Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer's Disease

Cerebrovascular markers of WMH and infarcts in ADNI: A historical perspective and future directions

White matter hyperintensities (WMH) and infarcts found on magnetic resonance imaging (MR infarcts) are common biomarkers of cerebrovascular disease. In this review, we summarize the methods, publications, and conclusions stemming from the Alzheimer's Disease Neuroimaging Initiative (ADNI) related to these measures. We combine analysis of WMH and MR infarct data from across the three main ADNI cohorts with a review of existing literature discussing new methodologies and scientific findings derived from these data. Although ADNI inclusion criteria were designed to minimize vascular risk factors and disease, data across all the ADNI cohorts found consistent trends of increasing WMH volumes associated with advancing age, female sex, and cognitive impairment. ADNI, initially proposed as a study to investigate biomarkers of AD pathology, has also helped elucidate the impact of asymptomatic cerebrovascular brain injury on cognition within a cohort relatively free of vascular disease. Future ADNI work will emphasize additional vascular biomarkers. HIGHLIGHTS: White matter hyperintensities (WMHs) are common to advancing age and likely reflect brain vascular injury among older individuals. WMH and to a lesser extent, magnetic resonance (MR) infarcts, affect risk for transition to cognitive impairment. WMHs and MR infarcts are present, even among Alzheimer's Disease Neuroimaging Initiative (ADNI) participants highly selected to have Alzheimer's disease (AD) as the primary pathology. WMH burden in ADNI is greater among individuals with cognitive impairment and has been associated with AD neurodegenerative markers and cerebral amyloidosis. The negative additive effects of cerebrovascular disease appear present, even in select populations, and future biomarker work needs to further explore this relationship.

Associations of cerebrovascular disease and Alzheimer's disease pathology with cognitive decline: Analysis of the National Alzheimer's Coordinating Center Uniform Data Set

Cerebrovascular disease (CVD) and Alzheimer's disease (AD) often co-occur and may impact specific cognitive domains. This study's goal was to determine effects of CVD and AD burden on cross-sectional and longitudinal executive function (EF) and memory in older adults. Longitudinally followed participants from the National Alzheimer Coordinating Center database (n = 3342) were included. Cognitive outcomes were EF and memory composite scores. Baseline CVD presence was defined by moderate-to-severe white matter hyperintensities or lacunar infarct on MRI. Baseline AD pathology was defined by amyloid positivity via PET or CSF. Linear mixed models examined effects of CVD, AD, and time on cognitive outcomes, controlling for sex, education, baseline age, MoCA score, and total number of study visits. At baseline, CVD associated with lower EF (p < 0.001), while AD associated with lower EF and memory (ps < 0.001). Longitudinally only AD associated with faster declines in memory and EF (ps < 0.001). These results extend our understanding of CVD and AD pathology, highlighting that CVD does not necessarily indicate accelerated decline.

Ensemble Vision Transformer for Dementia Diagnosis

In recent years, deep learning has gained momentum in computer-aided Alzheimer's Disease (AD) diagnosis. This study introduces a novel approach, Monte Carlo Ensemble Vision Transformer (MC-ViT), which develops an ensemble approach with Vision transformer (ViT). Instead of using traditional ensemble methods that deploy multiple learners, our approach employs a single vision transformer learner. By harnessing Monte Carlo sampling, this method produces a broad spectrum of classification decisions, enhancing the MC-ViT performance. This novel technique adeptly overcomes the limitation of 3D patch convolutional neural networks that only characterize partial of the whole brain anatomy, paving the way for a neural network adept at discerning 3D inter-feature correlations. Evaluations using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with 7199 scans and Open Access Series of Imaging Studies-3 (OASIS-3) with 1992 scans showcased its performance. With minimal preprocessing, our approach achieved an impressive 90% accuracy in AD classification, surpassing both 2D-slice CNNs and 3D CNNs.

Beyond Hypertension: Examining Variable Blood Pressure's Role in Cognition and Brain Structure

OBJECTIVES

Hypertension or high blood pressure (BP) is one of the 12 modifiable risk factors that contribute to 40% of dementia cases that could be delayed or prevented. Although hypertension is associated with cognitive decline and structural brain changes, less is known about the long-term association between variable BP and cognitive/brain changes. This study examined the relationship between variable BP and longitudinal cognitive, white matter hyperintensity (WMH), gray matter (GM), and white matter (WM) volume change over time and postmortem neuropathology.

METHODS

A total of 4,606 participants (32,776 follow-ups) from RADC Research Resource Sharing Hub (RUSH) and 2,114 participants (9,827 follow-ups) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were included. Participants were divided into 1 of 3 groups: normal, high, or variable BP. Linear-mixed models investigated the relationship between BP and cognition, brain structure, and neuropathology.

RESULTS

Older adults with variable BP exhibited the highest rate of cognitive decline followed by high and then normal BP. Increased GM volume loss and WMH burden were also observed in variable compared to high and normal BP. In postmortem neuropathology, both variable and high BP had increased rates compared to normal BP. Results were consistent across the RUSH and ADNI participants, supporting the generalizability of the findings.

DISCUSSION

Damages potentially associated with variable BP may reduce resilience to future dementia-related pathology and increased the risk of dementia more than that caused by high BP. Improved treatment and management of variable BP may help reduce cognitive decline in the older adult population.

Evaluating age-and gender-related changes in brain volumes in normal adult using synthetic magnetic resonance imaging

OBJECTIVE

Normal aging is associated with brain volume change, and brain segmentation can be performed within an acceptable scan time using synthetic magnetic resonance imaging (MRI). This study aimed to investigate the brain volume changes in healthy adult according to age and gender, and provide age- and gender-specific reference values using synthetic MRI.

METHODS

A total of 300 healthy adults (141 males, median age 48; 159 females, median age 50) were underwent synthetic MRI on 3.0 T. Brain parenchymal volume (BPV), gray matter volume (GMV), white matter volume (WMV), myelin volume (MYV), and cerebrospinal fluid volume (CSFV) were calculated using synthetic MRI software. These volumes were normalized by intracranial volume to normalized GMV (nGMV), normalized WMV (nWMV), normalized MYV (nMYV), normalized BPV (nBPV), and normalized CSFV (nCSFV). The normalized brain volumes were plotted against age in both males and females, and a curve fitting model that best explained the age dependence of brain volume was identified. The normalized brain volumes were compared between different age and gender groups.

RESULTS

The approximate curves of nGMV, nWMV, nCSFV, nBPV, and nMYV were best fitted by quadratic curves. The nBPV decreased monotonously through all ages in both males and females, while the changes of nCSFV showed the opposite trend. The nWMV and nMYV in both males and females increased gradually and then decrease with age. In early adulthood (20s), nWMV and nMYV in males were lower and peaked later than that in females (p < .005). The nGMV in both males and females decreased in the early adulthood until the 30s and then remains stable. A significant decline in nWMV, nBPV, and nMYV was noted in the 60s (Turkey test, p < .05).

CONCLUSIONS

Our study provides age- and gender-specific reference values of brain volumes using synthetic MRI, which could be objective tools for discriminating brain disorders from healthy brains.

Enlarged perivascular spaces are associated with white matter injury, cognition and inflammation in cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy

Enlarged perivascular spaces have been previously reported in cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy, but their significance and pathophysiology remains unclear. We investigated associations of white matter enlarged perivascular spaces with classical imaging measures, cognitive measures and plasma proteins to better understand what enlarged perivascular spaces represent in cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy and whether radiographic measures of enlarged perivascular spaces would be of value in future therapeutic discovery studies for cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy. Twenty-four individuals with cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy and 24 age- and sex-matched controls were included. Disease status was determined based on the presence of NOTCH3 mutation. Brain imaging measures of white matter hyperintensity, brain parenchymal fraction, white matter enlarged perivascular space volumes, clinical and cognitive measures as well as plasma proteomics were used in models. White matter enlarged perivascular space volumes were calculated via a novel, semiautomated pipeline, and levels of 7363 proteins were quantified in plasma using the SomaScan assay. The relationship of enlarged perivascular spaces with global burden of white matter hyperintensity, brain atrophy, functional status, neurocognitive measures and plasma proteins was modelled with linear regression models. Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy and control groups did not exhibit differences in mean enlarged perivascular space volumes. However, increased enlarged perivascular space volumes in cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy were associated with increased white matter hyperintensity volume (β = 0.57, P = 0.05), Clinical Dementia Rating Sum-of-Boxes score (β = 0.49, P = 0.04) and marginally with decreased brain parenchymal fraction (β = -0.03, P = 0.10). In interaction term models, the interaction term between cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy disease status and enlarged perivascular space volume was associated with increased white matter hyperintensity volume (β = 0.57, P = 0.02), Clinical Dementia Rating Sum-of-Boxes score (β = 0.52, P = 0.02), Mini-Mental State Examination score (β = -1.49, P = 0.03) and marginally with decreased brain parenchymal fraction (β = -0.03, P = 0.07). Proteins positively associated with enlarged perivascular space volumes were found to be related to leukocyte migration and inflammation, while negatively associated proteins were related to lipid metabolism. Two central hub proteins were identified in protein networks associated with enlarged perivascular space volumes: CXC motif chemokine ligand 8/interleukin-8 and C-C motif chemokine ligand 2/monocyte chemoattractant protein 1. The levels of CXC motif chemokine ligand 8/interleukin-8 were also associated with increased white matter hyperintensity volume (β = 42.86, P = 0.03), and levels of C-C motif chemokine ligand 2/monocyte chemoattractant protein 1 were further associated with decreased brain parenchymal fraction (β = -0.0007, P < 0.01) and Mini-Mental State Examination score (β = -0.02, P < 0.01) and increased Trail Making Test B completion time (β = 0.76, P < 0.01). No proteins were associated with all three studied imaging measures of pathology (brain parenchymal fraction, enlarged perivascular spaces, white matter hyperintensity). Based on associations uncovered between enlarged perivascular space volumes and cognitive functions, imaging and plasma proteins, we conclude that white matter enlarged perivascular space volumes may capture pathologies contributing to chronic brain dysfunction and degeneration in cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy.

Sex differences in risk factors, burden, and outcomes of cerebrovascular disease in Alzheimer's disease populations

BACKGROUND

White matter hyperintensities (WMHs) are associated with cognitive decline and progression to mild cognitive impairment (MCI) and dementia. It remains unclear if sex differences influence WMH progression or the relationship between WMH and cognition.

METHODS

Linear mixed models examined the relationship between risk factors, WMHs, and cognition in males and females.

RESULTS

Males exhibited increased WMH progression in occipital, but lower progression in frontal, total, and deep than females. For males, history of hypertension was the strongest contributor, while in females, the vascular composite was the strongest contributor to WMH burden. WMH burden was more strongly associated with decreases in global cognition, executive functioning, memory, and functional activities in females than males.

DISCUSSION

Controlling vascular risk factors may reduce WMH in both males and females. For males, targeting hypertension may be most important to reduce WMHs. The results have implications for therapies/interventions targeting cerebrovascular pathology and subsequent cognitive decline.

HIGHLIGHTS

Hypertension is the main vascular risk factor associated with WMH in males A combination of vascular risk factors contributes to WMH burden in females Only small WMH burden differences were observed between sexes Females' cognition was more negatively impacted by WMH burden than males Females with WMHs may have less resilience to future pathology.

Investigating the relationship between sleep disturbances and white matter hyperintensities in older adults on the Alzheimer's disease spectrum

INTRODUCTION

While studies report that sleep disturbance can have negative effects on brain vasculature, its impact on cerebrovascular diseases such as white matter hyperintensities (WMHs) in beta-amyloid-positive older adults remains unexplored.

METHODS

Sleep disturbance, WMH burden, and cognition in normal controls (NCs), and individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD), were examined at baseline and longitudinally. A total of 912 amyloid-positive participants were included (198 NC, 504 MCI, and 210 AD).

RESULTS

Individuals with AD reported more sleep disturbances than NC and MCI participants. Those with sleep disturbances had more WMHs than those without sleep disturbances in the AD group. Mediation analysis revealed an effect of regional WMH burden on the relationship between sleep disturbance and future cognition.

DISCUSSION

These results suggest that WMH burden and sleep disturbance increase from aging to AD. Sleep disturbance decreases cognition through increases in WMH burden. Improved sleep could mitigate the impact of WMH accumulation and cognitive decline.

Alzheimer's Disease Prediction via Brain Structural-Functional Deep Fusing Network

Fusing structural-functional images of the brain has shown great potential to analyze the deterioration of Alzheimer's disease (AD). However, it is a big challenge to effectively fuse the correlated and complementary information from multimodal neuroimages. In this work, a novel model termed cross-modal transformer generative adversarial network (CT-GAN) is proposed to effectively fuse the functional and structural information contained in functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI). The CT-GAN can learn topological features and generate multimodal connectivity from multimodal imaging data in an efficient end-to-end manner. Moreover, the swapping bi-attention mechanism is designed to gradually align common features and effectively enhance the complementary features between modalities. By analyzing the generated connectivity features, the proposed model can identify AD-related brain connections. Evaluations on the public ADNI dataset show that the proposed CT-GAN can dramatically improve prediction performance and detect AD-related brain regions effectively. The proposed model also provides new insights into detecting AD-related abnormal neural circuits.

Assessment of white matter hyperintensity severity using multimodal magnetic resonance imaging

White matter hyperintensities are radiological abnormalities reflecting cerebrovascular dysfunction detectable using MRI. White matter hyperintensities are often present in individuals at the later stages of the lifespan and in prodromal stages in the Alzheimer's disease spectrum. Tissue alterations underlying white matter hyperintensities may include demyelination, inflammation and oedema, but these are highly variable by neuroanatomical location and between individuals. There is a crucial need to characterize these white matter hyperintensity tissue alterations in vivo to improve prognosis and, potentially, treatment outcomes. How different MRI measure(s) of tissue microstructure capture clinically-relevant white matter hyperintensity tissue damage is currently unknown. Here, we compared six MRI signal measures sampled within white matter hyperintensities and their associations with multiple clinically-relevant outcomes, consisting of global and cortical brain morphometry, cognitive function, diagnostic and demographic differences and cardiovascular risk factors. We used cross-sectional data from 118 participants: healthy controls (n = 30), individuals at high risk for Alzheimer's disease due to familial history (n = 47), mild cognitive impairment (n = 32) and clinical Alzheimer's disease dementia (n = 9). We sampled the median signal within white matter hyperintensities on weighted MRI images [T1-weighted (T1w), T2-weighted (T2w), T1w/T2w ratio, fluid-attenuated inversion recovery (FLAIR)] as well as the relaxation times from quantitative T1 (qT1) and T2* (qT2*) images. qT2* and fluid-attenuated inversion recovery signals within white matter hyperintensities displayed different age- and disease-related trends compared to normal-appearing white matter signals, suggesting sensitivity to white matter hyperintensity-specific tissue deterioration. Further, white matter hyperintensity qT2*, particularly in periventricular and occipital white matter regions, was consistently associated with all types of clinically-relevant outcomes in both univariate and multivariate analyses and across two parcellation schemes. qT1 and fluid-attenuated inversion recovery measures showed consistent clinical relationships in multivariate but not univariate analyses, while T1w, T2w and T1w/T2w ratio measures were not consistently associated with clinical variables. We observed that the qT2* signal was sensitive to clinically-relevant microstructural tissue alterations specific to white matter hyperintensities. Our results suggest that combining volumetric and signal measures of white matter hyperintensity should be considered to fully characterize the severity of white matter hyperintensities in vivo. These findings may have implications in determining the reversibility of white matter hyperintensities and the potential efficacy of cardio- and cerebrovascular treatments.

Understanding the impact of radical changes in diet and the gut microbiota on brain function and structure: rationale and design of the EMBRACE study

BACKGROUND

Bariatric surgery leads to profound changes in gut microbiota and dietary patterns, both of which may interact to impact gut-brain communication. Though cognitive function improves postsurgery, there is a large variability in outcomes. How bariatric surgery-induced modifications in the gut microbiota and dietary patterns influence the variability in cognitive function is still unclear.

OBJECTIVES

To elucidate the associations between bariatric surgery-induced changes in dietary and gut microbiota patterns with cognition and brain structure.

SETTING

University hospital.

METHODS

A total of 120 adult patients (≥30 years) scheduled to undergo a primary bariatric surgery along with 60 age-, sex-, and body mass index-matched patients on the surgery waitlist will undergo assessments 3-months presurgery and 6- and 12-month postsurgery (or an equivalent time for the waitlist group). Additionally, 60 age-and sex-matched nonbariatric surgery eligible individuals will complete the presurgical assessments only. Evaluations will include sociodemographic and health behavior questionnaires, physiological assessments (anthropometrics, blood-, urine-, and fecal-based measures), neuropsychological cognitive tests, and structural magnetic resonance imaging. Cluster analyses of the dietary and gut microbiota changes will define the various dietary patterns and microbiota profiles, then using repeated measures mixed models, their associations with global cognitive and structural brain alterations will be explored.

