Association between white matter hyperintensity load and grey matter atrophy in mild cognitive impairment is not unidirectional

Deep learning-based grading of white matter hyperintensities enables identification of potential markers in multi-sequence MRI data

BACKGROUND

White matter hyperintensities (WMHs) are widely-seen in the aging population, which are associated with cerebrovascular risk factors and age-related cognitive decline. At present, structural atrophy and functional alterations coexisted with WMHs lacks comprehensive investigation. This study developed a WMHs risk prediction model to evaluate WHMs according to Fazekas scales, and to locate potential regions with high risks across the entire brain.

METHODS

We developed a WMHs risk prediction model, which consisted of the following steps: T2 fluid attenuated inversion recovery (T2-FLAIR) image of each participant was firstly segmented into 1000 tiles with the size of 32 × 32 × 1, features from the tiles were extracted using the ResNet18-based feature extractor, and then a 1D convolutional neural network (CNN) was used to score all tiles based on the extracted features. Finally, a multi-layer perceptron (MLP) was constructed to predict the Fazekas scales based on the tile scores. The proposed model was trained using T2-FLAIR images, we selected tiles with abnormal scores in the test set after prediction, and evaluated their corresponding gray matter (GM) volume, white matter (WM) volume, fractional anisotropy (FA), mean diffusivity (MD), and cerebral blood flow (CBF) via longitudinal and multi-sequence Magnetic Resonance Imaging (MRI) data analysis.

RESULTS

The proposed WMHs risk prediction model could accurately predict the Fazekas ratings based on the tile scores from T2-FLAIR MRI images with accuracy of 0.656, 0.621 in training data set and test set, respectively. The longitudinal MRI validation revealed that most of the high-risk tiles predicted by the WMHs risk prediction model in the baseline images had WMHs in the corresponding positions in the longitudinal images. The validation on multi-sequence MRI demonstrated that WMHs were associated with GM and WM atrophies, WM micro-structural and perfusion alterations in high-risk tiles, and multi-modal MRI measures of most high-risk tiles showed significant associations with Mini Mental State Examination (MMSE) score.

CONCLUSION

Our proposed WMHs risk prediction model can not only accurately evaluate WMH severities according to Fazekas scales, but can also uncover potential markers of WMHs across modalities. The WMHs risk prediction model has the potential to be used for the early detection of WMH-related alterations in the entire brain and WMH-induced cognitive decline.

Evaluation of the default mode network using nonnegative matrix factorization in patients with cognitive impairment induced by occupational aluminum exposure

Aluminum (Al) is an important environmental pathogenic factor for neurodegenerative diseases, especially mild cognitive impairment (MCI). The aim of this study was to evaluate the gray matter volume of structural covariance network alterations in patients with Al-induced MCI. Male subjects who had been exposed to Al for >10 years were included in the present study. The plasma Al concentration, Montreal cognitive assessment (MoCA) score, and verbal memory assessed by the Rey auditory verbal learning test (AVLT) score were collected from each participant. Nonnegative matrix factorization was used to identify the structural covariance network. The neural structural basis for patients with Al-induced MCI was investigated using correlation analysis and group comparison. Plasma Al concentration was inversely related to MoCA scores, particularly AVLT scores. In patients with Al-induced MCI, the gray matter volume of the default mode network (DMN) was considerably lower than that in controls. Positive correlations were discovered between the DMN and MoCA scores as well as between the DMN and AVLT scores. In sum, long-term occupational Al exposure has a negative impact on cognition, primarily by affecting delayed recognition. The reduced gray matter volume of the DMN may be the neural mechanism of Al-induced MCI.

A Machine Learning Approach for Early Diagnosis of Cognitive Impairment Using Population-Based Data

BACKGROUND

The major mechanisms of dementia and cognitive impairment are vascular and neurodegenerative processes. Early diagnosis of cognitive impairment can facilitate timely interventions to mitigate progression.

OBJECTIVE

This study aims to develop a reliable machine learning (ML) model using socio-demographics, vascular risk factors, and structural neuroimaging markers for early diagnosis of cognitive impairment in a multi-ethnic Asian population.

