidence of depression, anxiety, obsessive-compulsive disorder (OCD), and post-traumatic stress disorder has already been reported. The loss of human lives and the implementation of physical distance measures in the pandemic and post-COVID scenarios may have a greater impact on the elderly, mostly in those with dementia, as OCD and other neuropsychiatric symptoms (NPS) are quite prevalent in this population. Modeling NPS in animals relies in neuroethological perspectives since the response to new situations and traumatic events, critical for survival and adaptation to the environment, is strongly preserved in the phylogeny. In the laboratory, mice dig vigorously in deep bedding to bury food pellets or small objects they may find. This behavior, initially used to screen anxiolytic activity, was later proposed to model better meaningless repetitive and perseverative behaviors characteristic of OCD or autism spectrum disorders. Other authors found that digging can also be understood as part of the expression of the animals' general activity. In the present brief report, we studied the digging ethograms in 13-month-old non-transgenic and 3xTg-AD mice modeling normal aging and advanced Alzheimer's disease (AD), respectively. This genetic model presents AD-like cognitive dysfunction and NPS-like phenotype, with high mortality rates at this age, mostly in males. This allowed us to observe the digging pattern's disruption in a subgroup of 3xTg-AD mice that survived to their cage mates. Two digging paradigms involving different anxiogenic and contextual situations were used to investigate their behavior. The temporal course and intensity of digging were found to increase in those 3xTg-AD mice that had lost their "room partners" despite having lived in social structures since they were born. However, when tested under neophobia conditions, this behavior's incidence was low (delayed), and the temporal pattern was disrupted, suggesting worsening of this NPS-like profile. The outcomes showed that this combined behavioral paradigm unveiled distinct features of digging signatures that can be useful to study these perseverative behaviors and their interplay with anxiety states already present in the AD scenario and their worsening by naturalistic/forced isolation.

Altered Neuroanatomical Asymmetries of Subcortical Structures in Subjective Cognitive Decline, Amnestic Mild Cognitive Impairment, and Alzheimer's Disease

BACKGROUND

Individuals with subjective cognitive decline (SCD), defined by self-reported memory complaints but normal performance in objective neuropsychological tests, may be at higher risk of worsening or more frequent memory loss until conversion to Alzheimer's disease (AD) or related dementia. Asymmetry in two hemispheres is a cardinal character of human brain's structure and function, and altered brain asymmetry has also been connected with AD.

OBJECTIVE

This study aimed to determine whether the asymmetry of subcortical structures in individuals with SCD and amnestic mild cognitive impairment (aMCI) and AD patients are altered compared with normal controls (NC).

METHODS

We investigated neuroanatomical alterations in 35 SCD, 43 aMCI, and 41 AD subjects compared with 42 NC, focusing on asymmetrical changes in subcortical structures based on structural magnetic resonance images (sMRI). General linear model was conducted to test group differences, and partial correlation was used to model the interaction between asymmetry measurements and cognitive tests.

RESULTS

Individuals with SCD (lateral ventricle and cerebellum-WM), aMCI patients (lateral ventricle, pallidum, hippocampus, amygdala, accumbens, and ventral DC), and AD patients (lateral-ventricle, cerebellum-cortical pallidum, thalamus, hippocampus, amygdala, accumbens, and ventral DC) exhibited significant altered neuroanatomical asymmetries of volume, surface area, and shape compared with NC. Significant associations between shape asymmetry and neuropsychological examinations were found in the hippocampus and accumbens.

CONCLUSION

Altered neuroanatomical asymmetries of subcortical structures were significantly detected in SCD individuals and aMCI patients as well AD patients, and these specific asymmetry alterations are potential to be used as neuroimaging markers and for monitoring disease progression.

Parallels between retinal and brain pathology and response to immunotherapy in old, late-stage Alzheimer's disease mouse models

Despite growing evidence for the characteristic signs of Alzheimer's disease (AD) in the neurosensory retina, our understanding of retina-brain relationships, especially at advanced disease stages and in response to therapy, is lacking. In transgenic models of AD (APPSWE/PS1∆E9; ADtg mice), glatiramer acetate (GA) immunomodulation alleviates disease progression in pre- and early-symptomatic disease stages. Here, we explored the link between retinal and cerebral AD-related biomarkers, including response to GA immunization, in cohorts of old, late-stage ADtg mice. This aged model is considered more clinically relevant to the age-dependent disease. Levels of synaptotoxic amyloid β-protein (Aβ)1-42, angiopathic Aβ1-40, non-amyloidogenic Aβ1-38, and Aβ42/Aβ40 ratios tightly correlated between paired retinas derived from oculus sinister (OS) and oculus dexter (OD) eyes, and between left and right posterior brain hemispheres. We identified lateralization of Aβ burden, with one-side dominance within paired retinal and brain tissues. Importantly, OS and OD retinal Aβ levels correlated with their cerebral counterparts, with stronger contralateral correlations and following GA immunization. Moreover, immunomodulation in old ADtg mice brought about reductions in cerebral vascular and parenchymal Aβ deposits, especially of large, dense-core plaques, and alleviation of microgliosis and astrocytosis. Immunization further enhanced cerebral recruitment of peripheral myeloid cells and synaptic preservation. Mass spectrometry analysis identified new parallels in retino-cerebral AD-related pathology and response to GA immunization, including restoration of homeostatic glutamine synthetase expression. Overall, our results illustrate the viability of immunomodulation-guided CNS repair in old AD model mice, while shedding light onto similar retino-cerebral responses to intervention, providing incentives to explore retinal AD biomarkers.

Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases

Biomarkers for dementia of Alzheimer's type (DAT) are sought to facilitate accurate prediction of the disease onset, ideally predating the onset of cognitive deterioration. T1-weighted magnetic resonance imaging (MRI) is a commonly used neuroimaging modality for measuring brain structure in vivo, potentially providing information enabling the design of biomarkers for DAT. We propose a novel biomarker using structural MRI volume-based features to compute a similarity score for the individual's structural patterns relative to those observed in the DAT group. We employed ensemble-learning framework that combines structural features in most discriminative ROIs to create an aggregate measure of neurodegeneration in the brain. This classifier is trained on 423 stable normal control (NC) and 330 DAT subjects, where clinical diagnosis is likely to have the highest certainty. Independent validation on 8,834 unseen images from ADNI, AIBL, OASIS, and MIRIAD Alzheimer's disease (AD) databases showed promising potential to predict the development of DAT depending on the time-to-conversion (TTC). Classification performance on stable versus progressive mild cognitive impairment (MCI) groups achieved an AUC of 0.81 for TTC of 6 months and 0.73 for TTC of up to 7 years, achieving state-of-the-art results. The output score, indicating similarity to patterns seen in DAT, provides an intuitive measure of how closely the individual's brain features resemble the DAT group. This score can be used for assessing the presence of AD structural atrophy patterns in normal aging and MCI stages, as well as monitoring the progression of the individual's brain along with the disease course.

Blood-brain barrier dysfunction in aging induces hyperactivation of TGFβ signaling and chronic yet reversible neural dysfunction

Aging involves a decline in neural function that contributes to cognitive impairment and disease. However, the mechanisms underlying the transition from a young-and-healthy to aged-and-dysfunctional brain are not well understood. Here, we report breakdown of the vascular blood-brain barrier (BBB) in aging humans and rodents, which begins as early as middle age and progresses to the end of the life span. Gain-of-function and loss-of-function manipulations show that this BBB dysfunction triggers hyperactivation of transforming growth factor-β (TGFβ) signaling in astrocytes, which is necessary and sufficient to cause neural dysfunction and age-related pathology in rodents. Specifically, infusion of the serum protein albumin into the young rodent brain (mimicking BBB leakiness) induced astrocytic TGFβ signaling and an aged brain phenotype including aberrant electrocorticographic activity, vulnerability to seizures, and cognitive impairment. Furthermore, conditional genetic knockdown of astrocytic TGFβ receptors or pharmacological inhibition of TGFβ signaling reversed these symptomatic outcomes in aged mice. Last, we found that this same signaling pathway is activated in aging human subjects with BBB dysfunction. Our study identifies dysfunction in the neurovascular unit as one of the earliest triggers of neurological aging and demonstrates that the aging brain may retain considerable latent capacity, which can be revitalized by therapeutic inhibition of TGFβ signaling.

Spatially-Constrained Fisher Representation for Brain Disease Identification With Incomplete Multi-Modal Neuroimages

Multi-modal neuroimages, such as magnetic resonance imaging (MRI) and positron emission tomography (PET), can provide complementary structural and functional information of the brain, thus facilitating automated brain disease identification. Incomplete data problem is unavoidable in multi-modal neuroimage studies due to patient dropouts and/or poor data quality. Conventional methods usually discard data-missing subjects, thus significantly reducing the number of training samples. Even though several deep learning methods have been proposed, they usually rely on pre-defined regions-of-interest in neuroimages, requiring disease-specific expert knowledge. To this end, we propose a spatially-constrained Fisher representation framework for brain disease diagnosis with incomplete multi-modal neuroimages. We first impute missing PET images based on their corresponding MRI scans using a hybrid generative adversarial network. With the complete (after imputation) MRI and PET data, we then develop a spatially-constrained Fisher representation network to extract statistical descriptors of neuroimages for disease diagnosis, assuming that these descriptors follow a Gaussian mixture model with a strong spatial constraint (i.e., images from different subjects have similar anatomical structures). Experimental results on three databases suggest that our method can synthesize reasonable neuroimages and achieve promising results in brain disease identification, compared with several state-of-the-art methods.

Prediction of clinical and biomarker conformed Alzheimer's disease and mild cognitive impairment from multi-feature brain structural MRI using age-correction from a large independent lifespan sample

Structural neuroimaging has been applied to the identification of individuals with Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, these methods are greatly impacted by age limiting their utility for detection of preclinical pathology. We built linear models for age based on multiple combined structural features using a large independent lifespan sample of 272 healthy adults across a wide age range from the Human Connectome Project Aging study. These models were then used to create a new support vector machine (SVM) training model in 136 AD and 268 control participants based on residues of fit from the expected age-effects relationship. Subsequent validation assessed the accuracy of the SVM model in new datasets. Finally, we applied the classifier to 276 individuals with MCI to evaluate prediction for early impairment and longitudinal cognitive change. The optimal 10-fold cross-validation accuracy was 93.07%, compared to 91.83% without age detrending. In the validation dataset, the classifier for AD obtained an accuracy of 84.85% (56/66), sensitivity of 85.36% (35/41) and specificity of 84% (21/25). Classification accuracy was improved when using the lifespan sample as opposed to the classification sample. Importantly, we observed cross-sectional greater AD specific biomarkers, as well as faster cognitive decline in MCI who were classified as more 'AD-like' (MCI-AD), and these effects were pronounced in individuals who were late MCI. The top five contributive features were volumes of left hippocampus, right hippocampus, left amygdala, the thickness of left and right middle temporal & parahippocampus gyrus. Linear detrending for age in SVM for combined structural features resulted in good performance for recognition of AD and AD-specific biomarkers, as well as prediction of MCI progression. Such procedures may be used in future work to enhance prediction in samples with atypical age distributions.