RESULTS

The coordinating study site (Centre intégré universitaire de santé et de services sociaux du Nord-de-l'Île-de-Montréal, QC, Canada), provided the primary ethical approval (Research Ethics Board#: MP-32-2022-2412).

CONCLUSIONS

The insights generated from this study can be used to develop individually-targeted neurodegenerative disease prevention strategies, as well as providing critical mechanistic information.

Classification of Alzheimer's Disease Using Maximal Information Coefficient-Based Functional Connectivity with an Extreme Learning Machine

Alzheimer's disease (AD) is a progressive chronic illness that leads to cognitive decline and dementia. Neuroimaging technologies, such as functional magnetic resonance imaging (fMRI), and deep learning approaches offer promising avenues for AD classification. In this study, we investigate the use of fMRI-based functional connectivity (FC) measures, including the Pearson correlation coefficient (PCC), maximal information coefficient (MIC), and extended maximal information coefficient (eMIC), combined with extreme learning machines (ELM) for AD classification. Our findings demonstrate that employing non-linear techniques, such as MIC and eMIC, as features for classification yields accurate results. Specifically, eMIC-based features achieve a high accuracy of 94% for classifying cognitively normal (CN) and mild cognitive impairment (MCI) individuals, outperforming PCC (81%) and MIC (85%). For MCI and AD classification, MIC achieves higher accuracy (81%) compared to PCC (58%) and eMIC (78%). In CN and AD classification, eMIC exhibits the best accuracy of 95% compared to MIC (90%) and PCC (87%). These results underscore the effectiveness of fMRI-based features derived from non-linear techniques in accurately differentiating AD and MCI individuals from CN individuals, emphasizing the potential of neuroimaging and machine learning methods for improving AD diagnosis and classification.

Differences in AD-related pathology profiles across APOE groups

BACKGROUND

The apolipoprotein (APOE) e4 allele is a known risk factor for Alzheimer's disease (AD), while the e2 allele is thought to be protective against AD. Few studies have examined the relationship between brain pathologies, atrophy, and white matter hyperintensities (WMHs) and APOE status in those with the e2e4 genotype and results are inconsistent for those with an e2 allele.

METHODS

We analyzed Alzheimer's Disease Neuroimaging participants that had APOE genotyping and at least one of the following metrics: regional WMH load, ventricle size, hippocampal (HC) and entorhinal cortex (EC) volume, amyloid level (i.e., AV-45), and phosphorylated tau (pTau). Participants were divided into one of four APOE allele profiles (E4=e4e4 or e3e4; E2=e2e2 or e2e3; E3=e3e3; or E24=e2e4, Fig.1). Linear mixed models examined the relationship between APOE profiles and each pathology (i.e., regional WMHs, ventricle size, hippocampal and entorhinal cortex volume, amyloid level, and phosphorylated tau measures). while controlling for age, sex, education, and diagnostic status at baseline and over time.

RESULTS

APOE ε4 is associated with increased pathology while ε2 positivity is associated with reduced baseline and lower accumulation of pathologies and rates of neurodegeneration. APOE ε2ε4 is similar to ε4 (increased neurodegeneration) but with a slower rate of change.

CONCLUSIONS

The strong associations observed between APOE and pathology in this study show the importance of how genetic factors influence structural brain changes. These findings suggest that ε2ε4 genotype is related to increased declines associated with the ε4 as opposed to the protective effects of the ε2. These findings have important implications for initiating treatments and interventions. Given that people who have the ε2ε4 genotype can expect to have increased atrophy, they must be included (alongside those with an ε4 profile) in targeted interventions to reduce brain changes that occur with AD.

Investigating the relationship between sleep disturbances and white matter hyperintensities in older adults on the Alzheimer's disease spectrum

Background

While studies report that sleep disturbance can have negative effects on brain vasculature, its impact on cerebrovascular disease such as white matter hyperintensities (WMHs) in beta-amyloid positive older adults remains unexplored.

Methods

Linear regressions, mixed effects models, and mediation analysis examined the crosssectional and longitudinal associations between sleep disturbance, cognition, and WMH burden, and cognition in normal controls (NCs), mild cognitive impairment (MCI), and Alzheimer's disease (AD) at baseline and longitudinally.

Results

People with AD reported more sleep disturbance than NC and MCI. AD with sleep disturbance had more WMHs than AD without sleep disturbances. Mediation analysis revealed an effect of regional WMH burden on the relationship between sleep disturbance and future cognition.

Conclusion

These results suggest that WMH burden and sleep disturbance increases from aging to AD. Sleep disturbance decreases cognition through increases in WMH burden. Improved sleep could mitigate the impact of WMH accumulation and cognitive decline.

Racial differences in white matter hyperintensity burden in older adults

White matter hyperintensities (WMHs) may be one of the earliest pathological changes in aging. Race differences in WMH burden has been conflicting. This study examined if race influences WMHs and whether these differences are influenced by vascular risk factors. Alzheimer's Disease Neuroimaging Initiative participants were included if they had a baseline MRI, diagnosis, and WMH measurements. Ninety-one Blacks and 1937 Whites were included. Using bootstrap re-sampling, 91 Whites were randomly sampled and matched to Blacks based on age, sex, education, and diagnosis 1000 times. Linear models examined the influence of race on baseline WMHs, and change of WMHs over time, with and without vascular factors. Vascular risk factors had higher prevalence in Blacks than Whites. When not including vascular factors, Blacks had greater frontal, parietal, deep, and total WMH burden compared to Whites. There were no race differences in longitudinal progression of WMH accumulation. After controlling for vascular factors, only overall longitudinal parietal WMH group differences remained significant, suggesting that vascular factors contribute to racial group differences observed in WMHs.

White matter hyperintensity load varies depending on subjective cognitive decline criteria

Increased age and cognitive impairment is associated with an increase in cerebrovascular pathology often measured as white matter hyperintensities (WMHs) on MRI. Whether WMH burden differs between cognitively unimpaired older adults with subjective cognitive decline (SCD +) and without subjective cognitive decline (SCD -) remains conflicting, and could be related to the methods used to identify SCD. Our goal was to examine if four common SCD classification methods are associated with different WMH accumulation patterns between SCD + and SCD - . A total of 535 cognitively unimpaired older adults with 1353 time points from the Alzheimer's Disease Neuroimaging Initiative were included in this study. SCD was operationalized using four different methods: Cognitive Change Index (CCI), Everyday Cognition Scale (ECog), ECog + Worry, and Worry. Linear mixed-effects models were used to investigate the associations between SCD and overall and regional WMH burden. Overall temporal WMH burden differences were only observed with the Worry questionnaire. Higher WMH burden change over time was observed in SCD + compared to SCD - in the temporal and parietal regions using the CCI (temporal, p = .01; parietal p = .02) and ECog (temporal, p = .02; parietal p = .01). For both the ECog + Worry and Worry questionnaire, change in WMH burden over time was increased in SCD + compared to SCD - for overall, frontal, temporal, and parietal WMH burden (p < .05). These results show that WMH burden differs between SCD + and SCD - depending on the questionnaire and the approach (regional/global) used to measure WMHs. The various methods used to define SCD may reflect different types of underlying pathologies.

A joint ventricle and WMH segmentation from MRI for evaluation of healthy and pathological changes in the aging brain

Age-related changes in brain structure include atrophy of the brain parenchyma and white matter changes of presumed vascular origin. Enlargement of the ventricles may occur due to atrophy or impaired cerebrospinal fluid (CSF) circulation. The co-occurrence of these changes in neurodegenerative diseases and in aging brains often requires investigators to take both into account when studying the brain, however, automated segmentation of enlarged ventricles and white matter hyperintensities (WMHs) can be a challenging task. Here, we present a hybrid multi-atlas segmentation and convolutional autoencoder approach for joint ventricle parcellation and WMH segmentation from magnetic resonance images (MRIs). Our fully automated approach uses a convolutional autoencoder to generate a standardized image of grey matter, white matter, CSF, and WMHs, which, in conjunction with labels generated by a multi-atlas segmentation approach, is then fed into a convolutional neural network to parcellate the ventricular system. Hence, our approach does not depend on manually delineated training data for new data sets. The segmentation pipeline was validated on both healthy elderly subjects and subjects with normal pressure hydrocephalus using ground truth manual labels and compared with state-of-the-art segmentation methods. We then applied the method to a cohort of 2401 elderly brains to investigate associations of ventricle volume and WMH load with various demographics and clinical biomarkers, using a multiple regression model. Our results indicate that the ventricle volume and WMH load are both highly variable in a cohort of elderly subjects and there is an independent association between the two, which highlights the importance of taking both the possibility of enlarged ventricles and WMHs into account when studying the aging brain.

