The use of PET in Alzheimer disease

Dimensional Neuroimaging Endophenotypes: Neurobiological Representations of Disease Heterogeneity Through Machine Learning

Machine learning has been increasingly used to obtain individualized neuroimaging signatures for disease diagnosis, prognosis, and response to treatment in neuropsychiatric and neurodegenerative disorders. Therefore, it has contributed to a better understanding of disease heterogeneity by identifying disease subtypes with different brain phenotypic measures. In this review, we first present a systematic literature overview of studies using machine learning and multimodal magnetic resonance imaging to unravel disease heterogeneity in various neuropsychiatric and neurodegenerative disorders, including Alzheimer's disease, schizophrenia, major depressive disorder, autism spectrum disorder, and multiple sclerosis, as well as their potential in a transdiagnostic framework, where neuroanatomical and neurobiological commonalities were assessed across diagnostic boundaries. Subsequently, we summarize relevant machine learning methodologies and their clinical interpretability. We discuss the potential clinical implications of the current findings and envision future research avenues. Finally, we discuss an emerging paradigm called dimensional neuroimaging endophenotypes. Dimensional neuroimaging endophenotypes dissects the neurobiological heterogeneity of neuropsychiatric and neurodegenerative disorders into low-dimensional yet informative, quantitative brain phenotypic representations, serving as robust intermediate phenotypes (i.e., endophenotypes), presumably reflecting the interplay of underlying genetic, lifestyle, and environmental processes associated with disease etiology.

Alzheimer's disease prediction algorithm based on de-correlation constraint and multi-modal feature interaction

Alzheimer's disease (AD) is a neurodegenerative disease characterized by various pathological changes. Utilizing multimodal data from Fluorodeoxyglucose positron emission tomography(FDG-PET) and Magnetic Resonance Imaging(MRI) of the brain can offer comprehensive information about the lesions from different perspectives and improve the accuracy of prediction. However, there are significant differences in the feature space of multimodal data. Commonly, the simple concatenation of multimodal features can cause the model to struggle in distinguishing and utilizing the complementary information between different modalities, thus affecting the accuracy of predictions. Therefore, we propose an AD prediction model based on de-correlation constraint and multi-modal feature interaction. This model consists of the following three parts: (1) The feature extractor employs residual connections and attention mechanisms to capture distinctive lesion features from FDG-PET and MRI data within their respective modalities. (2) The de-correlation constraint function enhances the model's capacity to extract complementary information from different modalities by reducing the feature similarity between them. (3) The mutual attention feature fusion module interacts with the features within and between modalities to enhance the modal-specific features and adaptively adjust the weights of these features based on information from other modalities. The experimental results on ADNI database demonstrate that the proposed model achieves a prediction accuracy of 86.79% for AD, MCI and NC, which is higher than the existing multi-modal AD prediction models.

Brain metabolic network covariance and aging in a mouse model of Alzheimer's disease

INTRODUCTION

Alzheimer's disease (AD), the leading cause of dementia worldwide, represents a human and financial impact for which few effective drugs exist to treat the disease. Advances in molecular imaging have enabled assessment of cerebral glycolytic metabolism, and network modeling of brain region have linked to alterations in metabolic activity to AD stage.

METHODS

We performed 18 F-FDG positron emission tomography (PET) imaging in 4-, 6-, and 12-month-old 5XFAD and littermate controls (WT) of both sexes and analyzed region data via brain metabolic covariance analysis.

RESULTS

The 5XFAD model mice showed age-related changes in glucose uptake relative to WT mice. Analysis of community structure of covariance networks was different across age and sex, with a disruption of metabolic coupling in the 5XFAD model.

DISCUSSION

The current study replicates clinical AD findings and indicates that metabolic network covariance modeling provides a translational tool to assess disease progression in AD models.

Plasma pTau-217 and N-terminal tau (NTA) enhance sensitivity to identify tau PET positivity in amyloid-β positive individuals

INTRODUCTION

We set out to identify tau PET-positive (A+T+) individuals among amyloid-beta (Aβ) positive participants using plasma biomarkers.

METHODS

In this cross-sectional study we assessed 234 participants across the AD continuum who were evaluated by amyloid PET with [18 F]AZD4694 and tau-PET with [18 F]MK6240 and measured plasma levels of total tau, pTau-181, pTau-217, pTau-231, and N-terminal tau (NTA-tau). We evaluated the performances of plasma biomarkers to predict tau positivity in Aβ+ individuals.

RESULTS

Highest associations with tau positivity in Aβ+ individuals were found for plasma pTau-217 (AUC [CI95% ] = 0.89 [0.82, 0.96]) and NTA-tau (AUC [CI95% ] = 0.88 [0.91, 0.95]). Combining pTau-217 and NTA-tau resulted in the strongest agreement (Cohen's Kappa = 0.74, CI95%  = 0.57/0.90, sensitivity = 92%, specificity = 81%) with PET for classifying tau positivity.

DISCUSSION

The potential for identifying tau accumulation in later Braak stages will be useful for patient stratification and prognostication in treatment trials and in clinical practice.

HIGHLIGHTS

We found that in a cohort without pre-selection pTau-181, pTau-217, and NTA-tau showed the highest association with tau PET positivity. We found that in Aβ+ individuals pTau-217 and NTA-tau showed the highest association with tau PET positivity. Combining pTau-217 and NTA-tau resulted in the strongest agreement with the tau PET-based classification.

Single-cell mapping of lipid metabolites using an infrared probe in human-derived model systems

Understanding metabolic heterogeneity is the key to uncovering the underlying mechanisms of metabolic-related diseases. Current metabolic imaging studies suffer from limitations including low resolution and specificity, and the model systems utilized often lack human relevance. Here, we present a single-cell metabolic imaging platform to enable direct imaging of lipid metabolism with high specificity in various human-derived 2D and 3D culture systems. Through the incorporation of an azide-tagged infrared probe, selective detection of newly synthesized lipids in cells and tissue became possible, while simultaneous fluorescence imaging enabled cell-type identification in complex tissues. In proof-of-concept experiments, newly synthesized lipids were directly visualized in human-relevant model systems among different cell types, mutation status, differentiation stages, and over time. We identified upregulated lipid metabolism in progranulin-knockdown human induced pluripotent stem cells and in their differentiated microglia cells. Furthermore, we observed that neurons in brain organoids exhibited a significantly lower lipid metabolism compared to astrocytes.

Amyloid-β specific regulatory T cells attenuate Alzheimer's disease pathobiology in APP/PS1 mice

BACKGROUND

Regulatory T cells (Tregs) maintain immune tolerance. While Treg-mediated neuroprotective activities are now well-accepted, the lack of defined antigen specificity limits their therapeutic potential. This is notable for neurodegenerative diseases where cell access to injured brain regions is required for disease-specific therapeutic targeting and improved outcomes. To address this need, amyloid-beta (Aβ) antigen specificity was conferred to Treg responses by engineering the T cell receptor (TCR) specific for Aβ (TCRAβ). The TCRAb were developed from disease-specific T cell effector (Teff) clones. The ability of Tregs expressing a transgenic TCRAβ (TCRAβ -Tregs) to reduce Aβ burden, transform effector to regulatory cells, and reverse disease-associated neurotoxicity proved beneficial in an animal model of Alzheimer's disease.

METHODS

TCRAβ -Tregs were generated by CRISPR-Cas9 knockout of endogenous TCR and consequent incorporation of the transgenic TCRAb identified from Aβ reactive Teff monoclones. Antigen specificity was confirmed by MHC-Aβ-tetramer staining. Adoptive transfer of TCRAβ-Tregs to mice expressing a chimeric mouse-human amyloid precursor protein and a mutant human presenilin-1 followed measured behavior, immune, and immunohistochemical outcomes.

