Ventricular enlargement as a possible measure of Alzheimer's disease progression validated using the Alzheimer's disease neuroimaging initiative database

Transformer-based approaches for neuroimaging: an in-depth review of their role in classification and regression tasks

In the ever-evolving landscape of deep learning (DL), the transformer model emerges as a formidable neural network architecture, gaining significant traction in neuroimaging-based classification and regression tasks. This paper presents an extensive examination of transformer's application in neuroimaging, surveying recent literature to elucidate its current status and research advancement. Commencing with an exposition on the fundamental principles and structures of the transformer model and its variants, this review navigates through the methodologies and experimental findings pertaining to their utilization in neuroimage classification and regression tasks. We highlight the transformer model's prowess in neuroimaging, showcasing its exceptional performance in classification endeavors while also showcasing its burgeoning potential in regression tasks. Concluding with an assessment of prevailing challenges and future trajectories, this paper proffers insights into prospective research directions. By elucidating the current landscape and envisaging future trends, this review enhances comprehension of transformer's role in neuroimaging tasks, furnishing valuable guidance for further inquiry.

Supervised Functional Principal Component Analysis Under the Mixture Cure Rate Model: An Application to Alzheimer'S Disease

Brain imaging data is one of the primary predictors for assessing the risk of Alzheimer's disease (AD). This study aims to extract image-based features associated with the possibly right-censored time-to-event outcomes and to improve predictive performance. While the functional proportional hazards model is well-studied in the literature, these studies often do not consider the existence of patients who have a very low risk and are approximately insusceptible to AD. We introduce a functional mixture cure rate model that extends the proportional hazards model by allowing a proportion of event-free patients. We propose a novel supervised functional principal component analysis (sFPCA) method to extract image features associated with AD risk while accounting for the complexity arising from right censoring. The proposed method accommodates the irregular boundary issue inherent in brain images with bivariate splines over triangulations. We demonstrate the advantages of the proposed method through extensive simulation studies and provide an application to the Alzheimer's Disease Neuroimaging Initiative (ADNI) study.

Lipidome disruption in Alzheimer's disease brain: detection, pathological mechanisms, and therapeutic implications

Alzheimer's disease (AD) is among the most devastating neurodegenerative disorders with limited treatment options. Emerging evidence points to the involvement of lipid dysregulation in the development of AD. Nevertheless, the precise lipidomic landscape and the mechanistic roles of lipids in disease pathology remain poorly understood. This review aims to highlight the significance of lipidomics and lipid-targeting approaches in the diagnosis and treatment of AD. We summarized the connection between lipid dysregulation in the human brain and AD at both genetic and lipid species levels. We briefly introduced lipidomics technologies and discussed potential challenges and areas of future advancements in the lipidomics field for AD research. To elucidate the central role of lipids in converging multiple pathological aspects of AD, we reviewed the current knowledge on the interplay between lipids and major AD features, including amyloid beta, tau, and neuroinflammation. Finally, we assessed the progresses and obstacles in lipid-based therapeutics and proposed potential strategies for leveraging lipidomics in the treatment of AD.

Biomarker Investigation Using Multiple Brain Measures from MRI Through Explainable Artificial Intelligence in Alzheimer's Disease Classification

As the leading cause of dementia worldwide, Alzheimer's Disease (AD) has prompted significant interest in developing Deep Learning (DL) approaches for its classification. However, it currently remains unclear whether these models rely on established biological indicators. This work compares a novel DL model using structural connectivity (namely, BC-GCN-SE adapted from functional connectivity tasks) with an established model using structural magnetic resonance imaging (MRI) scans (namely, ResNet18). Unlike most studies primarily focusing on performance, our work places explainability at the forefront. Specifically, we define a novel Explainable Artificial Intelligence (XAI) metric, based on gradient-weighted class activation mapping. Its aim is quantitatively measuring how effectively these models fare against established AD biomarkers in their decision-making. The XAI assessment was conducted across 132 brain parcels. Results were compared to AD-relevant regions to measure adherence to domain knowledge. Then, differences in explainability patterns between the two models were assessed to explore the insights offered by each piece of data (i.e., MRI vs. connectivity). Classification performance was satisfactory in terms of both the median true positive (ResNet18: 0.817, BC-GCN-SE: 0.703) and true negative rates (ResNet18: 0.816; BC-GCN-SE: 0.738). Statistical tests (p < 0.05) and ranking of the 15% most relevant parcels revealed the involvement of target areas: the medial temporal lobe for ResNet18 and the default mode network for BC-GCN-SE. Additionally, our findings suggest that different imaging modalities provide complementary information to DL models. This lays the foundation for bioengineering advancements in developing more comprehensive and trustworthy DL models, potentially enhancing their applicability as diagnostic support tools for neurodegenerative diseases.

Multimodal imaging of murine cerebrovascular dynamics induced by transcranial pulse stimulation

INTRODUCTION

Transcranial pulse stimulation (TPS) is increasingly being investigated as a promising potential treatment for Alzheimer's disease (AD). Although the safety and preliminary clinical efficacy of TPS short pulses have been supported by neuropsychological scores in treated AD patients, its fundamental mechanisms are uncharted.

METHODS

Herein, we used a multi-modal preclinical imaging platform combining real-time volumetric optoacoustic tomography, contrast-enhanced magnetic resonance imaging, and ex vivo immunofluorescence to comprehensively analyze structural and hemodynamic effects induced by TPS. Cohorts of healthy and AD transgenic mice were imaged during and after TPS exposure at various per-pulse energy levels.

RESULTS

TPS enhanced the microvascular network, whereas the blood-brain barrier remained intact following the procedure. Notably, higher pulse energies were necessary to induce hemodynamic changes in AD mice, arguably due to their impacted vessels.

DISCUSSION

These findings shed light on cerebrovascular dynamics induced by TPS treatment, and hence are expected to assist improving safety and therapeutic outcomes.

HIGHLIGHTS

·Transcranial pulse stimulation (TPS) facilitates transcranial wave propagation using short pulses to avoid tissue heating. ·Preclinical multi-modal imaging combines real-time volumetric optoacoustic (OA) tomography, contrast-enhanced magnetic resonance imaging (CE-MRI), and ex vivo immunofluorescence to comprehensively analyze structural and hemodynamic effects induced by TPS. ·Blood volume enhancement in microvascular networks was reproducibly observed with real-time OA imaging during TPS stimulation. ·CE-MRI and gross pathology further confirmed that the brain architecture was maintained intact without blood-brain barrier (BBB) opening after TPS exposure, thus validating the safety of the procedure. ·Higher pulse energies were necessary to induce hemodynamic changes in AD compared to wild-type animals, arguably due to their pathological vessels.

Improved deep canonical correlation fusion approach for detection of early mild cognitive impairment

Detection of early mild cognitive impairment (EMCI) is clinically challenging as it involves subtle alterations in multiple brain sub-anatomic regions. Among different brain regions, the corpus callosum and lateral ventricles are primarily affected due to EMCI. In this study, an improved deep canonical correlation analysis (CCA) based framework is proposed to fuse magnetic resonance (MR) image features from lateral ventricular and corpus callosal structures for the detection of EMCI condition. For this, obtained structural MR images of healthy controls and EMCI subjects are preprocessed. Lateral ventricles and corpus callosum structures are segmented from these images and features are extracted. Extracted features from different brain structures are fused using non-linear orthogonal iteration-based deep CCA. Fused features are employed to differentiate healthy controls and EMCI condition using extreme learning machine classifier. Results indicate that fused callosal and ventricular features are able to detect EMCI. Improved deep CCA algorithm with tuned hyperparameters achieves the highest classifier performance with an F-score of 82.15%. The proposed framework is compared with state-of-the-art CCA approaches, and the results demonstrate its improved performance in EMCI detection. This highlights the potential of the proposed framework in the automated diagnosis of preclinical MCI conditions.

A machine learning approach for identifying anatomical biomarkers of early mild cognitive impairment

Background

Alzheimer's Disease (AD) poses a major challenge as a neurodegenerative disorder, and early detection is critical for effective intervention. Magnetic resonance imaging (MRI) is a critical tool in AD research due to its availability and cost-effectiveness in clinical settings.

Objective

This study aims to conduct a comprehensive analysis of machine learning (ML) methods for MRI-based biomarker selection and classification to investigate early cognitive decline in AD. The focus to discriminate between classifying healthy control (HC) participants who remained stable and those who developed mild cognitive impairment (MCI) within five years (unstable HC or uHC).

Methods

3-Tesla (3T) MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies 3 (OASIS-3) were used, focusing on HC and uHC groups. Freesurfer's recon-all and other tools were used to extract anatomical biomarkers from subcortical and cortical brain regions. ML techniques were applied for feature selection and classification, using the MATLAB Classification Learner (MCL) app for initial analysis, followed by advanced methods such as nested cross-validation and Bayesian optimization, which were evaluated within a Monte Carlo replication analysis as implemented in our customized pipeline. Additionally, polynomial regression-based data harmonization techniques were used to enhance ML and statistical analysis. In our study, ML classifiers were evaluated using performance metrics such as Accuracy (Acc), area under the receiver operating characteristic curve (AROC), F1-score, and a normalized Matthew's correlation coefficient (MCC').