Using transfer learning for automated microbleed segmentation

INTRODUCTION

Cerebral microbleeds are small perivascular hemorrhages that can occur in both gray and white matter brain regions. Microbleeds are a marker of cerebrovascular pathology and are associated with an increased risk of cognitive decline and dementia. Microbleeds can be identified and manually segmented by expert radiologists and neurologists, usually from susceptibility-contrast MRI. The latter is hard to harmonize across scanners, while manual segmentation is laborious, time-consuming, and subject to interrater and intrarater variability. Automated techniques so far have shown high accuracy at a neighborhood ("patch") level at the expense of a high number of false positive voxel-wise lesions. We aimed to develop an automated, more precise microbleed segmentation tool that can use standardizable MRI contrasts.

METHODS

We first trained a ResNet50 network on another MRI segmentation task (cerebrospinal fluid vs. background segmentation) using T1-weighted, T2-weighted, and T2* MRIs. We then used transfer learning to train the network for the detection of microbleeds with the same contrasts. As a final step, we employed a combination of morphological operators and rules at the local lesion level to remove false positives. Manual segmentation of microbleeds from 78 participants was used to train and validate the system. We assessed the impact of patch size, freezing weights of the initial layers, mini-batch size, learning rate, and data augmentation on the performance of the Microbleed ResNet50 network.

RESULTS

The proposed method achieved high performance, with a patch-level sensitivity, specificity, and accuracy of 99.57, 99.16, and 99.93%, respectively. At a per lesion level, sensitivity, precision, and Dice similarity index values were 89.1, 20.1, and 0.28% for cortical GM; 100, 100, and 1.0% for deep GM; and 91.1, 44.3, and 0.58% for WM, respectively.

DISCUSSION

The proposed microbleed segmentation method is more suitable for the automated detection of microbleeds with high sensitivity.

Automatic segmentation of white matter hyperintensities in routine clinical brain MRI by 2D VB-Net: A large-scale study

White matter hyperintensities (WMH) are imaging manifestations frequently observed in various neurological disorders, yet the clinical application of WMH quantification is limited. In this study, we designed a series of dedicated WMH labeling protocols and proposed a convolutional neural network named 2D VB-Net for the segmentation of WMH and other coexisting intracranial lesions based on a large dataset of 1,045 subjects across various demographics and multiple scanners using 2D thick-slice protocols that are more commonly applied in clinical practice. Using our labeling pipeline, the Dice consistency of the WMH regions manually depicted by two observers was 0.878, which formed a solid basis for the development and evaluation of the automatic segmentation system. The proposed algorithm outperformed other state-of-the-art methods (uResNet, 3D V-Net and Visual Geometry Group network) in the segmentation of WMH and other coexisting intracranial lesions and was well validated on datasets with thick-slice magnetic resonance (MR) images and the 2017 medical image computing and computer assisted intervention WMH Segmentation Challenge dataset (with thin-slice MR images), all showing excellent effectiveness. Furthermore, our method can subclassify WMH to display the WMH distributions and is very lightweight. Additionally, in terms of correlation to visual rating scores, our algorithm showed excellent consistency with the manual delineations and was overall better than those from other competing methods. In conclusion, we developed an automatic WMH quantification framework for multiple application scenarios, exhibiting a promising future in clinical practice.

White matter lesions may be an early marker for age-related cognitive decline

BACKGROUND

Research suggests that cerebral small vessel disease (CSVD), amyloid, and pTau contribute to age-related cognitive decline. It remains unknown how these factors relate to one another and how they jointly contribute to cognitive decline in normal aging. This project examines the association between these factors and their relationship to cognitive decline in cognitively unimpaired older adults without subjective cognitive decline.

METHODS

A total of 230 subjects with cerebrospinal fluid (CSF) Aß42, CSF pTau181, white matter lesions (WMLs) used as a proxy of CSVD, and cognitive scores from the Alzheimer's Disease Neuroimaging Initiative were included. Associations between each factor and cognitive score were investigated using regression models. Furthermore, relationships between the three pathologies were also examined using regression models.

RESULTS

At baseline, there was an inverse association between WML load and Aß42 (t = -4.20, p <.001). There was no association between WML load and pTau (t = 0.32, p = 0.75), nor with Aß42 and pTau (t = 0.51, p =.61). Correcting for age, sex and education, baseline WML load was associated with baseline ADAS-13 scores (t = 2.59, p =.01) and lower follow-up executive functioning (t = -2.84, p =.005). Baseline Aß42 was associated with executive function at baseline (t = 3.58, p<.004) but not at follow-up (t = 1.05, p = 0.30), nor with ADAS-13 at baseline (t = -0.24, p = 0.81) or follow-up (t = 0.09, p = 0.93). Finally, baseline pTau was not associated with any cognitive measure at baseline or follow-up.

CONCLUSION

Both baseline Aß42 and WML load are associated with some baseline cognition scores, but only baseline WML load is associated with follow-up executive functioning. This finding suggests that WMLs may be one of the earliest clinical manifestations that contributes to future cognitive decline in cognitively healthy older adults. Given that healthy older adults with WMLs exhibit declines in cognitive functioning, they may be less resilient to future pathology increasing their risk for cognitive impairment due to dementia than those without WMLs.

Diagnosis of Amnesic Mild Cognitive Impairment Using MGS-WBC and VGBN-LM Algorithms

Computer-aided diagnosis (CAD) has undergone rapid development with the advent of advanced neuroimaging and machine learning methods. Nevertheless, how to extract discriminative features from the limited and high-dimensional data is not ideal, especially for amnesic mild cognitive impairment (aMCI) data based on resting-state functional magnetic resonance imaging (rs-fMRI). Furthermore, a robust and reliable system for aMCI detection is conducive to timely detecting and screening subjects at a high risk of Alzheimer's disease (AD). In this scenario, we first develop the mask generation strategy based on within-class and between-class criterion (MGS-WBC), which primarily aims at reducing data redundancy and excavating multiscale features of the brain. Concurrently, vector generation for brain networks based on Laplacian matrix (VGBN-LM) is presented to obtain the global features of the functional network. Finally, all multiscale features are fused to further improve the diagnostic performance of aMCI. Typical classifiers for small data learning, such as naive Bayesian (NB), linear discriminant analysis (LDA), logistic regression (LR), and support vector machines (SVMs), are adopted to evaluate the diagnostic performance of aMCI. This study helps to reveal discriminative neuroimaging features, and outperforms the state-of-the-art methods, providing new insights for the intelligent construction of CAD system of aMCI.

Supervised Computer-Aided Diagnosis (CAD) Methods for Classifying Alzheimer's Disease-Based Neurodegenerative Disorders

Alzheimer's disease is incurable at the moment. If it can be appropriately diagnosed, the correct treatment can postpone the patient's illness. To aid in the diagnosis of Alzheimer's disease and to minimize the time and expense associated with manual diagnosis, a machine learning technique is employed, and a transfer learning method based on 3D MRI data is proposed. Machine learning algorithms can dramatically reduce the time and effort required for human treatment of Alzheimer's disease. This approach extracts bottleneck features from the M-Net migration network and then adds a top layer to supervised training to further decrease the dimensionality and delete portions. As a consequence, the transfer network presented in this study has several advantages in terms of computational efficiency and training time savings when used as a machine learning approach for AD-assisted diagnosis. Finally, the properties of all subject slices are combined and trained in the classification layer, completing the categorization of Alzheimer's disease symptoms and standard control. The results show that this strategy has a 1.5 percentage point better classification accuracy than the one that relies exclusively on VGG16 to extract bottleneck features. This strategy could cut the time it takes for the network to learn and improve its ability to classify things. The experiment shows that the method works by using data from OASIS. A typical transfer learning network's classification accuracy is about 8% better with this method than with a typical network, and it takes about 1/60 of the time with this method.

Accurate 3D Reconstruction of White Matter Hyperintensities Based on Attention-Unet

White matter hyperintensities (WMH), also known as white matter osteoporosis, have been clinically proven to be associated with cognitive decline, the risk of cerebral infarction, and dementia. The existing computer automatic measurement technology for the segmentation of patients' WMH does not have a good visualization and quantitative analysis. In this work, the author proposed a new WMH quantitative analysis and 3D reconstruction method for 3D reconstruction of high signal in white matter. At first, the author using ResUnet achieves the high signal segmentation of white matter and adds the attention mechanism into ResUnet to achieve more accurate segmentation. Afterwards, this paper used surface rendering to reconstruct the accurate segmentation results in 3D. Data experiments are conducted on the dataset collected from Shandong Province Third Hospital. After training, the Attention-Unet proposed in this paper is superior to other segmentation models in the segmentation of high signal in white matter and Dice coefficient and MPA reached 92.52% and 92.43%, respectively, thus achieving accurate 3D reconstruction and providing a new idea for quantitative analysis and 3D reconstruction of WMH.