RESULTS

TCRAβ-Tregs expressed an Aβ-specific TCR. Adoptive transfer of TCRAβ-Tregs led to sustained immune suppression, reduced microglial reaction, and amyloid loads. 18F-fluorodeoxyglucose radiolabeled TCRAβ-Treg homed to the brain facilitating antigen specificity. Reduction in amyloid load was associated with improved cognitive functions.

CONCLUSIONS

TCRAβ-Tregs reduced amyloid burden, restored brain homeostasis, and improved learning and memory, supporting the increased therapeutic benefit of antigen specific Treg immunotherapy for AD.

Identifying Sex-Specific Serum Patterns of Alzheimer's Mice through Deep TMT Profiling and a Concentration-Dependent Concatenation Strategy

Alzheimer's disease (AD) is the most prevalent form of dementia, disproportionately affecting women in disease prevalence and progression. Comprehensive analysis of the serum proteome in a common AD mouse model offers potential in identifying possible AD pathology- and gender-associated biomarkers. Here, we introduce a multiplexed, nondepleted mouse serum proteome profiling via tandem mass-tag (TMTpro) labeling. The labeled sample was separated into 475 fractions using basic reversed-phase liquid chromatography (RPLC), which were categorized into low-, medium-, and high-concentration fractions for concatenation. This concentration-dependent concatenation strategy resulted in 128 fractions for acidic RPLC-tandem mass spectrometry (MS/MS) analysis, collecting ∼5 million MS/MS scans and identifying 3972 unique proteins (3413 genes) that cover a dynamic range spanning at least 6 orders of magnitude. The differential expression analysis between wild type and the commonly used AD model (5xFAD) mice exhibited minimal significant protein alterations. However, we detected 60 statistically significant (FDR < 0.05), sex-specific proteins, including complement components, serpins, carboxylesterases, major urinary proteins, cysteine-rich secretory protein 1, pregnancy-associated murine protein 1, prolactin, amyloid P component, epidermal growth factor receptor, fibrinogen-like protein 1, and hepcidin. The results suggest that our platform possesses the sensitivity and reproducibility required to detect sex-specific differentially expressed proteins in mouse serum samples.

A strategic tool to improve the study of molecular determinants of Alzheimer's disease: The role of glyceraldehyde

Alzheimer's disease (AD) is the most prevalent form of dementia and is characterized by progressive neurodegeneration leading to severe cognitive, memory, and behavioral impairments. The onset of AD involves a complex interplay among various factors, including age, genetics, chronic inflammation, and impaired energy metabolism. Despite significant efforts, there are currently no effective therapies capable of modifying the course of AD, likely owing to an excessive focus on the amyloid hypothesis and a limited consideration of other intracellular pathways. In the present review, we emphasize the emerging concept of AD as a metabolic disease, where alterations in energy metabolism play a critical role in its development and progression. Notably, glucose metabolism impairment is associated with mitochondrial dysfunction, oxidative stress, Ca2+ dyshomeostasis, and protein misfolding, forming interconnected processes that perpetuate a detrimental self-feeding loop sustaining AD progression. Advanced glycation end products (AGEs), neurotoxic compounds that accumulate in AD, are considered an important consequence of glucose metabolism disruption, and glyceraldehyde (GA), a glycolytic intermediate, is a key contributor to AGEs formation in both neurons and astrocytes. Exploring the impact of GA-induced glucose metabolism impairment opens up exciting possibilities for creating an easy-to-handle in vitro model that recapitulates the early stage of the disease. This model holds great potential for advancing the development of novel therapeutics targeting various intracellular pathways implicated in AD pathogenesis. In conclusion, looking beyond the conventional amyloid hypothesis could lead researchers to discover promising targets for intervention, offering the possibility of addressing the existing medical gaps in AD treatment.

Recent progress of small-molecule-based theranostic agents in Alzheimer's disease

Alzheimer's disease (AD) is the most common form of neurodegenerative dementia. As a multifactorial disease, AD involves several etiopathogenic mechanisms, in which multiple pathological factors are interconnected with each other. This complicated and unclear pathogenesis makes AD lack effective diagnosis and treatment. Theranostics, exerting the synergistic effect of diagnostic and therapeutic functions, would provide a promising strategy for exploring AD pathogenesis and developing drugs for combating AD. With the efforts in small drug-like molecules for both diagnosis and treatment of AD, small-molecule-based theranostic agents have attracted significant attention owing to their facile synthesis, high biocompatibility and reproducibility, and easy clearance from the body through the excretion systems. In this review, the small-molecule-based theranostic agents reported in the literature for anti-AD are classified into four groups according to their diagnostic modalities. Their design rationales, chemical structures, and working mechanisms for theranostics are summarized. Finally, the opportunities for small-molecule-based theranostic agents in AD are also proposed.

From Recognition to Remedy: The Significance of Biomarkers in Neurodegenerative Disease Pathology

With the inexorable aging of the global populace, neurodegenerative diseases (NDs) like Alzheimer's disease (AD), Parkinson's disease (PD), and amyotrophic lateral sclerosis (ALS) pose escalating challenges, which are underscored by their socioeconomic repercussions. A pivotal aspect in addressing these challenges lies in the elucidation and application of biomarkers for timely diagnosis, vigilant monitoring, and effective treatment modalities. This review delineates the quintessence of biomarkers in the realm of NDs, elucidating various classifications and their indispensable roles. Particularly, the quest for novel biomarkers in AD, transcending traditional markers in PD, and the frontier of biomarker research in ALS are scrutinized. Emergent susceptibility and trait markers herald a new era of personalized medicine, promising enhanced treatment initiation especially in cases of SOD1-ALS. The discourse extends to diagnostic and state markers, revolutionizing early detection and monitoring, alongside progression markers that unveil the trajectory of NDs, propelling forward the potential for tailored interventions. The synergy between burgeoning technologies and innovative techniques like -omics, histologic assessments, and imaging is spotlighted, underscoring their pivotal roles in biomarker discovery. Reflecting on the progress hitherto, the review underscores the exigent need for multidisciplinary collaborations to surmount the challenges ahead, accelerate biomarker discovery, and herald a new epoch of understanding and managing NDs. Through a panoramic lens, this article endeavors to provide a comprehensive insight into the burgeoning field of biomarkers in NDs, spotlighting the promise they hold in transforming the diagnostic landscape, enhancing disease management, and illuminating the pathway toward efficacious therapeutic interventions.

Individualized Assessment of Brain Aβ Deposition With fMRI Using Deep Learning

PET-based Alzheimer's disease (AD) assessment has many limitations in large-scale screening. Non-invasive techniques such as resting-state functional magnetic resonance imaging (rs-fMRI) have been proven valuable in early AD diagnosis. This study investigated feasibility of using rs-fMRI, especially functional connectivity (FC), for individualized assessment of brain amyloid-β deposition derived from PET. We designed a graph convolutional networks (GCNs) and random forest (RF) based integrated framework for using rs-fMRI-derived multi-level FC networks to predict amyloid-β PET patterns with the OASIS-3 (N = 258) and ADNI-2 (N = 291) datasets. Our method achieved satisfactory accuracy not only in Aβ-PET grade classification (for negative, intermediate, and positive grades, with accuracy in the three-class classification as 62.8% and 64.3% on two datasets, respectively), but also in prediction of whole-brain region-level Aβ-PET standard uptake value ratios (SUVRs) (with the mean square errors as 0.039 and 0.074 for two datasets, respectively). Model interpretability examination also revealed the contributive role of the limbic network. This study demonstrated high feasibility and reproducibility of using low-cost, more accessible magnetic resonance imaging (MRI) to approximate PET-based diagnosis.