Results

Feature selection consistently identified biomarkers across ADNI and OASIS-3, with the entorhinal, hippocampus, lateral ventricle, and lateral orbitofrontal regions being the most affected. Classification results varied between balanced and imbalanced datasets and between ADNI and OASIS-3. For ADNI balanced datasets, the naíve Bayes model using z-score harmonization and ReliefF feature selection performed best (Acc = 69.17%, AROC = 77.73%, F1 = 69.21%, MCC' = 69.28%). For OASIS-3 balanced datasets, SVM with zscore-corrected data outperformed others (Acc = 66.58%, AROC = 72.01%, MCC' = 66.78%), while logistic regression had the best F1-score (66.68%). In imbalanced data, RUSBoost showed the strongest overall performance on ADNI (F1 = 50.60%, AROC = 81.54%) and OASIS-3 (MCC' = 63.31%). Support vector machine (SVM) excelled on ADNI in terms of Acc (82.93%) and MCC' (70.21%), while naïve Bayes performed best on OASIS-3 by F1 (42.54%) and AROC (70.33%).

Conclusion

Data harmonization significantly improved the consistency and performance of feature selection and ML classification, with z-score harmonization yielding the best results. This study also highlights the importance of nested cross-validation (CV) to control overfitting and the potential of a semi-automatic pipeline for early AD detection using MRI, with future applications integrating other neuroimaging data to enhance prediction.

The effects of locus coeruleus ablation on mouse brain volume and microstructure evaluated by high-field MRI

The locus coeruleus (LC) produces most of the brain's noradrenaline (NA). Among its many roles, NA is often said to be neuroprotective and important for brain upkeep. For this reason, loss of LC integrity is thought to impact brain volume and microstructure as well as plasticity broadly. LC dysfunction is also a suspected driver in the development of neurodegenerative diseases. Nevertheless, the impact of LC dysfunction on the gross structure and microstructure of normal brains is not well-studied. We employed high-field ex vivo magnetic resonance imaging (MRI) to investigate brain volumetrics and microstructure in control (CON) mice and mice with LC ablation (LCA) at two ages, representing the developing brain and the fully matured brain. These whole-brain methods are known to be capable of detecting subtle morphological changes and brain microstructural remodeling. We found mice behavior consistent with histologically confirmed LC ablation. However, MRI showed no difference between CON and LCA groups with regard to brain size, relative regional volumes, or regional microstructural indices. Our findings suggest that LC-NA is not needed for postnatal brain maturation and growth in mice. Nor is it required for maintenance in the normal adult mouse brain, as no atrophy or microstructural aberration is detected after weeks of LC dysfunction. This adds clarity to the often-encountered notion that LC-NA is important for brain "trophic support" as it shows that such effects are likely most relevant to mechanisms related to brain plasticity and neuroprotection in the (pre)diseased brain.

Portable, low-field magnetic resonance imaging for evaluation of Alzheimer's disease

Portable, low-field magnetic resonance imaging (LF-MRI) of the brain may facilitate point-of-care assessment of patients with Alzheimer's disease (AD) in settings where conventional MRI cannot. However, image quality is limited by a lower signal-to-noise ratio. Here, we optimize LF-MRI acquisition and develop a freely available machine learning pipeline to quantify brain morphometry and white matter hyperintensities (WMH). We validate the pipeline and apply it to outpatients presenting with mild cognitive impairment or dementia due to AD. We find hippocampal volumes from ≤ 3 mm isotropic LF-MRI scans have agreement with conventional MRI and are more accurate than anisotropic counterparts. We also show WMH volume has agreement between manual segmentation and the automated pipeline. The increased availability and reduced cost of LF-MRI, in combination with our machine learning pipeline, has the potential to increase access to neuroimaging for dementia.

Myelin Lipid Alterations in Neurodegenerative Diseases: Landscape and Pathogenic Implications

Significance: Lipids, which constitute the highest portion (over 50%) of brain dry mass, are crucial for brain integrity, energy homeostasis, and signaling regulation. Emerging evidence revealed that lipid profile alterations and abnormal lipid metabolism occur during normal aging and in different forms of neurodegenerative diseases. Moreover, increasing genome-wide association studies have validated new targets on lipid-associated pathways involved in disease development. Myelin, the protective sheath surrounding axons, is crucial for efficient neural signaling transduction. As the primary site enriched with lipids, impairments of myelin are increasingly recognized as playing significant and complex roles in various neurodegenerative diseases, beyond simply being secondary effects of neuronal loss. Recent Advances: With advances in the lipidomics field, myelin lipid alterations and their roles in contributing to or reflecting the progression of diseases, including Alzheimer's disease, Parkinson's disease, Huntington's disease, amyotrophic lateral sclerosis, multiple sclerosis, and others, have recently caught great attention. Critical Issues: This review summarizes recent findings of myelin lipid alterations in the five most common neurodegenerative diseases and discusses their implications in disease pathogenesis. Future Directions: By highlighting myelin lipid abnormalities in neurodegenerative diseases, this review aims to encourage further research focused on lipids and the development of new lipid-oriented therapeutic approaches in this area. Antioxid. Redox Signal. 00, 000-000.

Mediation Analysis with Multiple Exposures and Multiple Mediators

A mediation analysis approach is proposed for multiple exposures, multiple mediators, and a continuous scalar outcome under the linear structural equation modeling framework. It assumes that there exist orthogonal components that demonstrate parallel mediation mechanisms on the outcome, and thus is named principal component mediation analysis (PCMA). Likelihood-based estimators are introduced for simultaneous estimation of the component projections and effect parameters. The asymptotic distribution of the estimators is derived for low-dimensional data. A bootstrap procedure is introduced for inference. Simulation studies illustrate the superior performance of the proposed approach. Applied to a proteomics-imaging dataset from the Alzheimer's disease neuroimaging initiative (ADNI), the proposed framework identifies protein deposition - brain atrophy - memory deficit mechanisms consistent with existing knowledge and suggests potential AD pathology by integrating data collected from different modalities.

Detection of Alzheimer's Disease Using Hybrid Meta-ROI of MRI Structural Images

BACKGROUND

The averaged cortical thickness of meta-ROI is currently being used for the diagnosis and prognosis of Alzheimer's disease (AD) using structural MRI brain images. The purpose of this work is to present a hybrid meta-ROI for the detection of AD.

METHODS

The AD detectability of selected cortical and volumetric regions of the brain was examined using signal detection theory. The top performing cortical and volumetric ROIs were taken as input nodes to the artificial neural network (ANN) for AD classification.

RESULTS

An AD diagnostic accuracy of 91.9% was achieved by using a hybrid meta-ROI consisting of thicknesses of entorhinal and middle temporal cortices, and the volumes of the hippocampus and inferior lateral ventricles. Pairing inferior lateral ventricle dilation with hippocampal volume reduction improves AD detectability by 5.1%.

CONCLUSIONS

Hybrid meta-ROI, including the dilation of inferior lateral ventricles, outperformed both cortical thickness- and volumetric-based meta-ROIs in the detection of Alzheimer's disease.

Enlarged perivascular spaces in alcohol-related brain damage induced by dyslipidemia

Perivascular spaces (PVSs) as the anatomical basis of the glymphatic system, are increasingly recognized as potential imaging biomarkers of neurological conditions. However, it is not clear whether enlarged PVSs are associated with alcohol-related brain damage (ARBD). We aimed to investigate the effect of long-term alcohol exposure on dyslipidemia and the glymphatic system in ARBD. We found that patients with ARBD exhibited significantly enlargement of PVSs in the frontal cortex and basal ganglia, as well as a notable increased levels of total cholesterol (TC) and triglycerides (TG). The anatomical changes of the glymphatic drainage system mentioned above were positively associated with TC and TG. To further explore whether enlarged PVSs affects the function of the glymphatic system in ARBD, we constructed long alcohol exposure and high fat diet mice models. The mouse model of long alcohol exposure exhibited increased levels of TC and TG, enlarged PVSs, the loss of aquaporin-4 polarity caused by reactive astrocytes and impaired glymphatic drainage function which ultimately caused cognitive deficits, in a similar way as high fat diet leading to impairment in glymphatic drainage. Our study highlights the contribution of dyslipidemia due to long-term alcohol abuse in the impairment of the glymphatic drainage system.