METHODS

The study consisted of 911 participants from the Epidemiology of Dementia in Singapore study (aged 60- 88 years, 49.6% male). Three ML classifiers, logistic regression, support vector machine, and gradient boosting machine, were developed. Prediction results of independent classifiers were combined in a final ensemble model. Model performances were evaluated on test data using F1 score and area under the receiver operating curve (AUC) methods. Post modelling, SHapely Additive exPlanation (SHAP) was applied on the prediction results to identify the predictors that contribute most to the cognitive impairment prediction.

FINDINGS

The final ensemble model achieved a F1 score and AUC of 0.87 and 0.80 respectively. Accuracy (0.83), sensitivity (0.86), specificity (0.74) and predictive values (positive 0.88 negative 0.72) of the ensemble model were higher compared to the independent classifiers. Age, ethnicity, highest education attainment and neuroimaging markers were identified as important predictors of cognitive impairment.

CONCLUSION

This study demonstrates the feasibility of using ML tools to integrate multiple domains of data for reliable diagnosis of early cognitive impairment. The ML model uses easy-to-obtain variables and is scalable for screening individuals with a high risk of developing dementia in a population-based setting.

Correlation Between Plasma Oligomeric Amyloid-β and Performance on the Language Neutral Visual Cognitive Assessment Test in a Southeast Asian Population

Oligomeric amyloid-β (OAβ), an upstream driver of Alzheimer’s disease (AD) neuropathology, correlates with poor cognitive performance and brain volume reduction. Its effect on cognitive performance measured by the language neutral Visual Cognitive Assessment Test (VCAT) remains to be evaluated. We studied the correlation of plasma OAβ with VCAT scores and grey matter volume (GMV) in a Southeast Asian cohort with mild cognitive impairment. Higher plasma OAβ significantly correlated with lower; cognitive scores (VCAT, Mini-Mental State Examination) and GMV/intracranial volume ratio. Such findings reveal the clinical utility of plasma OAβ as a promising biomarker and support validation through longitudinal studies.

Research Progress on MRI for White Matter Hyperintensity of Presumed Vascular Origin and Cognitive Impairment

White matter hyperintensity of presumed vascular origin (WMH) is a common medical imaging manifestation in the brains of middle-aged and elderly individuals. WMH can lead to cognitive decline and an increased risk of cognitive impairment and dementia. However, the pathogenesis of cognitive impairment in patients with WMH remains unclear. WMH increases the risk of cognitive impairment, the nature and severity of which depend on lesion volume and location and the patient's cognitive reserve. Abnormal changes in microstructure, cerebral blood flow, metabolites, and resting brain function are observed in patients with WMH with cognitive impairment. Magnetic resonance imaging (MRI) is an indispensable tool for detecting WMH, and novel MRI techniques have emerged as the key approaches for exploring WMH and cognitive impairment. This article provides an overview of the association between WMH and cognitive impairment and the application of dynamic contrast-enhanced MRI, structural MRI, diffusion tensor imaging, 3D-arterial spin labeling, intravoxel incoherent motion, magnetic resonance spectroscopy, and resting-state functional MRI for examining WMH and cognitive impairment.

White matter hyperintensities-related cortical changes and correlation with mild behavioral impairment

PURPOSE

The aim of this study was to analyze cortical thickness and gray matter volume (GMV) changes in white matter hyperintensities (WMH) which were associated brain regions and their association with mild behavioral impairment (MBI) by means of voxel- and surface-based morphology (VBM and SBM).

METHODS

A total of 60 patients underwent 3T MRI scan and MBI checklist (MBI-C) assessment and were divided into two groups: lower WMH (LWMH) and higher WMH (HWMH). After adjusting for confounding factors i.e. age, gender, education, and total intracranial volume, we found a GMV decrease in the left anterior insula (AIns), right middle frontal gyrus, right central operculum, right fusiform gyrus, left cerebellum exterior, and thalamus proper in the HWMH group based VBM, while in the HWMH group based SBM we found cortical thickness decrease in the left lingual, right posterior cingulate cortex (rPCC), right precentral, left superior frontal, right medial orbitofrontal gyrus, and left pars opercularis.