The association of body mass index and body composition with plasma amyloid beta levels

Blood-based analysis of amyloid-β is increasingly applied to incrementally establish diagnostic tests for Alzheimer's disease. To this aim, it is necessary to determine factors that can alter blood-based concentrations of amyloid-β. We cross-sectionally analysed amyloid-β-40 and amyloid-β-42 concentrations and the 40/42 ratio in 440 community-dwelling adults and associations with body mass index, waist-to-height ratio and body composition assessed using bioelectrical impedance analysis. Body mass index and waist-to-height ratio were inversely associated with plasma amyloid-β-42 concentrations. Body fat mass, but not body cell mass and extracellular mass, was inversely associated with amyloid-β-42 levels. The results indicate that plasma concentrations of amyloid-β-42 are lower in those with increased body mass index and body fat, and associations with amyloid-β-40 did not reach significance after controlling for multiple testing. The findings support the use of body mass index as an easy-to-measure factor that should be accounted for in diagnostic models for plasma amyloid-β.

Clinical considerations in early-onset cerebral amyloid angiopathy

Cerebral amyloid angiopathy (CAA) is an important cerebral small vessel disease associated with brain haemorrhage and cognitive change. The commonest form, sporadic amyloid-β CAA, usually affects people in mid- to later life. However, early-onset forms, though uncommon, are increasingly recognized and may result from genetic or iatrogenic causes that warrant specific and focused investigation and management. In this review, we firstly describe the causes of early-onset CAA, including monogenic causes of amyloid-β CAA (APP missense mutations and copy number variants; mutations of PSEN1 and PSEN2) and non-amyloid-β CAA (associated with ITM2B, CST3, GSN, PRNP and TTR mutations), and other unusual sporadic and acquired causes including the newly-recognized iatrogenic subtype. We then provide a structured approach for investigating early-onset CAA, and highlight important management considerations. Improving awareness of these unusual forms of CAA amongst healthcare professionals is essential for facilitating their prompt diagnosis, and an understanding of their underlying pathophysiology may have implications for more common, late-onset, forms of the disease.

Conv-eRVFL: Convolutional Neural Network Based Ensemble RVFL Classifier for Alzheimer's Disease Diagnosis

As per the latest statistics, Alzheimer's disease (AD) has become a global burden over the following decades. Identifying AD at the intermediate stage became challenging, with mild cognitive impairment (MCI) utilizing credible biomarkers and robust learning approaches. Neuroimaging techniques like magnetic resonance imaging (MRI) and positron emission tomography (PET) are practical research approaches that provide structural atrophies and metabolic variations. With the help of MRI and PET scans, metabolic and structural changes in AD patients can be visible even ten years before the disease's onset. This paper proposes a novel wavelet packet transform-based structural and metabolic image fusion approach using MRI and PET scans. An eight-layer trained CNN extracts features from multiple layers and these features are fed to an ensemble of non-iterative random vector functional link (RVFL) models. The RVFL network incorporates the s-membership fuzzy function as an activation function that helps overcome outliers. Lastly, outputs of all the customized RVFL classifiers are averaged and fed to the RVFL classifier to make the final decision. Experiments are performed over Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and classification is made over CN vs. AD vs. MCI. The model performance obtained is decent enough to prove the effectiveness of the fusion-based ensemble approach.

Radiochemistry for positron emission tomography

Positron emission tomography (PET) constitutes a functional imaging technique that is harnessed to probe biological processes in vivo. PET imaging has been used to diagnose and monitor the progression of diseases, as well as to facilitate drug development efforts at both preclinical and clinical stages. The wide applications and rapid development of PET have ultimately led to an increasing demand for new methods in radiochemistry, with the aim to expand the scope of synthons amenable for radiolabeling. In this work, we provide an overview of commonly used chemical transformations for the syntheses of PET tracers in all aspects of radiochemistry, thereby highlighting recent breakthrough discoveries and contemporary challenges in the field. We discuss the use of biologicals for PET imaging and highlight general examples of successful probe discoveries for molecular imaging with PET - with a particular focus on translational and scalable radiochemistry concepts that have been entered to clinical use.

Selective In Vitro and Ex Vivo Staining of Brain Neurofibrillary Tangles and Amyloid Plaques by Novel Ethylene Ethynylene-Based Optical Sensors

The identification of protein aggregates as biomarkers for neurodegeneration is an area of interest for disease diagnosis and treatment development. In this work, we present novel super luminescent conjugated polyelectrolyte molecules as ex vivo sensors for tau-paired helical filaments (PHFs) and amyloid-β (Aβ) plaques. We evaluated the use of two oligo-p-phenylene ethynylenes (OPEs), anionic OPE12- and cationic OPE24+, as stains for fibrillar protein pathology in brain sections of transgenic mouse (rTg4510) and rat (TgF344-AD) models of Alzheimer's disease (AD) tauopathy, and post-mortem brain sections from human frontotemporal dementia (FTD). OPE12- displayed selectivity for PHFs in fluorimetry assays and strong staining of neurofibrillary tangles (NFTs) in mouse and human brain tissue sections, while OPE24+ stained both NFTs and Aβ plaques. Both OPEs stained the brain sections with limited background or non-specific staining. This novel family of sensors outperformed the gold-standard dye Thioflavin T in sensing capacities and co-stained with conventional phosphorylated tau (AT180) and Aβ (4G8) antibodies. As the OPEs readily bind protein amyloids in vitro and ex vivo, they are selective and rapid tools for identifying proteopathic inclusions relevant to AD. Such OPEs can be useful in understanding pathogenesis and in creating in vivo diagnostically relevant detection tools for neurodegenerative diseases.

Urinary Amino Acid-Conjugated Acrolein and Taurine as New Biomarkers for Detection of Dementia

BACKGROUND

Dementia, including Alzheimer's disease (AD), is one of the serious diseases at advanced age, and its early detection is important for maintaining quality of life (QOL).

OBJECTIVE

In this study, we sought novel biomarkers for dementia in urine.

METHODS

Samples of urine were collected from 57 control subjects without dementia, 62 mild cognitive impairment (MCI) patients, and 42 AD patients. Mini-Mental State Examination (MMSE) was evaluated when subjects were examined by medical doctors. Urinary amino acid (lysine)-conjugated acrolein (AC-Acro) was measured using N ɛ-(3-formyl-3, 4-dehydropiperidine) lysine (FDP-Lys) ELISA kit, and taurine content was measured using a taurine assay kit. Values were normalized by creatinine content which was measured with the colorimetric assay kit.

RESULTS

We found that urinary amino acid (lysine)-conjugated acrolein (AC-Acro) and taurine negatively correlated with MMSE score and are significantly lower in dementia patients compared to the normal subjects. When AC-Acro and taurine were evaluated together with age using an artificial neural network model, median relative risk values for subjects with AD, subjects with mild cognitive impairment, and control subjects were 0.96, 0.53, and 0.06, respectively.

CONCLUSION

Since urine is relatively easy to collect, our findings provide a novel biomarker for dementia without invasiveness.