The Effect of Training Sample Size on the Prediction of White Matter Hyperintensity Volume in a Healthy Population Using BIANCA

Introduction: White matter hyperintensities of presumed vascular origin (WMH) are an important magnetic resonance imaging marker of cerebral small vessel disease and are associated with cognitive decline, stroke, and mortality. Their relevance in healthy individuals, however, is less clear. This is partly due to the methodological challenge of accurately measuring rare and small WMH with automated segmentation programs. In this study, we tested whether WMH volumetry with FMRIB software library v6.0 (FSL; https://fsl.fmrib.ox.ac.uk/fsl/fslwiki) Brain Intensity AbNormality Classification Algorithm (BIANCA), a customizable and trainable algorithm that quantifies WMH volume based on individual data training sets, can be optimized for a normal aging population.

Methods: We evaluated the effect of varying training sample sizes on the accuracy and the robustness of the predicted white matter hyperintensity volume in a population (n = 201) with a low prevalence of confluent WMH and a substantial proportion of participants without WMH. BIANCA was trained with seven different sample sizes between 10 and 40 with increments of 5. For each sample size, 100 random samples of T1w and FLAIR images were drawn and trained with manually delineated masks. For validation, we defined an internal and external validation set and compared the mean absolute error, resulting from the difference between manually delineated and predicted WMH volumes for each set. For spatial overlap, we calculated the Dice similarity index (SI) for the external validation cohort.

Results: The study population had a median WMH volume of 0.34 ml (IQR of 1.6 ml) and included n = 28 (18%) participants without any WMH. The mean absolute error of the difference between BIANCA prediction and manually delineated masks was minimized and became more robust with an increasing number of training participants. The lowest mean absolute error of 0.05 ml (SD of 0.24 ml) was identified in the external validation set with a training sample size of 35. Compared to the volumetric overlap, the spatial overlap was poor with an average Dice similarity index of 0.14 (SD 0.16) in the external cohort, driven by subjects with very low lesion volumes.

Discussion: We found that the performance of BIANCA, particularly the robustness of predictions, could be optimized for use in populations with a low WMH load by enlargement of the training sample size. Further work is needed to evaluate and potentially improve the prediction accuracy for low lesion volumes. These findings are important for current and future population-based studies with the majority of participants being normal aging people.

White matter hyperintensities are associated with grey matter atrophy and cognitive decline in Alzheimer's disease and frontotemporal dementia

White matter hyperintensities (WMHs) are commonly assumed to represent non-specific cerebrovascular disease comorbid to neurodegenerative processes, rather than playing a synergistic role. We compared the impact of WMHs on grey matter (GM) atrophy and cognition in normal aging (n = 571), mild cognitive impairment (MCI, n = 551), Alzheimer's dementia (AD, n = 212), fronto-temporal dementia (FTD, n = 125), and Parkinson's disease (PD, n = 271). Longitudinal data were obtained from ADNI, FTLDNI, and PPMI datasets. Mixed-effects models were used to compare WMHs and GM atrophy between patients and controls and assess the impact of WMHs on GM atrophy and cognition. MCI, AD, and FTD patients had significantly higher WMH loads than controls. WMHs were related to GM atrophy in insular and parieto-occipital regions in MCI/AD, and frontal regions and basal ganglia in FTD. In addition, WMHs contributed to more severe cognitive deficits in AD and FTD compared to controls, whereas their impact in MCI and PD was not significantly different from controls. These results suggest potential synergistic effects between WMHs and proteinopathies in the neurodegenerative process in MCI, AD and FTD.

Birth Cohorts and Cognitive Reserve Influence Cognitive Performances in Older Adults

BACKGROUND

Evidence suggests birth cohort differences in cognitive performance of older adults. Proxies of cognitive reserve (CR), such as educational attainment and occupational complexity, could also partly account for these differences as they are influenced by the sociocultural environment of the birth cohorts.

OBJECTIVE

To predict cognitive performance using birth cohorts and CR and examine the moderating influence of CR on cognitive performance and structural brain health association.

METHODS

Using ADNI data (n = 1628), four birth cohorts were defined (1915-1928; 1929-1938; 1939-1945; 1946-1964). CR proxies were education, occupational complexity, and verbal IQ. We predicted baseline cognitive performances (verbal episodic memory; language and semantic memory; attention capacities; executive functions) using multiple linear regressions with CR, birth cohorts, age, structural brain health (total brain volume; total white matter hyperintensities volume) and vascular risk factors burden as predictors. Sex and CR interactions were also explored.

RESULTS

Recent birth cohorts, higher CR, and healthier brain structures predicted better performance in verbal episodic memory, language and semantic memory, and attention capacities, with large effect sizes. Better performance in executive functions was predicted by a higher CR and a larger total brain volume, with a small effect size. With equal score of CR, women outperformed men in verbal episodic memory and language and semantic memory in all cohorts. Higher level of CR predicted better performance in verbal episodic memory, only when total brain volume was lower.

CONCLUSION

Cohort differences in cognitive performance favor more recent birth cohorts and suggests that this association may be partly explained by proxies of CR.

Deep learning based pipelines for Alzheimer's disease diagnosis: A comparative study and a novel deep-ensemble method

BACKGROUND

Alzheimer's disease is a chronic neurodegenerative disease that destroys brain cells, causing irreversible degeneration of cognitive functions and dementia. Its causes are not yet fully understood, and there is no curative treatment. However, neuroimaging tools currently offer help in clinical diagnosis, and, recently, deep learning methods have rapidly become a key methodology applied to these tools. The reason is that they require little or no image preprocessing and can automatically infer an optimal representation of the data from raw images without requiring prior feature selection, resulting in a more objective and less biased process. However, training a reliable model is challenging due to the significant differences in brain image types.

METHODS

We aim to contribute to the research and study of Alzheimer's disease through computer-aided diagnosis (CAD) by comparing different deep learning models. In this work, there are three main objectives: i) to present a fully automated deep-ensemble approach for dementia-level classification from brain images, ii) to compare different deep learning architectures to obtain the most suitable one for the task, and (iii) evaluate the robustness of the proposed strategy in a deep learning framework to detect Alzheimer's disease and recognise different levels of dementia. The proposed approach is specifically designed to be potential support for clinical care based on patients' brain images.

RESULTS

Our strategy was developed and tested on three MRI and one fMRI public datasets with heterogeneous characteristics. By performing a comprehensive analysis of binary classification (Alzheimer's disease status or not) and multiclass classification (recognising different levels of dementia), the proposed approach can exceed state of the art in both tasks, reaching an accuracy of 98.51% in the binary case, and 98.67% in the multiclass case averaged over the four different data sets.

CONCLUSION

We strongly believe that integrating the proposed deep-ensemble approach will result in robust and reliable CAD systems, considering the numerous cross-dataset experiments performed. Being tested on MRIs and fMRIs, our strategy can be easily extended to other imaging techniques. In conclusion, we found that our deep-ensemble strategy could be efficiently applied for this task with a considerable potential benefit for patient management.

Deep Learning for COVID-19 Diagnosis from CT Images

COVID-19, an infectious coronavirus disease, caused a pandemic with countless deaths. From the outset, clinical institutes have explored computed tomography as an effective and complementary screening tool alongside the reverse transcriptase-polymerase chain reaction. Deep learning techniques have shown promising results in similar medical tasks and, hence, may provide solutions to COVID-19 based on medical images of patients. We aim to contribute to the research in this field by: (i) Comparing different architectures on a public and extended reference dataset to find the most suitable; (ii) Proposing a patient-oriented investigation of the best performing networks; and (iii) Evaluating their robustness in a real-world scenario, represented by cross-dataset experiments. We exploited ten well-known convolutional neural networks on two public datasets. The results show that, on the reference dataset, the most suitable architecture is VGG19, which (i) Achieved 98.87% accuracy in the network comparison; (ii) Obtained 95.91% accuracy on the patient status classification, even though it misclassifies some patients that other networks classify correctly; and (iii) The cross-dataset experiments exhibit the limitations of deep learning approaches in a real-world scenario with 70.15% accuracy, which need further investigation to improve the robustness. Thus, VGG19 architecture showed promising performance in the classification of COVID-19 cases. Nonetheless, this architecture enables extensive improvements based on its modification, or even with preprocessing step in addition to it. Finally, the cross-dataset experiments exposed the critical weakness of classifying images from heterogeneous data sources, compatible with a real-world scenario.