Association of Plasma Markers of Alzheimer's Disease, Neurodegeneration, and Neuroinflammation with the Choroid Plexus Integrity in Aging

The choroid plexus (CP) is a vital brain structure essential for cerebrospinal fluid (CSF) production. Moreover, alterations in the CP's structure and function are implicated in molecular conditions and neuropathologies including multiple sclerosis, Alzheimer's disease, and stroke. Our goal is to provide the first characterization of the association between variation in the CP microstructure and macrostructure/volume using advanced magnetic resonance imaging (MRI) methodology, and blood-based biomarkers of Alzheimer's disease (Aß42/40 ratio; pTau181), neuroinflammation and neuronal injury (GFAP; NfL). We hypothesized that plasma biomarkers of brain pathology are associated with disordered CP structure. Moreover, since cerebral microstructural changes can precede macrostructural changes, we also conjecture that these differences would be evident in the CP microstructural integrity. Our cross-sectional study was conducted on a cohort of 108 well-characterized individuals, spanning 22-94 years of age, after excluding participants with cognitive impairments and non-exploitable MR imaging data. Established automated segmentation methods were used to identify the CP volume/macrostructure using structural MR images, while the microstructural integrity of the CP was assessed using our advanced quantitative high-resolution MR imaging of longitudinal and transverse relaxation times (T1 and T2). After adjusting for relevant covariates, positive associations were observed between pTau181, NfL and GFAP and all MRI metrics. These associations reached significance (p<0.05) except for CP volume vs. pTau181 (p=0.14), CP volume vs. NfL (p=0.35), and T2 vs. NFL (p=0.07). Further, negative associations between Aß42/40 and all MRI metrics were observed but reached significance only for Aß42/40 vs. T2 (p=0.04). These novel findings demonstrate that reduced CP macrostructural and microstructural integrity is positively associated with blood-based biomarkers of AD pathology, neurodegeneration/neuroinflammation and neurodegeneration. Degradation of the CP structure may co-occur with AD pathology and neuroinflammation ahead of clinically detectable cognitive impairment, making the CP a potential structure of interest for early disease detection or treatment monitoring.

Accumulation of Cerebrospinal Fluid, Ventricular Enlargement, and Cerebral Folate Metabolic Errors Unify a Diverse Group of Neuropsychiatric Conditions Affecting Adult Neocortical Functions

Cerebrospinal fluid (CSF) is a fluid critical to brain development, function, and health. It is actively secreted by the choroid plexus, and it emanates from brain tissue due to osmolar exchange and the constant contribution of brain metabolism and astroglial fluid output to interstitial fluid into the ventricles of the brain. CSF acts as a growth medium for the developing cerebral cortex and a source of nutrients and signalling throughout life. Together with perivascular glymphatic and interstitial fluid movement through the brain and into CSF, it also acts to remove toxins and maintain metabolic balance. In this study, we focused on cerebral folate status, measuring CSF concentrations of folate receptor alpha (FOLR1); aldehyde dehydrogenase 1L1, also known as 10-formyl tetrahydrofolate dehydrogenase (ALDH1L1 and FDH); and total folate. These demonstrate the transport of folate from blood across the blood-CSF barrier and into CSF (FOLR1 + folate), and the transport of folate through the primary FDH pathway from CSF into brain FDH + ve astrocytes. Based on our hypothesis that CSF flow, drainage issues, or osmotic forces, resulting in fluid accumulation, would have an associated cerebral folate imbalance, we investigated folate status in CSF from neurological conditions that have a severity association with enlarged ventricles. We found that all the conditions we examined had a folate imbalance, but these folate imbalances were not all the same. Given that folate is essential for key cellular processes, including DNA/RNA synthesis, methylation, nitric oxide, and neurotransmitter synthesis, we conclude that ageing or some form of trauma in life can lead to CSF accumulation and ventricular enlargement and result in a specific folate imbalance/deficiency associated with the specific neurological condition. We believe that addressing cerebral folate imbalance may therefore alleviate many of the underlying deficits and symptoms in these conditions.

Osteopontin: A novel marker of pre-symptomatic sporadic Alzheimer's disease

INTRODUCTION

We investigate the role of osteopontin (OPN) in participants with Pre-symptomatic Alzheimer's disease (AD), mild cognitive impairment (MCI), and in AD brains.

METHODS

Cerebrospinal fluid (CSF) OPN, AD, and synaptic biomarker levels were measured in 109 cognitively unimpaired (CU), parental-history positive Pre-symptomatic Evaluation of Experimental or Novel Treatments for Alzheimer's Disease (PREVENT-AD) participants, and in 167 CU and 399 participants with MCI from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. OPN levels were examined as a function of amyloid beta (Aβ) and tau positivity. Survival analyses investigated the link between OPN and rate of conversion to AD.

RESULTS

In PREVENT-AD, CSF OPN was positively correlated with synaptic biomarkers. In PREVENT-AD and ADNI, OPN was elevated in CSF Aβ42/40(+)/total tau(+) and CSF Aβ42/40(+)/phosphorylated tau181(+) individuals. In ADNI, OPN was increased in Aβ(+) positron emission tomography (PET) and tau(+) PET individuals, and associated with an accelerated rate of conversion to AD. OPN was elevated in autopsy-confirmed AD brains.

DISCUSSION

Strong associations between CSF OPN and key markers of AD pathophysiology suggest a significant role for OPN in tau neurobiology, particularly in the early stages of the disease.

HIGHLIGHTS

In the Pre-symptomatic Evaluation of Experimental or Novel Treatments for Alzheimer's Disease cohort, we discovered that cerebrospinal fluid (CSF) osteopontin (OPN) levels can indicate early synaptic dysfunction, tau deposition, and neuronal loss in cognitively unimpaired elderly with a parental history. CSF OPN is elevated in amyloid beta(+) positron emission tomography (PET) and tau(+) PET individuals. Elevated CSF OPN is associated with an accelerated rate of conversion to Alzheimer's disease (AD). Elevated CSF OPN is associated with an accelerated rate of cognitive decline on the Alzheimer's Disease Assessment Scale-Cognitive subscale 13, Montreal Cognitive Assessment, Mini-Mental State Examination, and Clinical Dementia Rating Scale Sum of Boxes. OPN mRNA and protein levels are significantly upregulated in the frontal cortex of autopsy-confirmed AD brains.

Prognostic enrichment for early-stage Huntington's disease: An explainable machine learning approach for clinical trial

BACKGROUND

In Huntington's disease clinical trials, recruitment and stratification approaches primarily rely on genetic load, cognitive and motor assessment scores. They focus less on in vivo brain imaging markers, which reflect neuropathology well before clinical diagnosis. Machine learning methods offer a degree of sophistication which could significantly improve prognosis and stratification by leveraging multimodal biomarkers from large datasets. Such models specifically tailored to HD gene expansion carriers could further enhance the efficacy of the stratification process.

OBJECTIVES

To improve stratification of Huntington's disease individuals for clinical trials.

METHODS

We used data from 451 gene positive individuals with Huntington's disease (both premanifest and diagnosed) from previously published cohorts (PREDICT, TRACK, TrackON, and IMAGE). We applied whole-brain parcellation to longitudinal brain scans and measured the rate of lateral ventricular enlargement, over 3 years, which was used as the target variable for our prognostic random forest regression models. The models were trained on various combinations of features at baseline, including genetic load, cognitive and motor assessment score biomarkers, as well as brain imaging-derived features. Furthermore, a simplified stratification model was developed to classify individuals into two homogenous groups (low risk and high risk) based on their anticipated rate of ventricular enlargement.

RESULTS

The predictive accuracy of the prognostic models substantially improved by integrating brain imaging features alongside genetic load, cognitive and motor biomarkers: a 24 % reduction in the cross-validated mean absolute error, yielding an error of 530 mm3/year. The stratification model had a cross-validated accuracy of 81 % in differentiating between moderate and fast progressors (precision = 83 %, recall = 80 %).

CONCLUSIONS

This study validated the effectiveness of machine learning in differentiating between low- and high-risk individuals based on the rate of ventricular enlargement. The models were exclusively trained using features from HD individuals, which offers a more disease-specific, simplified, and accurate approach for prognostic enrichment compared to relying on features extracted from healthy control groups, as done in previous studies. The proposed method has the potential to enhance clinical utility by: i) enabling more targeted recruitment of individuals for clinical trials, ii) improving post-hoc evaluation of individuals, and iii) ultimately leading to better outcomes for individuals through personalized treatment selection.

Effects of sleep deprivation on brain atrophy in individuals with mild cognitive impairment and Alzheimer's disease

Dementia, a prevalent condition in the United States, affecting millions of individuals and their families, underscores the importance of healthy cognitive ageing, which involves maintaining cognitive function and mental wellness as individuals grow older, promoting overall well-being and quality of life. Our original research study investigates the correlation between lifestyle factors and brain atrophy in individuals with mild cognitive impairment (MCI) or Alzheimer's disease (AD), as well as healthy older adults. Conducted over six months in West Texas, the research involved 20 participants aged 62-87. Findings reveal that sleep deprivation in MCI subjects and AD patients correlate with posterior cingulate cortex, hippocampal atrophy and total brain volume, while both groups exhibit age-related hippocampal volume reduction. Notably, fruit/vegetable intake negatively correlates with certain brain regions' volume, emphasizing the importance of diet. Lack of exercise is associated with reduced brain volume and hippocampal atrophy, underlining the cognitive benefits of physical activity. The study underscores lifestyle's significant impact on cognitive health, advocating interventions to promote brain health and disease prevention, particularly in MCI/AD cases. While blood profile data showed no significant results regarding cognitive decline, the study underscores the importance of lifestyle modifications in preserving cognitive function.