State-of-the-art imaging of neuromodulatory subcortical systems in aging and Alzheimer's disease: Challenges and opportunities

Primary prevention trials have shifted their focus to the earliest stages of Alzheimer's disease (AD). Autopsy data indicates that the neuromodulatory subcortical systems' (NSS) nuclei are specifically vulnerable to initial tau pathology, indicating that these nuclei hold great promise for early detection of AD in the context of the aging brain. The increasing availability of new imaging methods, ultra-high field scanners, new radioligands, and routine deep brain stimulation implants has led to a growing number of NSS neuroimaging studies on aging and neurodegeneration. Here, we review findings of current state-of-the-art imaging studies assessing the structure, function, and molecular changes of these nuclei during aging and AD. Furthermore, we identify the challenges associated with these imaging methods, important pathophysiologic gaps to fill for the AD NSS neuroimaging field, and provide future directions to improve our assessment, understanding, and clinical use of in vivo imaging of the NSS.

Multi-photon time-of-flight MLEM application for the positronium imaging in J-PET

We develop a positronium imaging method for the Jagiellonian PET (J-PET) scanners based on the time-of-flight maximum likelihood expectation maximisation (TOF MLEM). The system matrix elements are calculated on-the-fly for the coincidences comprising two annihilation and one de-excitation photons that originate from the ortho-positronium (o-Ps) decay. Using the Geant4 library, a Monte Carlo simulation was conducted for four cylindrical 22Na sources of β+ decay with diverse o-Ps mean lifetimes, placed symmetrically inside the two JPET prototypes. The estimated time differences between the annihilation and the positron emission were aggregated into histograms (one per voxel), updated by the weights of the activities reconstructed by TOF MLEM. The simulations were restricted to include only the o-Ps decays into back-to-back photons, allowing a linear fitting model to be employed for the estimation of the mean lifetime from each histogram built in the log scale. To suppress the noise, the exclusion of voxels with activity below 2% – 10% of the peak was studied. The estimated o-Ps mean lifetimes were consistent with the simulation and distributed quasi -uniformly at high MLEM iterations. The proposed positronium imaging technique can be further upgraded to include various correction factors, as well as be modified according to realistic o-Ps decay models.

Advanced Diagnostic Technique for Alzheimer's Disease using MRI Top-Ranked Volume and Surface-based Features

Background

Alzheimer's disease (AD) is the most dominant type of dementia that has not been treated completely yet. Few Alzheimer's patients are correctly diagnosed on time. Therefore, diagnostic tools are needed for better and more efficient diagnoses.

Objective

This study aimed to develop an efficient automated method to differentiate Alzheimer's patients from normal elderly and present the essential features with accurate Alzheimer's diagnosis.

Material and Methods

In this analytical study, 154 Magnetic Resonance Imaging (MRI) scans were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, preprocessed, and normalized by the head size for extracting features (volume, cortical thickness, Sulci depth, and Gyrification Index Features (GIF). Relief-F algorithm, t-test, and one way-ANOVA were used for feature ranking to obtain the most effective features representing the AD for the classification process. Finally, in the classification step, four classifiers were used with 10 folds cross-validation as follows: Gaussian Support Vector Machine (GSVM), Linear Support Vector Machine (LSVM), Weighted K-Nearest Neighbors (W-KNN), and Decision Tree algorithm.

Results

The LSVM classifier and W-KNN produce a testing accuracy of 100% with only seven features. Additionally, GSVM and decision tree produce a testing accuracy of 97.83% and 93.48%, respectively.

Conclusion

The proposed system represents an automatic and highly accurate AD detection with a few reliable and effective features and minimum time.

3T sodium MR imaging in Alzheimer's disease shows stage-dependent sodium increase influenced by age and local brain volume

INTRODUCTION

Application of MRI in clinical routine mainly addresses structural alterations. However, pathological changes at a cellular level are expected to precede the occurrence of brain atrophy clusters and of clinical symptoms. In this context, ²³Na-MRI examines sodium changes in the brain as a potential metabolic parameter. Recently, we have shown that ²³Na-MRI at ultra-high-field (7 T) was able to detect increased tissue sodium concentration (TSC) in Alzheimer's disease (AD). In this work, we aimed at assessing AD-pathology with ²³Na-MRI in a larger cohort and on a clinical 3T MR scanner.

METHODS

We used a multimodal MRI protocol on 52 prodromal to mild AD patients and 34 cognitively healthy control subjects on a clinical 3T MR scanner. We examined the TSC, brain volume, and cortical thickness in association with clinical parameters. We further compared TSC with intra-individual normalized TSC for the reduction of inter-individual TSC variability resulting from physiological as well as experimental conditions. Normalized TSC maps were created by normalizing each voxel to the mean TSC inside the brain stem.

RESULTS

We found increased normalized TSC in the AD cohort compared to elderly control subjects both on global as well as on a region-of-interest-based level. We further confirmed a significant association of local brain volume as well as age with TSC. TSC increase in the left temporal lobe was further associated with the cognitive state, evaluated via the Montreal cognitive assessment (MoCA) screening test. An increase of normalized TSC depending on disease stage reflected by the Clinical Dementia Rating (CDR) was found in our AD patients in temporal lobe regions. In comparison to classical brain volume and cortical thickness assessments, normalized TSC had a higher discriminative power between controls and prodromal AD patients in several regions of the temporal lobe.

DISCUSSION

We confirm the feasibility of ²³Na-MRI at 3T and report an increase of TSC in AD in several regions of the brain, particularly in brain regions of the temporal lobe. Furthermore, to reduce inter-subject variability caused by physiological factors such as circadian rhythms and experimental conditions, we introduced normalized TSC maps. This showed a higher discriminative potential between different clinical groups in comparison to the classical TSC analysis. In conclusion, ²³Na-MRI represents a potential translational imaging marker applicable e.g.for diagnostics and the assessment of intervention outcomes in AD even under clinically available field strengths such as 3T. Implication of ²³Na-MRI in association with other metabolic imaging marker needs to be further elucidated.

Near-Infrared Optical Transducer for Dynamic Imaging of Cerebrospinal Fluid Glucose in Brain Tumor

Aberrant cerebral glucose metabolism is related to many brain diseases, especially brain tumor. However, it remains challenging to measure the dynamic changes in cerebral glucose. Here, we developed a near-infrared (NIR) optical transducer to sensitively monitor the glucose variations in cerebrospinal fluid in vivo. The transducer consists of an oxygen-sensitive nanoparticle combined with glucose oxidase (GOx), yielding highly sensitive NIR phosphorescence in response to blood glucose change. We demonstrated long-term continuous glucose monitoring by using the NIR transducer. After subcutaneous implantation, the glucose transducer provides a strong luminescence signal that can continuously monitor blood glucose fluctuations for weeks. By using the NIR emission of the transducer, we further observed abnormal dynamic changes in cerebrospinal fluid glucose and quantitatively assessed cerebral glucose uptake rates in transgenic mice bearing brain tumors. This study provides a promising method for the diagnosis of various metabolic diseases with altered glucose metabolism.

Deep Learning Techniques for the Effective Prediction of Alzheimer’s Disease: A Comprehensive Review

“Alzheimer’s disease” (AD) is a neurodegenerative disorder in which the memory shrinks and neurons die. “Dementia” is described as a gradual decline in mental, psychological, and interpersonal qualities that hinders a person’s ability to function autonomously. AD is the most common degenerative brain disease. Among the first signs of AD are missing recent incidents or conversations. “Deep learning” (DL) is a type of “machine learning” (ML) that allows computers to learn by doing, much like people do. DL techniques can attain cutting-edge precision, beating individuals in certain cases. A large quantity of tagged information with multi-layered “neural network” architectures is used to perform analysis. Because significant advancements in computed tomography have resulted in sizable heterogeneous brain signals, the use of DL for the timely identification as well as automatic classification of AD has piqued attention lately. With these considerations in mind, this paper provides an in-depth examination of the various DL approaches and their implementations for the identification and diagnosis of AD. Diverse research challenges are also explored, as well as current methods in the field.