Beware of white matter hyperintensities causing systematic errors in FreeSurfer gray matter segmentations!

Volumetric estimates of subcortical and cortical structures, extracted from T1-weighted MRIs, are widely used in many clinical and research applications. Here, we investigate the impact of the presence of white matter hyperintensities (WMHs) on FreeSurfer gray matter (GM) structure volumes and its possible bias on functional relationships. T1-weighted images from 1,077 participants (4,321 timepoints) from the Alzheimer's Disease Neuroimaging Initiative were processed with FreeSurfer version 6.0.0. WMHs were segmented using a previously validated algorithm on either T2-weighted or Fluid-attenuated inversion recovery images. Mixed-effects models were used to assess the relationships between overlapping WMHs and GM structure volumes and overall WMH burden, as well as to investigate whether such overlaps impact associations with age, diagnosis, and cognitive performance. Participants with higher WMH volumes had higher overlaps with GM volumes of bilateral caudate, cerebral cortex, putamen, thalamus, pallidum, and accumbens areas (p < .0001). When not corrected for WMHs, caudate volumes increased with age (p < .0001) and were not different between cognitively healthy individuals and age-matched probable Alzheimer's disease patients. After correcting for WMHs, caudate volumes decreased with age (p < .0001), and Alzheimer's disease patients had lower caudate volumes than cognitively healthy individuals (p < .01). Uncorrected caudate volume was not associated with ADAS13 scores, whereas corrected lower caudate volumes were significantly associated with poorer cognitive performance (p < .0001). Presence of WMHs leads to systematic inaccuracies in GM segmentations, particularly for the caudate, which can also change clinical associations. While specifically measured for the Freesurfer toolkit, this problem likely affects other algorithms.

Functional connectivity changes in cerebral small vessel disease - a systematic review of the resting-state MRI literature

BACKGROUND

Cerebral small vessel disease (CSVD) is a common neurological disease present in the ageing population that is associated with an increased risk of dementia and stroke. Damage to white matter tracts compromises the substrate for interneuronal connectivity. Analysing resting-state functional magnetic resonance imaging (fMRI) can reveal dysfunctional patterns of brain connectivity and contribute to explaining the pathophysiology of clinical phenotypes in CSVD.

MATERIALS AND METHODS

This systematic review provides an overview of methods and results of recent resting-state functional MRI studies in patients with CSVD. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) protocol, a systematic search of the literature was performed.

RESULTS

Of 493 studies that were screened, 44 reports were identified that investigated resting-state fMRI connectivity in the context of cerebral small vessel disease. The risk of bias and heterogeneity of results were moderate to high. Patterns associated with CSVD included disturbed connectivity within and between intrinsic brain networks, in particular the default mode, dorsal attention, frontoparietal control, and salience networks; decoupling of neuronal activity along an anterior-posterior axis; and increases in functional connectivity in the early stage of the disease.

CONCLUSION

The recent literature provides further evidence for a functional disconnection model of cognitive impairment in CSVD. We suggest that the salience network might play a hitherto underappreciated role in this model. Low quality of evidence and the lack of preregistered multi-centre studies remain challenges to be overcome in the future.

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

OBJECTIVES

Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field.

DESIGN

Scoping review.

SETTING

Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison.

RESULTS

Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity.

CONCLUSIONS

The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

The Longitudinal Assessment of Neuropsychiatric Symptoms in Mild Cognitive Impairment and Alzheimer's Disease and Their Association With White Matter Hyperintensities in the National Alzheimer's Coordinating Center's Uniform Data Set

BACKGROUND

Neuropsychiatric symptoms (NPSs) are common in Alzheimer's disease (AD). NPSs contribute to patients' distress, caregiver burden, and institutionalization. White matter hyperintensities (WMHs) appear on magnetic resonance imaging, usually indicative of cerebrovascular disease. WMHs have been associated with certain NPSs. We aimed to assess the relationship between WMH and NPS severity in mild cognitive impairment (MCI) due to AD (MCI-AD) and in AD and to assess the ability of WMHs to predict NPS progression. Data were obtained from the National Alzheimer's Coordinating Center.

METHODS

A total of 252 participants (114 with MCI-AD and 138 with AD) were used in this study. Baseline WMHs were quantified using an automated segmentation technique. NPSs were measured using the Neuropsychiatric Inventory. Mixed-effect models and correlations were used to determine the relationship between WMHs and NPSs.

RESULTS

Longitudinal mixed-effect models revealed a significant relationship between increase in Neuropsychiatric Inventory total scores and baseline WMHs (p = .014). There was a significant relationship between baseline WMHs and an increase in delusions (p = .023), hallucinations (p = .040), agitation (p = .093), depression (p = .017), and irritability (p = .002). Correlation plot analysis showed that baseline whole-brain WMHs predicted change in future Neuropsychiatric Inventory total scores (r = .169, p = .008) and predicted change in future agitation severity scores (r = .165, p = .009). WMHs in the temporal lobes (r = .169, p = .008) and frontal lobes (r = .153, p = .016) contributed most to this change.

CONCLUSIONS

Depression, irritability, and agitation are common NPSs and very distressful to patients and caregivers. Our findings of increased NPS severity over time in MCI-AD and AD with increased WMHs have important implications for treatment, arguing for aggressive treatment of vascular risk factors in patients with MCI-AD or AD.

Cortical Thickness Estimation in Individuals With Cerebral Small Vessel Disease, Focal Atrophy, and Chronic Stroke Lesions

BACKGROUND

Regional changes to cortical thickness in individuals with neurodegenerative and cerebrovascular diseases (CVD) can be estimated using specialized neuroimaging software. However, the presence of cerebral small vessel disease, focal atrophy, and cortico-subcortical stroke lesions, pose significant challenges that increase the likelihood of misclassification errors and segmentation failures.

PURPOSE

The main goal of this study was to examine a correction procedure developed for enhancing FreeSurfer's (FS's) cortical thickness estimation tool, particularly when applied to the most challenging MRI obtained from participants with chronic stroke and CVD, with varying degrees of neurovascular lesions and brain atrophy.

METHODS

In 155 CVD participants enrolled in the Ontario Neurodegenerative Disease Research Initiative (ONDRI), FS outputs were compared between a fully automated, unmodified procedure and a corrected procedure that accounted for potential sources of error due to atrophy and neurovascular lesions. Quality control (QC) measures were obtained from both procedures. Association between cortical thickness and global cognitive status as assessed by the Montreal Cognitive Assessment (MoCA) score was also investigated from both procedures.

RESULTS

Corrected procedures increased "Acceptable" QC ratings from 18 to 76% for the cortical ribbon and from 38 to 92% for tissue segmentation. Corrected procedures reduced "Fail" ratings from 11 to 0% for the cortical ribbon and 62 to 8% for tissue segmentation. FS-based segmentation of T1-weighted white matter hypointensities were significantly greater in the corrected procedure (5.8 mL vs. 15.9 mL, p < 0.001). The unmodified procedure yielded no significant associations with global cognitive status, whereas the corrected procedure yielded positive associations between MoCA total score and clusters of cortical thickness in the left superior parietal (p = 0.018) and left insula (p = 0.04) regions. Further analyses with the corrected cortical thickness results and MoCA subscores showed a positive association between left superior parietal cortical thickness and Attention (p < 0.001).

CONCLUSION

These findings suggest that correction procedures which account for brain atrophy and neurovascular lesions can significantly improve FS's segmentation results and reduce failure rates, thus maximizing power by preventing the loss of our important study participants. Future work will examine relationships between cortical thickness, cerebral small vessel disease, and cognitive dysfunction due to neurodegenerative disease in the ONDRI study.

The temporal relationships between white matter hyperintensities, neurodegeneration, amyloid beta, and cognition

Introduction

Cognitive decline in Alzheimer's disease is associated with amyloid beta (Aβ) accumulation, neurodegeneration, and cerebral small vessel disease, but the temporal relationships among these factors is not well established.

Methods

Data included white matter hyperintensity (WMH) load, gray matter (GM) atrophy and Alzheimer's Disease Assessment Scale‐Cognitive‐Plus (ADAS13) scores for 720 participants and cerebrospinal fluid amyloid (Aβ1–42) for 461 participants from the Alzheimer's Disease Neuroimaging Initiative. Linear regressions were used to assess the relationships among baseline WMH, GM, and Aβ1–42 to changes in WMH, GM, Aβ1–42, and cognition at 1‐year follow‐up.

Results

Baseline WMHs and Aβ1–42 predicted WMH increase and GM atrophy. Baseline WMHs and Aβ1–42 predicted worsening cognition. Only baseline Aβ1–42 predicted change in Aβ1–42.