Impact of the Ventricle Size on Alzheimer's Disease Progression: A Retrospective Longitudinal Study

Background and Purpose

Ventricle enlargement has been implicated in the pathophysiology of Alzheimer's disease (AD). We studied the relationship between ventricular size and cognitive function in patients with AD. We focused on the effect of the initial ventricle size on the rate of cognitive decline in patients with AD.

Methods

A retrospective analysis of probable clinical AD participants with more than 2 magnetic resonance imaging images was performed. To measure ventricle size, we used visual rating scales of (1) Cardiovascular Health Study (CHS) score and (2) conventional linear measurement method.

Results

Increased clinical dementia rating (CDR) was correlated with a decreased Mini-Mental Status Examination (MMSE) score, and increased medial temporal lobe atrophy (MTLA) and global ventricle size (p<0.001, p<0.001, p=0.021, respectively). There was a significant correlation between the change in cognitive function in the group (70%-100%ile) with a large initial ventricle size (p=0.021 for ΔCDR, p=0.01 for ΔMMSE), while the median ventricle size (30%-70%ile) showed correlation with other brain structural changes (MTLA, frontal atrophy [FA], and white matter) (p=0.036 for initial MTLA, p=0.034 for FA).

Conclusions

In this study, the initial ventricle size may be a potential new imaging biomarker for initial cognitive function and clinical progression in AD. We found a relationship between the initial ventricle size and initial AD-related brain structural biomarkers.

Experimental Ischemic Stroke Induces Secondary Bihemispheric White Matter Degeneration and Long-Term Cognitive Impairment

Clinical studies have identified widespread white matter degeneration in ischemic stroke patients. However, contemporary research in stroke has predominately focused on the infarct and periinfarct penumbra regions. The involvement of white matter degeneration after ischemic stroke and its contribution to post-stroke cognitive impairment and dementia (PSCID) has remained less explored in experimental models. In this study, we examined the progression of locomotor and cognitive function up to 4 months after inducing ischemic stroke by middle cerebral artery occlusion in young adult rats. Despite evident ongoing locomotor recovery, long-term cognitive and affective impairments persisted after ischemic stroke, as indicated by Morris water maze, elevated plus maze, and open field performance. At 4 months after stroke, multimodal MRI was conducted to assess white matter degeneration. T2-weighted MRI (T2WI) unveiled bilateral cerebroventricular enlargement after ischemic stroke. Fluid Attenuated Inversion Recovery MRI (FLAIR) revealed white matter hyperintensities in the corpus callosum and fornix across bilateral hemispheres. A positive association between the volume of white matter hyperintensities and total cerebroventricular volume was noted in stroke rats. Further evidence of bilateral white matter degeneration was indicated by the reduction of fractional anisotropy and quantitative anisotropy at bilateral corpus callosum in diffusion-weighted MRI (DWI) analysis. Additionally, microglia and astrocyte activation were identified in the bilateral corpus callosum after stroke. Our study suggests that experimental ischemic stroke induced by MCAO in young rat replicate long-term cognitive impairment and bihemispheric white matter degeneration observed in ischemic stroke patients. This model provides an invaluable tool for unraveling the mechanisms underlying post-stroke secondary white matter degeneration and its contribution to PSCID.

Respiratory Dysfunction in Alzheimer's Disease-Consequence or Underlying Cause? Applying Animal Models to the Study of Respiratory Malfunctions

Alzheimer's disease (AD) is a neurodegenerative brain disease that is the most common cause of dementia among the elderly. In addition to dementia, which is the loss of cognitive function, including thinking, remembering, and reasoning, and behavioral abilities, AD patients also experience respiratory disturbances. The most common respiratory problems observed in AD patients are pneumonia, shortness of breath, respiratory muscle weakness, and obstructive sleep apnea (OSA). The latter is considered an outcome of Alzheimer's disease and is suggested to be a causative factor. While this narrative review addresses the bidirectional relationship between obstructive sleep apnea and Alzheimer's disease and reports on existing studies describing the most common respiratory disorders found in patients with Alzheimer's disease, its main purpose is to review all currently available studies using animal models of Alzheimer's disease to study respiratory impairments. These studies on animal models of AD are few in number but are crucial for establishing mechanisms, causation, implementing potential therapies for respiratory disorders, and ultimately applying these findings to clinical practice. This review summarizes what is already known in the context of research on respiratory disorders in animal models, while pointing out directions for future research.

Enabling uncertainty estimation in neural networks through weight perturbation for improved Alzheimer's disease classification

Background

The willingness to trust predictions formulated by automatic algorithms is key in a wide range of domains. However, a vast number of deep architectures are only able to formulate predictions without associated uncertainty.

Purpose

In this study, we propose a method to convert a standard neural network into a Bayesian neural network and estimate the variability of predictions by sampling different networks similar to the original one at each forward pass.

Methods

We combine our method with a tunable rejection-based approach that employs only the fraction of the data, i.e., the share that the model can classify with an uncertainty below a user-set threshold. We test our model in a large cohort of brain images from patients with Alzheimer's disease and healthy controls, discriminating the former and latter classes based on morphometric images exclusively.

Results

We demonstrate how combining estimated uncertainty with a rejection-based approach increases classification accuracy from 0.86 to 0.95 while retaining 75% of the test set. In addition, the model can select the cases to be recommended for, e.g., expert human evaluation due to excessive uncertainty. Importantly, our framework circumvents additional workload during the training phase by using our network "turned into Bayesian" to implicitly investigate the loss landscape in the neighborhood of each test sample in order to determine the reliability of the predictions.

Conclusion

We believe that being able to estimate the uncertainty of a prediction, along with tools that can modulate the behavior of the network to a degree of confidence that the user is informed about (and comfortable with), can represent a crucial step in the direction of user compliance and easier integration of deep learning tools into everyday tasks currently performed by human operators.

Magnetic resonance spectroscopy in the hippocampus of adult APP/PS1 mice following chronic vitamin D deficiency

Vitamin D (VitD) deficiency can exacerbate AD progression and may cause changes in brain metabolite levels that can be detected by magnetic resonance spectroscopy (MRS). The purpose of this study was to determine whether chronic VitD deficiency in an AD mouse model caused persistent metabolite levels changes in the hippocampus associated with memory performance. Six-month-old APPSwe/PS1ΔE9 (APP/PS1) mice (N = 14 mice/group) were fed either a VitD deficient (VitD-) diet or a control diet. Metabolite level changes in the hippocampus were evaluated by 1H MRS using a 9.4 T MRI. Ventricle volume was assessed by imaging and spatial memory was evaluated using the Barnes maze. All measurements were made at 6, 9, 12, and 15 months of age. At 15 months of age, amyloid plaque load and astrocyte number were evaluated histologically (N = 4 mice/group). Levels of N-acetyl aspartate and creatine were lower in VitD- mice compared to control diet mice at 12 months of age. VitD deficiency did not change ventricle volume. Lactate levels increased over time in VitD- mice and increases from 12 to 15 months were negatively correlated with changes in primary latency to the target hole in the Barns Maze. VitD- mice showed improved spatial memory performance compared to control diet mice. VitD- mice also had more astrocytes in the cortex and hippocampus at 15 months than control diet mice. This study suggests that severe VitD deficiency in APP/PS1 mice may lead to compensatory changes in metabolite and astrocyte levels that contribute to improved performance on spatial memory tasks.

The prevalence of mild cognitive impairment in Gulf War veterans: a follow-up study

Introduction

Gulf War Illness (GWI), also called Chronic Multisymptom Illness (CMI), is a multi-faceted condition that plagues an estimated 250,000 Gulf War (GW) veterans. Symptoms of GWI/CMI include fatigue, pain, and cognitive dysfunction. We previously reported that 12% of a convenience sample of middle aged (median age 52 years) GW veterans met criteria for mild cognitive impairment (MCI), a clinical syndrome most prevalent in older adults (e.g., ≥70 years). The current study sought to replicate and extend this finding.

Methods

We used the actuarial neuropsychological criteria and the Montreal Cognitive Assessment (MoCA) to assess the cognitive status of 952 GW veterans. We also examined regional brain volumes in a subset of GW veterans (n = 368) who had three Tesla magnetic resonance images (MRIs).

Results

We replicated our previous finding of a greater than 10% rate of MCI in four additional cohorts of GW veterans. In the combined sample of 952 GW veterans (median age 51 years at time of cognitive testing), 17% met criteria for MCI. Veterans classified as MCI were more likely to have CMI, history of depression, and prolonged (≥31 days) deployment-related exposures to smoke from oil well fires and chemical nerve agents compared to veterans with unimpaired and intermediate cognitive status. We also replicated our previous finding of hippocampal atrophy in veterans with MCI, and found significant group differences in lateral ventricle volumes.