GA-MADRID: design and validation of a machine learning tool for the diagnosis of Alzheimer’s disease and frontotemporal dementia using genetic algorithms

Artificial Intelligence aids early diagnosis and development of new treatments, which is key to slow down the progress of the diseases, which to date have no cure. The patients’ evaluation is carried out through diagnostic techniques such as clinical assessments neuroimaging techniques, which provide high-dimensionality data. In this work, a computational tool is presented that deals with the data provided by the clinical diagnostic techniques. This is a Python-based framework implemented with a modular design and fully extendable. It integrates (i) data processing and management of missing values and outliers; (ii) implementation of an evolutionary feature engineering approach, developed as a Python package, called PyWinEA using Mono-objective and Multi-objetive Genetic Algorithms (NSGAII); (iii) a module for designing predictive models based on a wide range of machine learning algorithms; (iv) a multiclass decision stage based on evolutionary grammars and Bayesian networks. Developed under the eXplainable Artificial Intelligence and open science perspective, this framework provides promising advances and opens the door to the understanding of neurodegenerative diseases from a data-centric point of view. In this work, we have successfully evaluated the potential of the framework for early and automated diagnosis with neuroimages and neurocognitive assessments from patients with Alzheimer’s disease (AD) and frontotemporal dementia (FTD).

Graphical abstract

Perspectives and challenges in patient stratification in Alzheimer’s disease

Background

Patient stratification is the division of a patient population into distinct subgroups based on the presence or absence of particular disease characteristics. As patient stratification can be used to account for the underlying pathology of a disease, it can help physicians to tailor therapeutic interventions to individuals and optimize their care management and treatment regime. Alzheimer’s disease, the most common form of dementia, is a heterogeneous disease and its management benefits from patient stratification in clinical trials, and the development of personalized care and treatment strategies for people living with the disease.

Main body

In this review, we discuss the importance of the stratification of people living with Alzheimer’s disease, the challenges associated with early diagnosis and patient stratification, and the evolution of patient stratification once disease-modifying therapies become widely available.

Conclusion

Patient stratification plays an important role in drug development in clinical trials and may play an even larger role in clinical practice. A timely diagnosis and stratification of people living with Alzheimer’s disease is paramount in determining people who are at risk of progressing from mild cognitive impairment to Alzheimer’s dementia. There are key issues associated with stratifying patients which include the heterogeneity and complex neurobiology behind Alzheimer’s disease, our inadequately prepared healthcare systems, and the cultural perceptions of Alzheimer’s disease. Stratifying people living with Alzheimer’s disease may be the key in establishing precision and personalized medicine in the field, optimizing disease prevention and pharmaceutical treatment to slow or stop cognitive decline, while minimizing adverse effects.

Residual reserve index modifies the effect of amyloid pathology on fluorodeoxyglucose metabolism: Implications for efficiency and capacity in cognitive reserve

Background

The residual approach to measuring cognitive reserve (using the residual reserve index) aims to capture cognitive resilience conferred by cognitive reserve, but may be confounded by factors representing brain resilience. We sought to distinguish between brain and cognitive resilience by comparing interactions between the residual reserve index and amyloid, tau, and neurodegeneration [“AT(N)”] biomarkers when predicting executive function. We hypothesized that the residual reserve index would moderate at least one path from an AT(N) biomarker to executive function (consistent with cognitive resilience), as opposed to moderating a path between two AT(N) biomarkers (suggestive of brain resilience).

Methods

Participants (N = 332) were from the Alzheimer’s Disease Neuroimaging Initiative. The residual reserve index represented the difference between observed and predicted memory performance (a positive residual reserve index suggests higher cognitive reserve). AT(N) biomarkers were: CSF β-amyloid_1–42/β-amyloid_1–40 (A), plasma phosphorylated tau-181 (T), and FDG metabolism in AD-specific regions ([N]). AT(N) biomarkers (measured at consecutive time points) were entered in a sequential mediation model testing the indirect effects from baseline amyloid to executive function intercept (third annual follow-up) and slope (baseline to seventh follow-up), via tau and/or FDG metabolism. The baseline residual reserve index was entered as a moderator of paths between AT(N) biomarkers (e.g., amyloid-tau), and paths between AT(N) biomarkers and executive function.

Results

The residual reserve index interacted with amyloid pathology when predicting FDG metabolism: the indirect effect of amyloid → FDG metabolism → executive function intercept and slope varied as a function of the residual reserve index. With lower amyloid pathology, executive function performance was comparable at different levels of the residual reserve index, but a higher residual reserve index was associated with lower FDG metabolism. With higher amyloid pathology, a higher residual reserve index predicted better executive function via higher FDG metabolism.

Conclusion

The effect of the residual reserve index on executive function performance via FDG metabolism was consistent with cognitive resilience. This suggests the residual reserve index captures variation in cognitive reserve; specifically, neural efficiency, and neural capacity to upregulate metabolism to enhance cognitive resilience in the face of greater amyloid pathology. Implications for future research include the potential bidirectionality between neural efficiency and amyloid accumulation.

Human tau mutations in cerebral organoids induce a progressive dyshomeostasis of cholesterol

Mutations in the MAPT gene that encodes tau lead to frontotemporal dementia (FTD) with pathology evident in both cerebral neurons and glia. Human cerebral organoids (hCOs) from individuals harboring pathogenic tau mutations can reveal the earliest downstream effects on molecular pathways within a developmental context, generating interacting neurons and glia. We found that in hCOs carrying the V337M and R406W tau mutations, the cholesterol biosynthesis pathway in astrocytes was the top upregulated gene set compared with isogenic controls by single-cell RNA sequencing (scRNA-seq). The 15 upregulated genes included HMGCR, ACAT2, STARD4, LDLR, and SREBF2. This result was confirmed in a homozygous R406W mutant cell line by immunostaining and sterol measurements. Cholesterol abundance in the brain is tightly regulated by efflux and cholesterol biosynthetic enzyme levels in astrocytes, and dysregulation can cause aberrant phosphorylation of tau. Our findings suggest that cholesterol dyshomeostasis is an early event in the etiology of neurodegeneration caused by tau mutations.

•

Cerebral organoid models of tauopathy caused by MAPT mutations

•

Upregulated cholesterol and fatty acid biosynthesis genes in MAPT mutant astrocytes

•

Elevation of cholesterol and its precursors in MAPT mutant cerebral organoids

X-ray multiscale 3D neuroimaging to quantify cellular aging and neurodegeneration postmortem in a model of Alzheimer’s disease

Purpose

Modern neuroimaging lacks the tools necessary for whole-brain, anatomically dense neuronal damage screening. An ideal approach would include unbiased histopathologic identification of aging and neurodegenerative disease.

Methods

We report the postmortem application of multiscale X-ray phase-contrast computed tomography (X-PCI-CT) for the label-free and dissection-free organ-level to intracellular-level 3D visualization of distinct single neurons and glia. In deep neuronal populations in the brain of aged wild-type and of 3xTgAD mice (a triply-transgenic model of Alzheimer’s disease), we quantified intracellular hyperdensity, a manifestation of aging or neurodegeneration.