Discussion

Baseline WMHs lead to greater future GM atrophy and cognitive decline, suggesting that WM damage precedes neurodegeneration and cognitive decline. Baseline Aβ1–42 predicted WMH increase, suggesting a potential role of amyloid in WM damage.

BISON: Brain tissue segmentation pipeline using T1 -weighted magnetic resonance images and a random forest classifier

PURPOSE

Tissue segmentation from T₁ -weighted (T1W) MRI is a critical requirement in many neuroscience and clinical applications. However, accurate tissue segmentation is challenging because of the variabilities in tissue intensity profiles caused by differences in scanner models, acquisition protocols, and age. In addition, many methods assume healthy anatomy and fail in the presence of pathology such as white matter hyperintensities (WMHs). We present BISON (Brain tISsue segmentatiON), a new pipeline for tissue segmentation using a random forest classifier and a set of intensity and location priors based on T1W MRI.

METHODS

BISON was developed and cross-validated using multiscanner manual labels of 72 subjects aged 5 to 96 years. We also assessed the test-retest reliability of BISON on two data sets: 20 subjects with scan/rescan MR images and manual segmentations and 90 scans from a single individual. The results were compared against Atropos, a state-of-the-art commonly used tissue classification method from advanced normalization tools (ANTs).

RESULTS

BISON cross-validation dice kappa values against manual segmentations of 72 MRI volumes yielded κ_GM = 0.88, κ_WM = 0.85, κ_CSF = 0.77, outperforming Atropos (κ_GM = 0.79, κ_WM = 0.84, κ_CSF = 0.64), test-retest values on 20 subjects of κ_GM = 0.94, κ_WM = 0.92, κ_CSF = 0.77 outperforming both manual (κ_GM = 0.92, κ_WM = 0.91, κ_CSF =0.74) and Atropos (κ_GM = 0.87, κ_WM = 0.92, κ_CSF = 0.79). Finally, BISON outperformed Atropos, FAST (fast automated segmentation tool) from the FMRIB (Functional Magnetic Resonance Imaging of the Brain) Software Library, and SPM12 (statistical parametric mapping 12) in the presence of WMHs.

CONCLUSION

BISON can provide accurate and robust segmentations in data from various age ranges and scanner models, making it ideal for performing tissue classification in large multicenter and multiscanner databases.

Deep Spatial-Temporal Feature Fusion From Adaptive Dynamic Functional Connectivity for MCI Identification

Dynamic functional connectivity (dFC) analysis using resting-state functional Magnetic Resonance Imaging (rs-fMRI) is currently an advanced technique for capturing the dynamic changes of neural activities in brain disease identification. Most existing dFC modeling methods extract dynamic interaction information by using the sliding window-based correlation, whose performance is very sensitive to window parameters. Because few studies can convincingly identify the optimal combination of window parameters, sliding window-based correlation may not be the optimal way to capture the temporal variability of brain activity. In this paper, we propose a novel adaptive dFC model, aided by a deep spatial-temporal feature fusion method, for mild cognitive impairment (MCI) identification. Specifically, we adopt an adaptive Ultra-weighted-lasso recursive least squares algorithm to estimate the adaptive dFC, which effectively alleviates the problem of parameter optimization. Then, we extract temporal and spatial features from the adaptive dFC. In order to generate coarser multi-domain representations for subsequent classification, the temporal and spatial features are further mapped into comprehensive fused features with a deep feature fusion method. Experimental results show that the classification accuracy of our proposed method is reached to 87.7%, which is at least 5.5% improvement than the state-of-the-art methods. These results elucidate the superiority of the proposed method for MCI classification, indicating its effectiveness in the early identification of brain abnormalities.

White matter hyperintensities and neuropsychiatric symptoms in mild cognitive impairment and Alzheimer's disease

•

White matter hyperintensities play a larger role than grey matter atrophy in neuropsychiatric symptoms in AD/MCI.

•

Greater white matter hyperintensities are related to lower grey matter volumes.

•

Frontotemporal atrophy implicated in neuropsychiatric symptoms.

Neuropsychiatric symptoms (NPS), such as apathy, irritability and depression, are frequently encountered in patients with Alzheimer’s disease (AD). Focal grey matter atrophy has been linked to NPS development. Cerebrovascular disease is common among AD patients and can be detected on MRI as white matter hyperintensities (WMH). In this longitudinal study, the relative contribution of WMH burden and GM atrophy to NPS was evaluated in a cohort of mild cognitive impairment (MCI), AD and normal controls. This study included 121 AD, 315 MCI and 225 normal control subjects from the Alzheimer’s Disease Neuroimaging Initiative. NPS were assessed using the Neuropsychiatric Inventory and grouped into hyperactivity, psychosis, affective and apathy subsyndromes. WMH were measured using an automatic segmentation technique and mean deformation-based morphometry (DBM) was used to measure atrophy of grey matter regions. Linear mixed-effects models found focal grey matter atrophy and WMH volume both contributed significantly to NPS subsyndromes in MCI and AD subjects, however, WMH burden played a greater role. This study could provide a better understanding of the pathophysiology of NPS in AD and support the monitoring and control of vascular risk factors.

White Matter Hyperintensities Mediate Impact of Dysautonomia on Cognition in Parkinson's Disease

Background

Patients with Parkinson's disease (PD) present with a broad spectrum of nonmotor features including autonomic disorders. More severe autonomic dysfunction in PD is associated with increased cognitive deficits. The presence of cerebral small-vessel disease, measured by T2-weighted magnetic resonance imaging white matter hyperintensity (WMH) burden, is also observed in patients with PD with faster cognitive decline.

Objective

To investigate whether baseline orthostatic hypotension and autonomic dysfunction in early-stage PD affect later cognitive decline via mediation through cerebral small-vessel disease.

Methods

De novo PD patients (N = 365) and age-matched controls (N = 174) with baseline T2-weighted/ fluid-attenuated inversion recovery scans were selected from the Parkinson's Progression Markers Initiative. WMHs were automatically segmented. Mediation analysis was used to assess whether WMH load mediates the effect of orthostatic hypotension and autonomic dysfunction (measured by Scales for Outcomes in Parkinson's Disease-Autonomic) on future cognitive decline (measured by Montreal Cognitive Assessment) in an average of 4 years of follow-up.

Results

Mediation analysis supported the existence of a full mediation of WMHs on the effect of diastolic orthostatic hypotension in patients with PD and future cognitive decline (average causal mediation effect: ab = -0.032, 95% confidence interval = -0.064 to -0.01, P = 0.01). There was also a partial mediation for overall autonomic dysfunction (ab = -0.027, 95% confidence interval = -0.054 to 0.00, P = 0.02).

Conclusions

WMHs fully mediate the effect of diastolic orthostatic hypotension and partially mediate the effect of autonomic dysregulation on future cognitive decline in patients with PD. Our findings support the hypothesis that autonomic dysfunction in early clinical stages predisposes the brain to WMHs through dysregulation of the blood flow in the small vessels. This in turn increases the risk of future cognitive impairment in early PD.

Cognitive and motor correlates of grey and white matter pathology in Parkinson's disease

INTRODUCTION

Previous studies have found associations between grey matter atrophy and white matter hyperintensities (WMH) of vascular origin with cognitive and motor deficits in Parkinson's disease (PD). Here we investigate these relationships in a sample of PD patients and age-matched healthy controls.

METHODS

Data included 50 PD patients and 45 age-matched controls with T1-weighted and FLAIR scans at baseline, 18-months, and 36-months follow-up. Deformation-based morphometry was used to measure grey matter atrophy. SNIPE (Scoring by Nonlocal Image Patch Estimator) was used to measure Alzheimer's disease-like textural patterns in the hippocampi. WMHs were segmented using T1-weighted and FLAIR images. The relationship between MRI features and clinical scores was assessed using mixed-effects models. The motor subscore of the Unified Parkinson's Disease Rating Scale (UPDRSIII), number of steps in a walking trial, and Dementia Rating Scale (DRS) were used respectively as measures of motor function, gait, and cognition.

RESULTS

Substantia nigra atrophy was significantly associated with motor deficits, with a greater impact in PDs (p < 0.05). Hippocampal SNIPE scores were associated with cognitve decline in both PD and controls (p < 0.01). WMH burden was significantly associated with cognitive decline and increased motor deficits in the PD group, and gait deficits in both PD and controls (p < 0.03).

CONCLUSION

While substantia nigra atrophy and WMH burden were significantly associated with additional motor deficits, WMH burden and hippocampal atrophy were associated with cognitive deficits in PD patients. These results suggest an additive contribution of both grey and white matter damage to the motor and cognitive deficits in PD.