Discussion

Because MCI increases the risk for late-life dementia and impacts quality of life, it may be prudent to counsel GW veterans with cognitive dysfunction, CMI, history of depression, and high levels of exposures to deployment-related toxicants to adopt lifestyle habits that have been associated with lowering dementia risk. With the Food and Drug Administration's recent approval of and the VA's decision to cover the cost for anti-amyloid β (Aβ) therapies, a logical next step for this research is to determine if GW veterans with MCI have elevated Aβ in their brains.

Associations of cerebrospinal fluid complement proteins with Alzheimer's pathology, cognition, and brain structure in non-dementia elderly

BACKGROUND

Cerebrospinal fluid (CSF) complement activation is a key part of neuroinflammation that occurs in the early stages of Alzheimer's disease (AD). However, the associations of CSF complement proteins with AD pathology, cognition, and structural neuroimaging biomarkers for AD have been rarely investigated.

METHODS

A total of 210 participants (125 mild cognitive impairment [MCI] patients and 85 normal controls) were included from Alzheimer's Disease Neuroimaging Initiative (ADNI) database who measured AD pathology, cognition, and neuroimaging at baseline and every 12 months. The mixed-effect linear models were utilized to investigate longitudinal associations of CSF complement proteins with AD pathology, cognition, and neuroimaging in cognitively normal (CN) and mild cognitive impairment (MCI) subjects. Causal mediation analyses were conducted to explore the potential mediators between CSF complement proteins and cognitive changes.

RESULTS

We found that the subjects with low CSF complement protein levels at baseline had worse outcomes in AD pathology, indicated by their lowest concentrations observed in A + and A + T + individuals. The reduced CSF complement proteins were associated with faster accumulation of tau among CN subjects and with cognitive decline and greater brain atrophy of specific regions among MCI subjects. Furthermore, mediation analyses showed that the effects of CSF complement proteins on cognitive performance were partially mediated by regional brain structures (mediation proportions range from 19.78 to 94.92%; p < 0.05).

CONCLUSIONS

This study demonstrated that CSF complement proteins were involved in the early progression of AD. Our results indicated that regional brain atrophy might be a plausible way to connect CSF complement protein levels and cognition.

Dual-Planar Monopole Antenna-Based Remote Sensing System for Microwave Medical Applications

Neurodegenerative diseases (NDs) can be life threatening and have chronic impacts on patients and society. Timely diagnosis and treatment are imperative to prevent deterioration. Conventional imaging modalities, such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET), are expensive and not readily accessible to patients. Microwave sensing and imaging (MSI) systems are promising tools for monitoring pathological changes, namely the lateral ventricle enlargement associated with ND, in a non-invasive and convenient way. This paper presents a dual-planar monopole antenna-based remote sensing system for ND monitoring. First, planar monopole antennas were designed using the simulation software CST Studio Suite. The antenna analysis was carried out regarding the reflection coefficient, gain, radiation pattern, time domain characterization, E-field distribution, and Specific Absorption Rate (SAR). The designed antennas were then integrated with a controlling circuit as a remote sensing system. The system was experimentally validated on brain phantoms using a vector network analyzer and a laptop. The collected reflection coefficient data were processed using a radar-based imaging algorithm to reconstruct images indicating brain abnormality in ND. The results suggest that the system could serve as a low-cost and efficient tool for long-term monitoring of ND, particularly in clinics and care home scenarios.

Unexpected gender differences in progressive supranuclear palsy reveal efficacy for davunetide in women

Progressive supranuclear palsy (PSP) is a pure tauopathy, implicating davunetide, enhancing Tau-microtubule interaction, as an ideal drug candidate. However, pooling patient data irrespective of sex concluded no efficacy. Here, analyzing sex-dependency in a 52 week-long- PSP clinical trial (involving over 200 patients) demonstrated clear baseline differences in brain ventricular volumes, a secondary endpoint. Dramatic baseline ventricular volume-dependent/volume increase correlations were observed in 52-week-placebo-treated females (r = 0.74, P = 2.36-9), whereas davunetide-treated females (like males) revealed no such effects. Assessment of primary endpoints, by the PSP Rating Scale (PSPRS) and markedly more so by the Schwab and England Activities of Daily Living (SEADL) scale, showed significantly faster deterioration in females, starting at trial week 13 (P = 0.01, and correlating with most other endpoints by week 52). Twice daily davunetide treatments slowed female disease progression and revealed significant protection according to the SEADL scale as early as at 39 weeks (P = 0.008), as well as protection of the bulbar and limb motor domains considered by the PSPRS, including speaking and swallowing difficulties caused by brain damage, and deterioration of fine motor skills, respectably (P = 0.01), at 52 weeks. Furthermore, at 52 weeks of trial, the exploratory Geriatric Depression Scale (GDS) significantly correlated with the SEADL scale deterioration in the female placebo group and demonstrated davunetide-mediated protection of females. Female-specific davunetide-mediated protection of ventricular volume corresponded to clinical efficacy. Together with the significantly slower disease progression seen in men, the results reveal sex-based drug efficacy differences, demonstrating the neuroprotective and disease-modifying impact of davunetide treatment for female PSP patients.

Neighborhood greenspace and neighborhood income associated with white matter grade worsening: Cardiovascular Health Study

INTRODUCTION

We examined whether a combined measure of neighborhood greenspace and neighborhood median income was associated with white matter hyperintensity (WMH) and ventricle size changes.

METHODS

The sample included 1260 cognitively normal ≥ 65-year-olds with two magnetic resonance images (MRI; ≈ 5 years apart). WMH and ventricular size were graded from 0 (least) to 9 (most) abnormal (worsening = increase of ≥1 grade from initial to follow-up MRI scans). The four-category neighborhood greenspace-income measure was based on median neighborhood greenspace and income values at initial MRI. Multivariable logistic regression tested associations between neighborhood greenspace-income and MRI measures (worsening vs. not).

RESULTS

White matter grade worsening was more likely for those in lower greenspace-lower income neighborhoods than higher greenspace-higher income neighborhoods (odds ratio = 1.73; 95% confidence interval = 1.19-2.51).

DISCUSSION

The combination of lower neighborhood income and lower greenspace may be a risk factor for worsening white matter grade on MRI. However, findings need to be replicated in more diverse cohorts.

HIGHLIGHTS

Population-based cohort of older adults (≥ 65 years) with greenspace and MRI dataCombined measure of neighborhood greenspace and neighborhood income at initial MRIMRI outcomes included white matter hyperintensities (WMH) and ventricular sizeLongitudinal change in MRI outcomes measured approximately 5 years apartWorsening WMH over time more likely for lower greenspace-lower income neighborhoods.

End-to-end automatic pathology localization for Alzheimer's disease diagnosis using structural MRI

Structural magnetic resonance imaging (sMRI) is an essential part of the clinical assessment of patients at risk of Alzheimer dementia. One key challenge in sMRI-based computer-aided dementia diagnosis is to localize local pathological regions for discriminative feature learning. Existing solutions predominantly depend on generating saliency maps for pathology localization and handle the localization task independently of the dementia diagnosis task, leading to a complex multi-stage training pipeline that is hard to optimize with weakly-supervised sMRI-level annotations. In this work, we aim to simplify the pathology localization task and construct an end-to-end automatic localization framework (AutoLoc) for Alzheimer's disease diagnosis. To this end, we first present an efficient pathology localization paradigm that directly predicts the coordinate of the most disease-related region in each sMRI slice. Then, we approximate the non-differentiable patch-cropping operation with the bilinear interpolation technique, which eliminates the barrier to gradient backpropagation and thus enables the joint optimization of localization and diagnosis tasks. Extensive experiments on commonly used ADNI and AIBL datasets demonstrate the superiority of our method. Especially, we achieve 93.38% and 81.12% accuracy on Alzheimer's disease classification and mild cognitive impairment conversion prediction tasks, respectively. Several important brain regions, such as rostral hippocampus and globus pallidus, are identified to be highly associated with Alzheimer's disease.

Identifying brain hierarchical structures associated with Alzheimer's disease using a regularized regression method with tree predictors

Brain segmentation at different levels is generally represented as hierarchical trees. Brain regional atrophy at specific levels was found to be marginally associated with Alzheimer's disease outcomes. In this study, we propose an ℓ1 -type regularization for predictors that follow a hierarchical tree structure. Considering a tree as a directed acyclic graph, we interpret the model parameters from a path analysis perspective. Under this concept, the proposed penalty regulates the total effect of each predictor on the outcome. With regularity conditions, it is shown that under the proposed regularization, the estimator of the model coefficient is consistent in ℓ2 -norm and the model selection is also consistent. When applied to a brain sMRI dataset acquired from the Alzheimer's Disease Neuroimaging Initiative (ADNI), the proposed approach identifies brain regions where atrophy in these regions demonstrates the declination in memory. With regularization on the total effects, the findings suggest that the impact of atrophy on memory deficits is localized from small brain regions, but at various levels of brain segmentation. Data used in preparation of this paper were obtained from the ADNI database.