Results

In 3xTgAD mice, the observed hyperdensity was identified as amyloid-β and hyper-phosphorylated tau protein deposits with calcium and iron involvement, by correlating the X-PCI-CT data to immunohistochemistry, X-ray fluorescence microscopy, high-field MRI, and TEM. As a proof-of-concept, X-PCI-CT was used to analyze hippocampal and cortical brain regions of 3xTgAD mice treated with LY379268, selective agonist of group II metabotropic glutamate receptors (mGlu2/3 receptors). Chronic pharmacologic activation of mGlu2/3 receptors significantly reduced the hyperdensity particle load in the ventral cortical regions of 3xTgAD mice, suggesting a neuroprotective effect with locoregional efficacy.

Conclusions

This multiscale micro-to-nano 3D imaging method based on X-PCI-CT enabled identification and quantification of cellular and sub-cellular aging and neurodegeneration in deep neuronal and glial cell populations in a transgenic model of Alzheimer’s disease. This approach quantified the localized and intracellular neuroprotective effects of pharmacological activation of mGlu2/3 receptors.

Positron Emission Tomography-Based Assessment of Cognitive Impairment and Dementias, Critical Role of Fluorodeoxyglucose in such Settings

Positron emission tomography (PET) has been a key component in the diagnostic armamentarium for assessing neurodegenerative diseases such as Alzheimer or Parkinson disease. PET imaging has been useful for diagnosing these disorders, identifying their pathophysiology, and following their treatment. Further, PET imaging has been extensively used for both clinical and research purposes, particularly for helping with potential therapeutic approaches for managing neurodegenerative diseases. This article will review the current literature regarding PET imaging in patients with neurodegenerative disorders. This includes an evaluation of the most commonly used tracer fluorodeoxyglucose that measures cerebral glucose metabolism, tracers that assess neurotransmitter systems, and tracers designed to reveal disease-specific pathophysiological processes. With the continuing development of an expanding variety of radiopharmaceuticals, PET imaging will likely play a prominent role in future research and clinical applications for neurodegenerative diseases.

Lipids as Early and Minimally Invasive Biomarkers for Alzheimer's Disease

Alzheimer's disease (AD) is the most common neurodegenerative disorder worldwide. Specifically, typical late-onset AD is a sporadic form with a complex etiology that affects over 90% of patients. The current gold standard for AD diagnosis is based on the determination of amyloid status by analyzing cerebrospinal fluid samples or brain positron emission tomography. These procedures can be used widely as they have several disadvantages (expensive, invasive). As an alternative, blood metabolites have recently emerged as promising AD biomarkers. Small molecules that cross the compromised AD blood-brain barrier could be determined in plasma to improve clinical AD diagnosis at early stages through minimally invasive techniques. Specifically, lipids could play an important role in AD since the brain has a high lipid content, and they are present ubiquitously inside amyloid plaques. Therefore, a systematic review was performed with the aim of identifying blood lipid metabolites as potential early AD biomarkers. In conclusion, some lipid families (fatty acids, glycerolipids, glycerophospholipids, sphingolipids, lipid peroxidation compounds) have shown impaired levels at early AD stages. Ceramide levels were significantly higher in AD subjects, and polyunsaturated fatty acids levels were significantly lower in AD. Also, high arachidonic acid levels were found in AD patients in contrast to low sphingomyelin levels. Consequently, these lipid biomarkers could be used for minimally invasive and early AD clinical diagnosis.

WTD-PSD: Presentation of Novel Feature Extraction Method Based on Discrete Wavelet Transformation and Time-Dependent Power Spectrum Descriptors for Diagnosis of Alzheimer's Disease

Alzheimer's disease (AD) is a type of dementia that affects the elderly population. A machine learning (ML) system has been trained to recognize particular patterns to diagnose AD using an algorithm in an ML system. As a result, developing a feature extraction approach is critical for reducing calculation time. The input image in this article is a Two-Dimensional Discrete Wavelet (2D-DWT). The Time-Dependent Power Spectrum Descriptors (TD-PSD) model is used to represent the subbanded wavelet coefficients. The principal property vector is made up of the characteristics of the TD-PSD model. Based on classification algorithms, the collected characteristics are applied independently to present AD classifications. The categorization is used to determine the kind of tumor. The TD-PSD method was used to extract wavelet subbands features from three sets of test samples: moderate cognitive impairment (MCI), AD, and healthy controls (HC). The outcomes of three modes of classic classification methods, including KNN, SVM, Decision Tree, and LDA approaches, are documented, as well as the final feature employed in each. Finally, we show the CNN architecture for AD patient classification. Output assessment is used to show the results. Other techniques are outperformed by the given CNN and DT.

Blood phospho-tau in Alzheimer disease: analysis, interpretation, and clinical utility

Well-authenticated biomarkers can provide critical insights into the biological basis of Alzheimer disease (AD) to enable timely and accurate diagnosis, estimate future burden and support therapeutic trials. Current cerebrospinal fluid and molecular neuroimaging biomarkers fulfil these criteria but lack the scalability and simplicity necessary for widespread application. Blood biomarkers of adequate effectiveness have the potential to act as first-line diagnostic and prognostic tools, and offer the possibility of extensive population screening and use that is not limited to specialized centres. Accelerated progress in our understanding of the biochemistry of brain-derived tau protein and advances in ultrasensitive technologies have enabled the development of AD-specific phosphorylated tau (p-tau) biomarkers in blood. In this Review we discuss how new information on the molecular processing of brain p-tau and secretion of specific fragments into biofluids is informing blood biomarker development, enabling the evaluation of preanalytical factors that affect quantification, and informing harmonized protocols for blood handling. We also review the performance of blood p-tau biomarkers in the context of AD and discuss their potential contexts of use for clinical and research purposes. Finally, we highlight outstanding ethical, clinical and analytical challenges, and outline the steps that need to be taken to standardize inter-laboratory and inter-assay measurements.

Multimer Detection System-Oligomerized Amyloid Beta (MDS-OAβ): A Plasma-Based Biomarker Differentiates Alzheimer's Disease from Other Etiologies of Dementia

With emerging amyloid therapies, documentation of the patient's amyloid status to confirm the etiology of a clinical diagnosis is warranted prior to instituting amyloid-based therapy. The Multimer Detection System-Oligomeric Amyloid-β (MDS-OAβ) is a noninvasive blood-based biomarker utilized to measure Aβ oligomerization tendency. We determined the difference in MDS-OAβ ratio across the groups: (a) no cognitive impairment or subjective cognitive impairment (NCI/SCI), (b) Alzheimer's disease (AD), (c) non-AD, and (d) mixed Alzheimer's disease-Vascular dementia (AD-VaD). MDS-OAβ level was not significantly different between AD and mixed AD-VaD, but both groups were significantly different from the NCI/SCI and from the non-AD group. An MDS-OAβ level of >1 could potentially indicate clinical variants of AD or mixed pathology (AD-VaD).

Effect of Denoising and Deblurring 18F-Fluorodeoxyglucose Positron Emission Tomography Images on a Deep Learning Model’s Classification Performance for Alzheimer’s Disease

Alzheimer’s disease (AD) is the most common progressive neurodegenerative disease. 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) is widely used to predict AD using a deep learning model. However, the effects of noise and blurring on 18F-FDG PET images were not considered. The performance of a classification model trained using raw, deblurred (by the fast total variation deblurring method), or denoised (by the median modified Wiener filter) 18F-FDG PET images without or with cropping around the limbic system area using a 3D deep convolutional neural network was investigated. The classification model trained using denoised whole-brain 18F-FDG PET images achieved classification performance (0.75/0.65/0.79/0.39 for sensitivity/specificity/F1-score/Matthews correlation coefficient (MCC), respectively) higher than that with raw and deblurred 18F-FDG PET images. The classification model trained using cropped raw 18F-FDG PET images achieved higher performance (0.78/0.63/0.81/0.40 for sensitivity/specificity/F1-score/MCC) than the whole-brain 18F-FDG PET images (0.72/0.32/0.71/0.10 for sensitivity/specificity/F1-score/MCC, respectively). The 18F-FDG PET image deblurring and cropping (0.89/0.67/0.88/0.57 for sensitivity/specificity/F1-score/MCC) procedures were the most helpful for improving performance. For this model, the right middle frontal, middle temporal, insula, and hippocampus areas were the most predictive of AD using the class activation map. Our findings demonstrate that 18F-FDG PET image preprocessing and cropping improves the explainability and potential clinical applicability of deep learning models.