Systemic Tumor Necrosis Factor-Alpha Trajectories Relate to Brain Health in Typically Aging Older Adults

BACKGROUND

Central nervous system levels of tumor necrosis factor-alpha (TNF-α), a pro-inflammatory cytokine, regulate the neuroinflammatory response and may play a role in age-related neurodegenerative diseases. The longitudinal relation between peripheral levels of TNF-α and typical brain aging is understudied. We hypothesized that within-person increases in systemic TNF-α would track with poorer brain health outcomes in functionally normal adults.

METHODS

Plasma-based TNF-α concentrations (pg/mL; fasting morning draws) and magnetic resonance imaging were acquired in 424 functionally intact adults (mean age = 71) followed annually for up to 8.4 years (mean follow-up = 2.2 years). Brain outcomes included total gray matter volume and white matter hyperintensities. Cognitive outcomes included composites of memory, executive functioning, and processing speed, as well as Mini-Mental State Examination total scores. Longitudinal mixed-effects models were used, controlling for age, sex, education, and total intracranial volume, as appropriate.

RESULTS

TNF-α concentrations significantly increased over time (p < .001). Linear increases in within-person TNF-α were longitudinally associated with declines in gray matter volume (p < .001) and increases in white matter hyperintensities (p = .003). Exploratory analyses suggested that the relation between TNF-α and gray matter volume was curvilinear (TNF-α 2p = .002), such that initial increases in inflammation were associated with more precipitous atrophy. There was a negative linear relationship of within-person changes in TNF-α to Mini-Mental State Examination scores over time (p = .036) but not the cognitive composites (all ps >.05).

CONCLUSION

Systemic inflammation, as indexed by plasma TNF-α, holds potential as a biomarker for age-related declines in brain health.

Plasma biomarkers of astrocytic and neuronal dysfunction in early- and late-onset Alzheimer's disease

INTRODUCTION

We investigated plasma proteomic markers of astrocytopathy, brain degeneration, plasticity, and inflammation in sporadic early-onset versus late-onset Alzheimer's disease (EOAD and LOAD).

METHODS

Plasma was analyzed using ultra-sensitive immuno-based assays from 33 EOAD, 30 LOAD, and 36 functionally normal older adults.

RESULTS

Principle component analyses identified 3 factors: trophic (BDNF, VEGF, TGFβ), degenerative (GFAP, NfL), and inflammatory (TNFα, IL-6, IP-10, IL-10). Trophic factor was elevated in both AD groups and associated with cognition and gray matter volumes. Degenerative factor was elevated in EOAD, with higher levels associated with worse functioning in this group. Biomarkers of inflammation were not significantly different between groups and were only associated with age.

DISUCSSION

Plasma proteomic biomarkers provide novel means of investigating molecular processes in vivo and their contributions to clinical outcomes. We present initial investigations of several of these fluid biomarkers, capturing aspects of astrocytopathy, neuronal injury, cellular plasticity, and inflammation in EOAD versus LOAD.

Cornea: A Window to White Matter Changes in Stroke; Corneal Confocal Microscopy a Surrogate Marker for the Presence and Severity of White Matter Hyperintensities in Ischemic Stroke

PURPOSE

The presence of white matter hyperintensities (WMH) on MRI imaging confers an increased risk of stroke, dementia, and death. Corneal confocal microscopy (CCM) can detect nerve injury non-invasively and may be a useful surrogate marker for WMH. The objective is to determine whether corneal nerve pathology identified using CCM is associated with the presence of WMH in patients with acute ischemic stroke.

METHODS

This is a cross-sectional study where 196 consecutive individuals with acute ischemic stroke were enrolled and underwent neurological examination, MRI brain imaging and CCM. Participants underwent blinded quantification of WMH and corneal nerve fiber density (CNFD), corneal nerve branch density (CNBD) and corneal nerve fiber length (CNFL).

RESULTS

The prevalence of hypertension [P = .013] was significantly higher and CNFD [P = .031] was significantly lower in patients with WMH compared to those without WMH. CNFD and CNFL were significantly lower in patients with DM without WMH [P = .008, P = .019] and in patients with DM and WMH [P = .042, P = .024] compared to patients without DM or WMH, respectively. In a multivariate model, a 1-unit decrease in the CNFD increased the risk of WMH by 6%, after adjusting for age, DM, gender, dyslipidemia, metabolic syndrome, smoking, and HbA1c. DM was associated with a decrease in all CCM parameters but was not a significant independent factor associated with WMH.

CONCLUSIONS

CCM demonstrates corneal nerve pathology, which is associated with the presence of WMH in participants with acute ischemic stroke. CCM may be a useful surrogate imaging marker for the presence and severity of WMHs.

Medical Image Synthesis via Deep Learning

Medical images have been widely used in clinics, providing visual representations of under-skin tissues in human body. By applying different imaging protocols, diverse modalities of medical images with unique characteristics of visualization can be produced. Considering the cost of scanning high-quality single modality images or homogeneous multiple modalities of images, medical image synthesis methods have been extensively explored for clinical applications. Among them, deep learning approaches, especially convolutional neural networks (CNNs) and generative adversarial networks (GANs), have rapidly become dominating for medical image synthesis in recent years. In this chapter, based on a general review of the medical image synthesis methods, we will focus on introducing typical CNNs and GANs models for medical image synthesis. Especially, we will elaborate our recent work about low-dose to high-dose PET image synthesis, and cross-modality MR image synthesis, using these models.

Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge

Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. The automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their methods on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge. Sixty T1 + FLAIR images from three MR scanners were released with the manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. The segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: 1) Dice similarity coefficient; 2) modified Hausdorff distance (95th percentile); 3) absolute log-transformed volume difference; 4) sensitivity for detecting individual lesions; and 5) F1-score for individual lesions. In addition, the methods were ranked on their inter-scanner robustness; 20 participants submitted their methods for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all the methods generalize to unseen scanners. The challenge remains open for future submissions and provides a public platform for method evaluation.

A longitudinal characterization of perfusion in the aging brain and associations with cognition and neural structure

Cerebral perfusion declines across the lifespan and is altered in the early stages of several age-related neuropathologies. Little is known, however, about the longitudinal evolution of perfusion in healthy older adults, particularly when perfusion is quantified using magnetic resonance imaging with arterial spin labeling (ASL). The objective was to characterize longitudinal perfusion in typically aging adults and elucidate associations with cognition and brain structure. Adults who were functionally intact at baseline (n = 161, ages 47-89) underwent ASL imaging to quantify whole-brain gray matter perfusion; a subset (n = 136) had repeated imaging (average follow-up: 2.3 years). Neuropsychological testing at each visit was summarized into executive function, memory, and processing speed composites. Global gray matter volume, white matter microstructure (mean diffusivity), and white matter hyperintensities were also quantified. We assessed baseline associations among perfusion, cognition, and brain structure using linear regression, and longitudinal relationships using linear mixed effects models. Greater baseline perfusion, particularly in the left dorsolateral prefrontal cortex and right thalamus, was associated with better executive functions. Greater whole-brain perfusion loss was associated with worsening brain structure and declining processing speed. This study helps validate noninvasive MRI-based perfusion imaging and underscores the importance of cerebral blood flow in cognitive aging.

Brain Amyloid PET Tracer Delivery is Related to White Matter Integrity in Patients with Mild Cognitive Impairment

BACKGROUND AND PURPOSE

Amyloid deposition, tau neurofibrillary tangles, and cerebrovascular dysfunction are important pathophysiologic features in Alzheimer's disease. Pittsburgh compound B ([¹¹ C]-PIB) is a positron emission tomography (PET) radiotracer used to quantify amyloid deposition in vivo. In addition, certain models of [¹¹ C]-PIB delivery reflect cerebral blood flow rather than amyloid plaques. As cerebral blood flow and perfusion deficits are associated with white matter pathology, we hypothesized that [¹¹ C]-PIB delivery in white matter regions may reflect white matter integrity.

METHODS

We obtained [¹¹ C]-PIB-PET scans and quantified white matter hyperintensities and global fractional anisotropy on magnetic resonance images as biomarkers of white matter pathology in 34 older participants with mild cognitive impairment with or without a history of major depressive disorder. We analyzed the [¹¹ C]-PIB time-activity curve data with models associated with cerebral blood flow: the early maximum standard uptake value and the relative delivery parameter R1. We used a global white matter region of interest.

RESULTS

Both of the partial-volume corrected PET parameters were correlated with white matter hyperintensities and fractional anisotropy.

CONCLUSION

Future studies are warranted to explore whether [¹¹ C]-PIB PET is a "triple biomarker" that may provide information about amyloid deposition, cerebral blood flow, and white matter pathology.