Age-, sex-, and pathology-related variability in brain structure and cognition

This work aimed to investigate potential pathways linking age and imaging measures to early age- and pathology-related changes in cognition. We used [18F]-Flutemetamol (amyloid) and [18F]-Flortaucipir (tau) positron emission tomography (PET), structural MRI, and neuropsychological assessment from 232 elderly individuals aged 50-89 years (46.1% women, 23% APOE-ε4 carrier, 23.3% MCI). Tau-PET was available for a subsample of 93 individuals. Structural equation models were used to evaluate cross-sectional pathways between age, amyloid and tau burden, grey matter thickness and volumes, white matter hyperintensity volume, lateral ventricle volume, and cognition. Our results show that age is associated with worse outcomes in most of the measures examined and had similar negative effects on episodic memory and executive functions. While increased lateral ventricle volume was consistently associated with executive function dysfunction, participants with mild cognitive impairment drove associations between structural measures and episodic memory. Both age and amyloid-PET could be associated with medial temporal lobe tau, depending on whether we used a continuous or a dichotomous amyloid variable. Tau burden in entorhinal cortex was related to worse episodic memory in individuals with increased amyloid burden (Centiloid >12) independently of medial temporal lobe atrophy. Testing models for sex differences revealed that amyloid burden was more strongly associated with regional atrophy in women compared with men. These associations were likely mediated by higher tau burden in women. These results indicate that influences of pathological pathways on cognition and sex-specific vulnerabilities are dissociable already in early stages of neuropathology and cognitive impairment.

GIRUS-net: A Multimodal Deep Learning Model Identifying Imaging and Genetic Biomarkers Linked to Alzheimer's Disease Severity

We introduce an explainable deep neural architecture that combines brain structure with genetic influence to improve disease severity prediction in Alzheimer's disease. Our framework consists of an encoder, a decoder, and a rank-consistent ordinal regression module. The encoder projects neural imaging and genetics data into a low-dimensional latent space regularized by the decoder. The ordinal regression module guides the feature embedding process to find discriminative patterns representative of disease severity. We also add a learnable dropout layer that learns feature importance and extracts explainable biomarkers from the data. We evaluate our model using structural MRI (sMRI) and Single Nucleotide Polymorphism (SNP) data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. In 2-class severity classification comparison, our model has a median F-score of 0.86 (baseline median F-score range: 0.57-0.81). In 3-class classification comparison, our model's median F-score is 0.50 (baseline range: 0.17 - 0.41). In 4-class classification comparison, our model's median F-score is 0.40 (baseline range: 0.14 - 0.39). We demonstrate that our model provides improved disease diagnosis alongside sparse and clinically relevant biomarkers.Clinical relevance-This study provides a deep-learning model that can predict Alzheimer's disease severity levels while identifying consistent and clinically relevant biomarkers.

A Hybrid Multi-Scale Attention Convolution and Aging Transformer Network for Alzheimer's Disease Diagnosis

Deep neural networks have been successfully investigated in the computational analysis of structural magnetic resonance imaging (sMRI) data for the diagnosis of dementia, such as Alzheimer's disease (AD). The disease-related changes in sMRI may be different in local brain regions, which have variant structures but with some correlations. In addition, aging increases the risk of dementia. However, it is still challenging to capture the local variations and long-range correlations of different brain regions and make use of the age information for disease diagnosis. To address these problems, we propose a hybrid network with multi-scale attention convolution and aging transformer for AD diagnosis. First, to capture the local variations, a multi-scale attention convolution is proposed to learn the feature maps with multi-scale kernels, which are adaptively aggregated by an attention module. Then, to model the long-range correlations of brain regions, a pyramid non-local block is used on the high-level features to learn more powerful features. Finally, we propose an aging transformer subnetwork to embed the age information into image features and capture the dependencies between subjects at different ages. The proposed method can learn not only the subject-specific rich features but also the inter-subject age correlations in an end-to-end framework. Our method is evaluated with T1-weighted sMRI scans from a large cohort of subjects on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results demonstrate that our method has achieved promising performance for AD-related diagnosis.

An Alzheimer's disease category progression sub-grouping analysis using manifold learning on ADNI

Many current statistical and machine learning methods have been used to explore Alzheimer's disease (AD) and its associated patterns that contribute to the disease. However, there has been limited success in understanding the relationship between cognitive tests, biomarker data, and patient AD category progressions. In this work, we perform exploratory data analysis of AD health record data by analyzing various learned lower dimensional manifolds to separate early-stage AD categories further. Specifically, we used Spectral embedding, Multidimensional scaling, Isomap, t-Distributed Stochastic Neighbour Embedding, Uniform Manifold Approximation and Projection, and sparse denoising autoencoder based manifolds on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. We then determine the clustering potential of the learned embeddings and then determine if category sub-groupings or sub-categories can be found. We then used a Kruskal-sWallis H test to determine the statistical significance of the discovered AD subcategories. Our results show that the existing AD categories do exhibit sub-groupings, especially in mild cognitive impairment transitions in many of the tested manifolds, showing there may be a need for further subcategories to describe AD progression.

Preliminary validation of a structural magnetic resonance imaging metric for tracking dementia-related neurodegeneration and future decline

Alzheimer's disease (AD) is a progressive neurodegenerative disease characterized by cognitive decline and atrophy in the medial temporal lobe (MTL) and subsequent brain regions. Structural magnetic resonance imaging (sMRI) has been widely used in research and clinical care for diagnosis and monitoring AD progression. However, atrophy patterns are complex and vary by patient. To address this issue, researchers have made efforts to develop more concise metrics that can summarize AD-specific atrophy. Many of these methods can be difficult to interpret clinically, hampering adoption. In this study, we introduce a novel index which we call an "AD-NeuroScore," that uses a modified Euclidean-inspired distance function to calculate differences between regional brain volumes associated with cognitive decline. The index is adjusted for intracranial volume (ICV), age, sex, and scanner model. We validated AD-NeuroScore using 929 older adults from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, with a mean age of 72.7 years (SD = 6.3; 55.1-91.5) and cognitively normal (CN), mild cognitive impairment (MCI), or AD diagnoses. Our validation results showed that AD-NeuroScore was significantly associated with diagnosis and disease severity scores (measured by MMSE, CDR-SB, and ADAS-11) at baseline. Furthermore, baseline AD-NeuroScore was associated with both changes in diagnosis and disease severity scores at all time points with available data. The performance of AD-NeuroScore was equivalent or superior to adjusted hippocampal volume (AHV), a widely used metric in AD research. Further, AD-NeuroScore typically performed as well as or sometimes better when compared to other existing sMRI-based metrics. In conclusion, we have introduced a new metric, AD-NeuroScore, which shows promising results in detecting AD, benchmarking disease severity, and predicting disease progression. AD-NeuroScore differentiates itself from other metrics by being clinically practical and interpretable.

Association of brain tissue cerebrospinal fluid fraction with age in healthy cognitively normal adults

Background and purpose

Our objective was to apply multi-compartment T2 relaxometry in cognitively normal individuals aged 20-80 years to study the effect of aging on the parenchymal CSF fraction (CSFF), a potential measure of the subvoxel CSF space.

Materials and methods

A total of 60 volunteers (age range, 22-80 years) were enrolled. Voxel-wise maps of short-T2 myelin water fraction (MWF), intermediate-T2 intra/extra-cellular water fraction (IEWF), and long-T2 CSFF were obtained using fast acquisition with spiral trajectory and adiabatic T2prep (FAST-T2) sequence and three-pool non-linear least squares fitting. Multiple linear regression analyses were performed to study the association between age and regional MWF, IEWF, and CSFF measurements, adjusting for sex and region of interest (ROI) volume. ROIs include the cerebral white matter (WM), cerebral cortex, and subcortical deep gray matter (GM). In each model, a quadratic term for age was tested using an ANOVA test. A Spearman's correlation between the normalized lateral ventricle volume, a measure of organ-level CSF space, and the regional CSFF, a measure of tissue-level CSF space, was computed.

Results

Regression analyses showed that there was a statistically significant quadratic relationship with age for CSFF in the cortex (p = 0.018), MWF in the cerebral WM (p = 0.033), deep GM (p = 0.017) and cortex (p = 0.029); and IEWF in the deep GM (p = 0.033). There was a statistically highly significant positive linear relationship between age and regional CSFF in the cerebral WM (p < 0.001) and deep GM (p < 0.001). In addition, there was a statistically significant negative linear association between IEWF and age in the cerebral WM (p = 0.017) and cortex (p < 0.001). In the univariate correlation analysis, the normalized lateral ventricle volume correlated with the regional CSFF measurement in the cerebral WM (ρ = 0.64, p < 0.001), cortex (ρ = 0.62, p < 0.001), and deep GM (ρ = 0.66, p < 0.001).

Conclusion

Our cross-sectional data demonstrate that brain tissue water in different compartments shows complex age-dependent patterns. Parenchymal CSFF, a measure of subvoxel CSF-like water in the brain tissue, is quadratically associated with age in the cerebral cortex and linearly associated with age in the cerebral deep GM and WM.