Predicting Brain Amyloid-β PET Grades with Graph Convolutional Networks Based on Functional MRI and Multi-Level Functional Connectivity

BACKGROUND

The detection of amyloid-β (Aβ) deposition in the brain provides crucial evidence in the clinical diagnosis of Alzheimer's disease (AD). However, the current positron emission tomography (PET)-based brain Aβ examination suffers from the problems of coarse visual inspection (in many cases, with 2-class stratification) and high scanning cost.

OBJECTIVE

1) To characterize the non-binary Aβ deposition levels in the AD continuum based on clustering of PET data, and 2) to explore the feasibility of predicting individual Aβ deposition grades with non-invasive functional magnetic resonance imaging (fMRI).

METHODS

1) Individual whole-brain Aβ-PET images from the OASIS-3 dataset (N = 258) were grouped into three clusters (grades) with t-SNE and k-means. The demographical data as well as global and regional standard uptake value ratios (SUVRs) were compared among the three clusters with Chi-square tests or ANOVA tests. 2) From resting-state fMRI, both conventional functional connectivity (FC) and high-order FC networks were constructed and the topological architectures of the two networks were jointly learned with graph convolutional networks (GCNs) to predict the Aβ-PET grades for each individual.

RESULTS

We found three clearly separated clusters, indicating three Aβ-PET grades. There were significant differences in gender, age, cognitive ability, APOE type, as well as global and regional SUVRs among the three grades we found. The prediction of Aβ-PET grades with GCNs on FC for the 258 participants in the AD continuum reached a satisfactory averaged accuracy (78.8%) in the two-class classification tasks.

CONCLUSION

The results demonstrated the feasibility of using deep learning on a non-invasive brain functional imaging technique to approximate PET-based Aβ deposition grading.

A few-shot U-Net deep learning model for lung cancer lesion segmentation via PET/CT imaging

Over the past few years, positron emission tomography/computed tomography (PET/CT) imaging for computer-aided diagnosis has received increasing attention. Supervised deep learning architectures are usually employed for the detection of abnormalities, with anatomical localization, especially in the case of CT scans. However, the main limitations of the supervised learning paradigm include (i) large amounts of data required for model training, and (ii) the assumption of fixed network weights upon training completion, implying that the performance of the model cannot be further improved after training. In order to overcome these limitations, we apply a few-shot learning (FSL) scheme. Contrary to traditional deep learning practices, in FSL the model is provided with less data during training. The model then utilizes end-user feedback after training to constantly improve its performance. We integrate FSL in a U-Net architecture for lung cancer lesion segmentation on PET/CT scans, allowing for dynamic model weight fine-tuning and resulting in an online supervised learning scheme. Constant online readjustments of the model weights according to the user's feedback, increase the detection and classification accuracy, especially in cases where low detection performance is encountered. Our proposed method is validated on the Lung-PET-CT-DX TCIA database. PET/CT scans from 87 patients were included in the dataset and were acquired 60 minutes after intravenous¹⁸F-FDG injection. Experimental results indicate the superiority of our approach compared to other state of the art methods.

Combined Structural MR and Diffusion Tensor Imaging Classify the Presence of Alzheimer's Disease With the Same Performance as MR Combined With Amyloid Positron Emission Tomography: A Data Integration Approach

Background: In recent years, classification frameworks using imaging data have shown that multimodal classification methods perform favorably over the use of a single imaging modality for the diagnosis of Alzheimer's Disease. The currently used clinical approach often emphasizes the use of qualitative MRI and/or PET data for clinical diagnosis. Based on the hypothesis that classification of isolated imaging modalities is not predictive of their respective value in combined approaches, we investigate whether the combination of T1 Weighted MRI and diffusion tensor imaging (DTI) can yield an equivalent performance as the combination of quantitative structural MRI (sMRI) with amyloid-PET. Methods: We parcellated the brain into regions of interest (ROI) following different anatomical labeling atlases. For each region of interest different metrics were extracted from the different imaging modalities (sMRI, PiB-PET, and DTI) to be used as features. Thereafter, the feature sets were reduced using an embedded-based feature selection method. The final reduced sets were then used as input in support vector machine (SVM) classifiers. Three different base classifiers were created, one for each imaging modality, and validated using internal (n = 41) and external data from the ADNI initiative (n = 330 for sMRI, n = 148 for DTI and n = 55 for PiB-PET) sources. Finally, the classifiers were ensembled using a weighted method in order to evaluate the performance of different combinations. Results: For the base classifiers the following performance levels were found: sMRI-based classifier (accuracy, 92%; specificity, 97% and sensitivity, 87%), PiB-PET (accuracy, 91%; specificity, 89%; and sensitivity, 92%) and the lowest performance was attained with DTI (accuracy, 80%; specificity, 76%; and sensitivity, 82%). From the multimodal approaches, when integrating two modalities, the following results were observed: sMRI+PiB-PET (accuracy, 98%; specificity, 98%; and sensitivity, 99%), sMRI+DTI (accuracy, 97%; specificity, 99%; and sensitivity, 94%) and PiB-PET+DTI (accuracy, 91%; specificity, 90%; and sensitivity, 93%). Finally, the combination of all imaging modalities yielded an accuracy of 98%, specificity of 97% and sensitivity of 99%. Conclusion: Although DTI in isolation shows relatively poor performance, when combined with structural MR, it showed a surprising classification performance which was comparable to MR combined with amyloid PET. These results are consistent with the notion that white matter changes are also important in Alzheimer's Disease.

Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis

Fusing multi-modality medical images, such as magnetic resonance (MR) imaging and positron emission tomography (PET), can provide various anatomical and functional information about the human body. However, PET data is not always available for several reasons, such as high cost, radiation hazard, and other limitations. This paper proposes a 3D end-to-end synthesis network called Bidirectional Mapping Generative Adversarial Networks (BMGAN). Image contexts and latent vectors are effectively used for brain MR-to-PET synthesis. Specifically, a bidirectional mapping mechanism is designed to embed the semantic information of PET images into the high-dimensional latent space. Moreover, the 3D Dense-UNet generator architecture and the hybrid loss functions are further constructed to improve the visual quality of cross-modality synthetic images. The most appealing part is that the proposed method can synthesize perceptually realistic PET images while preserving the diverse brain structures of different subjects. Experimental results demonstrate that the performance of the proposed method outperforms other competitive methods in terms of quantitative measures, qualitative displays, and evaluation metrics for classification.

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.

CD4+ effector T cells accelerate Alzheimer's disease in mice

BACKGROUND

Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by pathological deposition of misfolded self-protein amyloid beta (Aβ) which in kind facilitates tau aggregation and neurodegeneration. Neuroinflammation is accepted as a key disease driver caused by innate microglia activation. Recently, adaptive immune alterations have been uncovered that begin early and persist throughout the disease. How these occur and whether they can be harnessed to halt disease progress is unclear. We propose that self-antigens would induct autoreactive effector T cells (Teffs) that drive pro-inflammatory and neurodestructive immunity leading to cognitive impairments. Here, we investigated the role of effector immunity and how it could affect cellular-level disease pathobiology in an AD animal model.