RESULTS

The HWMH group had higher MBI-C scores. The GMV in the left AIns and thalamus proper and the thickness of rPCC negatively correlated with the MBI-C scores. The mediation analysis suggested that WMH may partially mediate MBI-C scores by reducing the GMV and cortical thickness of the mentioned brain regions.

CONCLUSIONS

In WMH patients, the occurrence of MBI is associated with atrophy of gray matter and cortex. The occurrence of MBI may be partially mediated by WMH through gray matter and cortical atrophy. It provides a new insight into the relationship between WMH and dementia.

Abnormal Cerebrovascular Reactivity and Functional Connectivity Caused by White Matter Hyperintensity Contribute to Cognitive Decline

Aims

This study aimed to investigate the relationships of impaired cerebrovascular reactivity (CVR) and abnormal functional connectivity (FC) with white matter hyperintensity (WMH)-related cognitive decline.

Methods

A total of 233 WMH subjects were recruited and categorized into WMH-I (n = 106), WMH-II (n = 72), and WMH-III (n = 55) groups according to Fazekas visual rating scale. All participants underwent neuropsychological tests and multimodal MRI scans, including 3D-T1, and resting-state functional magnetic resonance imaging (rs-fMRI). The alterations of CVR maps and FC were further explored.

Results

Subjects with a higher WMH burden displayed a lower CVR in the left medial occipital gyrus (MOG). The FC analysis using MOG as a seed revealed that the FC of the left insula, left inferior parietal lobule, and thalamus changed abnormally as WMH aggravated. After adjusting for age, gender, and education years, the serial mediation analysis revealed that periventricular white matter hyperintensity contributes indirectly to poorer Mini-Mental State Examination (MMSE) scores (indirect effect: β = −0.1248, 95% CI: −0.4689, −0188), poorer Montreal Cognitive Assessment (MoCA) (indirect effect: β = −0.1436, 95% CI: −0.4584, −0.0292) scores, and longer trail making tests A (TMT-A) (indirect effect: β = 0.1837, 95% CI: 0.0069, 0.8273) times, specifically due to the lower CVR of the left MOG and the higher FC of the left insula-MOG.

Conclusion

The CVR decline of the left MOG and the abnormal FC of the left insula-MOG attributed to WMH progression were responsible for the poor general cognition (MMSE and MoCA) and information processing speed (TMT-A). The left MOG may act as a connection, which is involved in the processing of cognitive biases by connecting with the left insula-cortical regions in WMH individuals.

Dementia in Southeast Asia: influence of onset-type, education, and cerebrovascular disease

Background

Southeast Asia represents 10% of the global population, yet little is known about regional clinical characteristics of dementia and risk factors for dementia progression. This study aims to describe the clinico-demographic profiles of dementia in Southeast Asia and investigate the association of onset-type, education, and cerebrovascular disease (CVD) on dementia progression in a real-world clinic setting.

Methods

In this longitudinal study, participants were consecutive series of 1606 patients with dementia from 2010 to 2019 from a tertiary memory clinic from Singapore. The frequency of dementia subtypes stratified into young-onset (YOD; <65 years age-at-onset) and late-onset dementia (LOD; ≥65 years age-at-onset) was studied. Association of onset-type (YOD or LOD), years of lifespan education, and CVD on the trajectory of cognition was evaluated using linear mixed models. The time to significant cognitive decline was investigated using Kaplan-Meier analysis.

Results

Dementia of the Alzheimer’s type (DAT) was the most common diagnosis (59.8%), followed by vascular dementia (14.9%) and frontotemporal dementia (11.1%). YOD patients accounted for 28.5% of all dementia patients. Patients with higher lifespan education had a steeper decline in global cognition (p<0.001), with this finding being more pronounced in YOD (p=0.0006). Older patients with a moderate-to-severe burden of CVD demonstrated a trend for a faster decline in global cognition compared to those with a mild burden.

Conclusions

There is a high frequency of YOD with DAT being most common in our Southeast Asian memory clinic cohort. YOD patients with higher lifespan education and LOD patients with moderate-to-severe CVD experience a steep decline in cognition.