Comparison of EEG Source Localization Using Simplified and Anatomically Accurate Head Models in Younger and Older Adults

Accuracy of electroencephalography (EEG) source localization relies on the volume conduction head model. A previous analysis of young adults has shown that simplified head models have larger source localization errors when compared with head models based on magnetic resonance images (MRIs). As obtaining individual MRIs may not always be feasible, researchers often use generic head models based on template MRIs. It is unclear how much error would be introduced using template MRI head models in older adults that likely have differences in brain structure compared to young adults. The primary goal of this study was to determine the error caused by using simplified head models without individual-specific MRIs in both younger and older adults. We collected high-density EEG during uneven terrain walking and motor imagery for 15 younger (22±3 years) and 21 older adults (74±5 years) and obtained [Formula: see text]-weighted MRI for each individual. We performed equivalent dipole fitting after independent component analysis to obtain brain source locations using four forward modeling pipelines with increasing complexity. These pipelines included: 1) a generic head model with template electrode positions or 2) digitized electrode positions, 3) individual-specific head models with digitized electrode positions using simplified tissue segmentation, or 4) anatomically accurate segmentation. We found that when compared to the anatomically accurate individual-specific head models, performing dipole fitting with generic head models led to similar source localization discrepancies (up to 2 cm) for younger and older adults. Co-registering digitized electrode locations to the generic head models reduced source localization discrepancies by  ∼  6 mm. Additionally, we found that source depths generally increased with skull conductivity for the representative young adult but not as much for the older adult. Our results can help inform a more accurate interpretation of brain areas in EEG studies when individual MRIs are unavailable.

Elevated plasma sulfides are associated with cognitive dysfunction and brain atrophy in human Alzheimer's disease and related dementias

Emerging evidence indicates that vascular stress is an important contributor to the pathophysiology of Alzheimer's disease and related dementias (ADRD). Hydrogen sulfide (H2S) and its metabolites (acid-labile (e.g., iron-sulfur clusters) and bound (e.g., per-, poly-) sulfides) have been shown to modulate both vascular and neuronal homeostasis. We recently reported that elevated plasma sulfides were associated with cognitive dysfunction and measures of microvascular disease in ADRD. Here we extend our previous work to show associations between elevated sulfides and magnetic resonance-based metrics of brain atrophy and white matter integrity. Elevated bound sulfides were associated with decreased grey matter volume, while increased acid labile sulfides were associated with decreased white matter integrity and greater ventricular volume. These findings are consistent with alterations in sulfide metabolism in ADRD which may represent maladaptive responses to oxidative stress.

Tau-targeting antisense oligonucleotide MAPTRx in mild Alzheimer's disease: a phase 1b, randomized, placebo-controlled trial

Tau plays a key role in Alzheimer's disease (AD) pathophysiology, and accumulating evidence suggests that lowering tau may reduce this pathology. We sought to inhibit MAPT expression with a tau-targeting antisense oligonucleotide (MAPTRx) and reduce tau levels in patients with mild AD. A randomized, double-blind, placebo-controlled, multiple-ascending dose phase 1b trial evaluated the safety, pharmacokinetics and target engagement of MAPTRx. Four ascending dose cohorts were enrolled sequentially and randomized 3:1 to intrathecal bolus administrations of MAPTRx or placebo every 4 or 12 weeks during the 13-week treatment period, followed by a 23 week post-treatment period. The primary endpoint was safety. The secondary endpoint was MAPTRx pharmacokinetics in cerebrospinal fluid (CSF). The prespecified key exploratory outcome was CSF total-tau protein concentration. Forty-six patients enrolled in the trial, of whom 34 were randomized to MAPTRx and 12 to placebo. Adverse events were reported in 94% of MAPTRx-treated patients and 75% of placebo-treated patients; all were mild or moderate. No serious adverse events were reported in MAPTRx-treated patients. Dose-dependent reduction in the CSF total-tau concentration was observed with greater than 50% mean reduction from baseline at 24 weeks post-last dose in the 60 mg (four doses) and 115 mg (two doses) MAPTRx groups. Clinicaltrials.gov registration number: NCT03186989 .

An Insight into Cellular and Molecular Mechanisms Underlying the Pathogenesis of Neurodegeneration in Alzheimer's Disease

Alzheimer's disease (AD) is the most prominent neurodegenerative disorder in the aging population. It is characterized by cognitive decline, gradual neurodegeneration, and the development of amyloid-β (Aβ)-plaques and neurofibrillary tangles, which constitute hyperphosphorylated tau. The early stages of neurodegeneration in AD include the loss of neurons, followed by synaptic impairment. Since the discovery of AD, substantial factual research has surfaced that outlines the disease's causes, molecular mechanisms, and prospective therapeutics, but a successful cure for the disease has not yet been discovered. This may be attributed to the complicated pathogenesis of AD, the absence of a well-defined molecular mechanism, and the constrained diagnostic resources and treatment options. To address the aforementioned challenges, extensive disease modeling is essential to fully comprehend the underlying mechanisms of AD, making it easier to design and develop effective treatment strategies. Emerging evidence over the past few decades supports the critical role of Aβ and tau in AD pathogenesis and the participation of glial cells in different molecular and cellular pathways. This review extensively discusses the current understanding concerning Aβ- and tau-associated molecular mechanisms and glial dysfunction in AD. Moreover, the critical risk factors associated with AD including genetics, aging, environmental variables, lifestyle habits, medical conditions, viral/bacterial infections, and psychiatric factors have been summarized. The present study will entice researchers to more thoroughly comprehend and explore the current status of the molecular mechanism of AD, which may assist in AD drug development in the forthcoming era.

Does adding MRI and CSF-based biomarkers improve cognitive status classification based on cognitive performance questionnaires?

BACKGROUND

Cognitive status classification (e.g. dementia, cognitive impairment without dementia, and normal) based on cognitive performance questionnaires has been widely used in population-based studies, providing insight into the population dynamics of dementia. However, researchers have raised concerns about the accuracy of cognitive assessments. MRI and CSF biomarkers may provide improved classification, but the potential improvement in classification in population-based studies is relatively unknown.

METHODS

Data come from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We examined whether the addition of MRI and CSF biomarkers improved cognitive status classification based on cognitive status questionnaires (MMSE). We estimated several multinomial logistic regression models with different combinations of MMSE and CSF/MRI biomarkers. Based on these models, we also predicted prevalence of each cognitive status category using a model with MMSE only and a model with MMSE + MRI + CSF measures and compared them to diagnosed prevalence.

RESULTS

Our analysis showed a slight improvement in variance explained (pseudo-R2) between the model with MMSE only and the model including MMSE and MRI/CSF biomarkers; the pseudo-R2 increased from .401 to .445. Additionally, in evaluating differences in predicted prevalence for each cognitive status, we found a small improvement in the predicted prevalence of cognitively normal individuals between the MMSE only model and the model with MMSE and CSF/MRI biomarkers (3.1% improvement). We found no improvement in the correct prediction of dementia prevalence.

CONCLUSION

MRI and CSF biomarkers, while important for understanding dementia pathology in clinical research, were not found to substantially improve cognitive status classification based on cognitive status performance, which may limit adoption in population-based surveys due to costs, training, and invasiveness associated with their collection.

Prediction of Amyloid β-Positivity with both MRI Parameters and Cognitive Function Using Machine Learning

Purpose

To investigate the MRI markers for the prediction of amyloid β (Aβ)-positivity in mild cognitive impairment (MCI) and Alzheimer's disease (AD), and to evaluate the differences in MRI markers between Aβ-positive (Aβ [+]) and -negative groups using the machine learning (ML) method.

Materials and Methods

This study included 139 patients with MCI and AD who underwent amyloid PET-CT and brain MRI. Patients were divided into Aβ (+) (n = 84) and Aβ-negative (n = 55) groups. Visual analysis was performed with the Fazekas scale of white matter hyperintensity (WMH) and cerebral microbleeds (CMB) scores. The WMH volume and regional brain volume were quantitatively measured. The multivariable logistic regression and ML using support vector machine, and logistic regression were used to identify the best MRI predictors of Aβ-positivity.

Results

The Fazekas scale of WMH (p = 0.02) and CMB scores (p = 0.04) were higher in Aβ (+). The volumes of hippocampus, entorhinal cortex, and precuneus were smaller in Aβ (+) (p < 0.05). The third ventricle volume was larger in Aβ (+) (p = 0.002). The logistic regression of ML showed a good accuracy (81.1%) with mini-mental state examination (MMSE) and regional brain volumes.

Conclusion

The application of ML using the MMSE, third ventricle, and hippocampal volume is helpful in predicting Aβ-positivity with a good accuracy.

Higher performance for women than men in MRI-based Alzheimer's disease detection

INTRODUCTION

Although machine learning classifiers have been frequently used to detect Alzheimer's disease (AD) based on structural brain MRI data, potential bias with respect to sex and age has not yet been addressed. Here, we examine a state-of-the-art AD classifier for potential sex and age bias even in the case of balanced training data.