METHODS

In this report, we developed and characterized cloned lines of amyloid beta (Aβ) reactive type 1 T helper (Th1) and type 17 Th (Th17) cells to study their role in AD pathogenesis. The cellular phenotype and antigen-specificity of Aβ-specific Th1 and Th17 clones were confirmed using flow cytometry, immunoblot staining and Aβ T cell epitope loaded haplotype-matched major histocompatibility complex II IAb (MHCII-IAb-KLVFFAEDVGSNKGA) tetramer binding. Aβ-Th1 and Aβ-Th17 clones were adoptively transferred into APP/PS1 double-transgenic mice expressing chimeric mouse/human amyloid precursor protein and mutant human presenilin 1, and the mice were assessed for memory impairments. Finally, blood, spleen, lymph nodes and brain were harvested for immunological, biochemical, and histological analyses.

RESULTS

The propagated Aβ-Th1 and Aβ-Th17 clones were confirmed stable and long-lived. Treatment of APP/PS1 mice with Aβ reactive Teffs accelerated memory impairment and systemic inflammation, increased amyloid burden, elevated microglia activation, and exacerbated neuroinflammation. Both Th1 and Th17 Aβ-reactive Teffs progressed AD pathology by downregulating anti-inflammatory and immunosuppressive regulatory T cells (Tregs) as recorded in the periphery and within the central nervous system.

CONCLUSIONS

These results underscore an important pathological role for CD4+ Teffs in AD progression. We posit that aberrant disease-associated effector T cell immune responses can be controlled. One solution is by Aβ reactive Tregs.

Amyloid and Tau in Alzheimer's Disease: Biomarkers or Molecular Targets for Therapy? Are We Shooting the Messenger?

Alzheimer's disease is a neuropsychiatric disorder with devastating clinical and socioeconomic consequences. Since the original description of the neuropathological correlates of the disorder, neuritic plaques and neurofibrillary tangles have been presumed to be critical to the underlying pathophysiology of the illness. The authors review the clinical and neuropathological origins of Alzheimer's disease and trace the evolution of modern biomarkers from their historical roots. They describe how technological innovations such as neuroimaging and biochemical assays have been used to measure and quantify key proteins and lipids in the brain, cerebrospinal fluid, and blood and advance their role as biomarkers of Alzheimer's disease. Together with genomics, these approaches have led to the development of a thematic and focused science in the area of degenerative disorders. The authors conclude by drawing distinctions between legitimate biomarkers of disease and molecular targets for therapeutic intervention and discuss future approaches to this complex neurobehavioral illness.

In situ identification and G4-PPI-His-Mal-dendrimer-induced reduction of early-stage amyloid aggregates in Alzheimer's disease transgenic mice using synchrotron-based infrared imaging

Amyloid plaques composed of Aβ amyloid peptides and neurofibrillary tangles are a pathological hallmark of Alzheimer Disease. In situ identification of early-stage amyloid aggregates in Alzheimer's disease is relevant for their importance as potential targets for effective drugs. Synchrotron-based infrared imaging is here used to identify early-stage oligomeric/granular aggregated amyloid species in situ in the brain of APP/PS1 transgenic mice for the first time. Also, APP/PS1 mice show fibrillary aggregates at 6 and 12 months. A significant decreased burden of early-stage aggregates and fibrillary aggregates is obtained following treatment with poly(propylene imine) dendrimers with histidine-maltose shell (a neurodegenerative protector) in 6-month-old APP/PS1 mice, thus demonstrating their putative therapeutic properties of in AD models. Identification, localization, and characterization using infrared imaging of these non-fibrillary species in the cerebral cortex at early stages of AD progression in transgenic mice point to their relevance as putative pharmacological targets. No less important, early detection of these structures may be useful in the search for markers for non-invasive diagnostic techniques.

On the Common Journey of Neural Cells through Ischemic Brain Injury and Alzheimer's Disease

Ischemic brain injury and Alzheimer's disease (AD) both lead to cell death in the central nervous system (CNS) and thus negatively affect particularly the elderly population. Due to the lack of a definitive cure for brain ischemia and AD, it is advisable to carefully study, compare, and contrast the mechanisms that trigger, and are involved in, both neuropathologies. A deeper understanding of these mechanisms may help ameliorate, or even prevent, the destructive effects of neurodegenerative disorders. In this review, we deal with ischemic damage and AD, with the main emphasis on the common properties of these CNS disorders. Importantly, we discuss the Wnt signaling pathway as a significant factor in the cell fate determination and cell survival in the diseased adult CNS. Finally, we summarize the interesting findings that may improve or complement the current sparse and insufficient treatments for brain ischemia and AD, and we delineate prospective directions in regenerative medicine.

Early Detection of Alzheimer's Disease Based on Clinical Trials, Three-Dimensional Imaging Data, and Personal Information Using Autoencoders

Background:

A timely diagnosis of Alzheimer's disease (AD) is crucial to obtain more practical treatments. In this article, a novel approach using Auto-Encoder Neural Networks (AENN) for early detection of AD was proposed.

Method:

The proposed method mainly deals with the classification of multimodal data and the imputation of missing data. The data under study involve the MiniMental State Examination, magnetic resonance imaging, positron emission tomography, cerebrospinal fluid data, and personal information. Natural logarithm was used for normalizing the data. The Auto-Encoder Neural Networks was used for imputing missing data. Principal component analysis algorithm was used for reducing dimensionality of data. Support Vector Machine (SVM) was used as classifier. The proposed method was evaluated using Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Then, 10fold crossvalidation was used to audit the detection accuracy of the method.

Results:

The effectiveness of the proposed approach was studied under several scenarios considering 705 cases of ADNI database. In three binary classification problems, that is AD vs. normal controls (NCs), mild cognitive impairment (MCI) vs. NC, and MCI vs. AD, we obtained the accuracies of 95.57%, 83.01%, and 78.67%, respectively.

Conclusion:

Experimental results revealed that the proposed method significantly outperformed most of the stateoftheart methods.

D-Glucose uptake and clearance in the tauopathy Alzheimer's disease mouse brain detected by on-resonance variable delay multiple pulse MRI

In this study, we applied on-resonance variable delay multiple pulse (onVDMP) MRI to study D-glucose uptake in a mouse model of Alzheimer's disease (AD) tauopathy and demonstrated its feasibility in discriminating AD mice from wild-type mice. The D-glucose uptake in the cortex of AD mice (1.70 ± 1.33%) was significantly reduced compared to that of wild-type mice (5.42 ± 0.70%, p = 0.0051). Also, a slower D-glucose uptake rate was found in the cerebrospinal fluid (CSF) of AD mice (0.08 ± 0.01 min-1) compared to their wild-type counterpart (0.56 ± 0.1 min-1, p < 0.001), which suggests the presence of an impaired glucose transporter on both blood-brain and blood-CSF barriers of these AD mice. Clearance of D-glucose was observed in the CSF of wild-type mice but not AD mice, which suggests dysfunction of the glymphatic system in the AD mice. The results in this study indicate that onVDMP MRI could be a cost-effective and widely available method for simultaneously evaluating glucose transporter and glymphatic function of AD. This study also suggests that tau protein affects the D-glucose uptake and glymphatic impairment in AD at a time point preceding neurofibrillary tangle pathology.