METHODS

Based on an age- and sex-balanced cohort of 432 subjects (306 healthy controls, 126 subjects with AD) extracted from the ADNI data base, we trained a convolutional neural network to detect AD in MRI brain scans and performed ten different random training-validation-test splits to increase robustness of the results. Classifier decisions for single subjects were explained using layer-wise relevance propagation.

RESULTS

The classifier performed significantly better for women (balanced accuracy [Formula: see text]) than for men ([Formula: see text]). No significant differences were found in clinical AD scores, ruling out a disparity in disease severity as a cause for the performance difference. Analysis of the explanations revealed a larger variance in regional brain areas for male subjects compared to female subjects.

DISCUSSION

The identified sex differences cannot be attributed to an imbalanced training dataset and therefore point to the importance of examining and reporting classifier performance across population subgroups to increase transparency and algorithmic fairness. Collecting more data especially among underrepresented subgroups and balancing the dataset are important but do not always guarantee a fair outcome.

Should artificial intelligence be used in conjunction with Neuroimaging in the diagnosis of Alzheimer's disease?

Alzheimer's disease (AD) is a progressive, neurodegenerative disorder that affects memory, thinking, behavior, and other cognitive functions. Although there is no cure, detecting AD early is important for the development of a therapeutic plan and a care plan that may preserve cognitive function and prevent irreversible damage. Neuroimaging, such as magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET), has served as a critical tool in establishing diagnostic indicators of AD during the preclinical stage. However, as neuroimaging technology quickly advances, there is a challenge in analyzing and interpreting vast amounts of brain imaging data. Given these limitations, there is great interest in using artificial Intelligence (AI) to assist in this process. AI introduces limitless possibilities in the future diagnosis of AD, yet there is still resistance from the healthcare community to incorporate AI in the clinical setting. The goal of this review is to answer the question of whether AI should be used in conjunction with neuroimaging in the diagnosis of AD. To answer the question, the possible benefits and disadvantages of AI are discussed. The main advantages of AI are its potential to improve diagnostic accuracy, improve the efficiency in analyzing radiographic data, reduce physician burnout, and advance precision medicine. The disadvantages include generalization and data shortage, lack of in vivo gold standard, skepticism in the medical community, potential for physician bias, and concerns over patient information, privacy, and safety. Although the challenges present fundamental concerns and must be addressed when the time comes, it would be unethical not to use AI if it can improve patient health and outcome.

Uncovering heterogeneous cognitive trajectories in mild cognitive impairment: a data-driven approach

BACKGROUND

Given the complex and progressive nature of mild cognitive impairment (MCI), the ability to delineate and understand the heterogeneous cognitive trajectories is crucial for developing personalized medicine and informing trial design. The primary goals of this study were to examine whether different cognitive trajectories can be identified within subjects with MCI and, if present, to characterize each trajectory in relation to changes in all major Alzheimer's disease (AD) biomarkers over time.

METHODS

Individuals with a diagnosis of MCI at the first visit and ≥ 1 follow-up cognitive assessment were selected from the Alzheimer's Disease Neuroimaging Initiative database (n = 936; age 73 ± 8; 40% female; 16 ± 3 years of education; 50% APOE4 carriers). Based on the Alzheimer's Disease Assessment Scale-Cognitive Subscale-13 (ADAS-Cog-13) total scores from baseline up to 5 years follow-up, a non-parametric k-means longitudinal clustering method was performed to obtain clusters of individuals with similar patterns of cognitive decline. We further conducted a series of linear mixed-effects models to study the associations of cluster membership with longitudinal changes in other cognitive measures, neurodegeneration, and in vivo AD pathologies.

RESULTS

Four distinct cognitive trajectories emerged. Cluster 1 consisted of 255 individuals (27%) with a nearly non-existent rate of change in the ADAS-Cog-13 over 5 years of follow-up and a healthy-looking biomarker profile. Individuals in the cluster 2 (n = 336, 35%) and 3 (n = 240, 26%) groups showed relatively mild and moderate cognitive decline trajectories, respectively. Cluster 4, comprising about 11% of our study sample (n = 105), exhibited an aggressive cognitive decline trajectory and was characterized by a pronouncedly abnormal biomarker profile.

CONCLUSIONS

Individuals with MCI show substantial heterogeneity in cognitive decline. Our findings may potentially contribute to improved trial design and patient stratification.

Synaptic loss and gliosis in the nucleus tractus solitarii with streptozotocin-induced Alzheimer's disease

Obstructive sleep apnea is highly prevalent in Alzheimer's disease (AD). However, brainstem centers controlling respiration have received little attention in AD research, and mechanisms behind respiratory dysfunction in AD are not understood. The nucleus tractus solitarii (nTS) is an important brainstem center for respiratory control and chemoreflex function. Alterations of nTS integrity, like those shown in AD patients, likely affect neuronal processing and adequate control of breathing. We used the streptozotocin-induced rat model of AD (STZ-AD) to analyze cellular changes in the nTS that corroborate previously documented respiratory dysfunction. We used 2 common dosages of STZ (2 and 3 mg/kg STZ) for model induction and evaluated the early impact on cell populations in the nTS. The hippocampus served as control region to identify site-specific effects of STZ. There was significant atrophy in the caudal nTS of the 3 mg/kg STZ-AD group only, an area known to integrate chemoafferent information. Also, the hippocampus had significant atrophy with the highest STZ dosage tested. Both STZ-AD groups showed respiratory dysfunction along with multiple indices for astroglial and microglial activation. These changes were primarily located in the caudal and intermediate nTS. While there was no change of astrocytes in the hippocampus, microglial activation was accompanied by a reduction in synaptic density. Together, our data demonstrate that STZ-AD induces site-specific effects on all major cell types, primarily in the caudal/intermediate nTS. Both STZ dosages used in this study produced a similar outcome and can be used for future studies examining the initial symptoms of STZ-AD.

Plasma extracellular vesicles reveal early molecular differences in amyloid positive patients with early-onset mild cognitive impairment

In the clinical course of Alzheimer's disease (AD) development, the dementia phase is commonly preceded by a prodromal AD phase, which is mainly characterized by reaching the highest levels of Aβ and p-tau-mediated neuronal injury and a mild cognitive impairment (MCI) clinical status. Because of that, most AD cases are diagnosed when neuronal damage is already established and irreversible. Therefore, a differential diagnosis of MCI causes in these prodromal stages is one of the greatest challenges for clinicians. Blood biomarkers are emerging as desirable tools for pre-screening purposes, but the current results are still being analyzed and much more data is needed to be implemented in clinical practice. Because of that, plasma extracellular vesicles (pEVs) are gaining popularity as a new source of biomarkers for the early stages of AD development. To identify an exosome proteomics signature linked to prodromal AD, we performed a cross-sectional study in a cohort of early-onset MCI (EOMCI) patients in which 184 biomarkers were measured in pEVs, cerebrospinal fluid (CSF), and plasma samples using multiplex PEA technology of Olink© proteomics. The obtained results showed that proteins measured in pEVs from EOMCI patients with established amyloidosis correlated with CSF p-tau181 levels, brain ventricle volume changes, brain hyperintensities, and MMSE scores. In addition, the correlations of pEVs proteins with different parameters distinguished between EOMCI Aβ( +) and Aβ(-) patients, whereas the CSF or plasma proteome did not. In conclusion, our findings suggest that pEVs may be able to provide information regarding the initial amyloidotic changes of AD. Circulating exosomes may acquire a pathological protein signature of AD before raw plasma, becoming potential biomarkers for identifying subjects at the earliest stages of AD development.

Automatic Preprocessing Pipeline for White Matter Functional Analyses of Large-Scale Databases

Recently, increasing evidence suggests that fMRI signals in white matter (WM), conventionally ignored as nuisance, are robustly detectable using appropriate processing methods and are related to neural activity, while changes in WM with aging and degeneration are also well documented. These findings suggest variations in patterns of BOLD signals in WM should be investigated. However, existing fMRI analysis tools, which were designed for processing gray matter signals, are not well suited for large-scale processing of WM signals in fMRI data. We developed an automatic pipeline for high-performance preprocessing of fMRI images with emphasis on quantifying changes in BOLD signals in WM in an aging population. At the image processing level, the pipeline integrated existing software modules with fine parameter tunings and modifications to better extract weaker WM signals. The preprocessing results primarily included whole-brain time-courses, functional connectivity, maps and tissue masks in a common space. At the job execution level, this pipeline exploited a local XNAT to store datasets and results, while using DAX tool to automatic distribute batch jobs that run on high-performance computing clusters. Through the pipeline, 5,034 fMRI/T1 scans were preprocessed. The intraclass correlation coefficient (ICC) of test-retest experiment based on the preprocessed data is 0.52 - 0.86 (N=1000), indicating a high reliability of our pipeline, comparable to previously reported ICC in gray matter experiments. This preprocessing pipeline highly facilitates our future analyses on WM functional alterations in aging and may be of benefit to a larger community interested in WM fMRI studies.