A multi-scale feature selection module based architecture for the diagnosis of Alzheimer's disease on [18F]FDG PET

OBJECTIVE

Alzheimer's disease (AD) is a prevalent form of dementia worldwide as a cryptic neurodegenerative disease. The symptoms of AD will last for several years, which brings great mental and economic burden to patients and their families. Unfortunately, the complete cure of AD still faces great challenges. Therefore, it is crucial to diagnose the disease in the early stage.

MATERIALS AND METHODS

The Visual Geometry Group (VGG) network serves as the backbone for feature extraction, which could reduce the time cost of network training to a certain extent. In order to better extract image information and pay attention to the association information in the images, the group convolutional module and the multi-scale RNN-based feature selection module are proposed. The dataset employed in the study are drawn from [18F]FDG-PET images within the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.

RESULTS

Comprehensive experimental results show that the proposed model outperforms several competing approaches in AD-related diagnostic tasks. In addition, the model reduces the number of parameters of the model compared to the backbone model, from 134.27 M to 17.36 M. Furthermore, the ablation reaserch is conducted to confirm the effectiveness of the proposed module.

CONCLUSIONS

The paper introduces a lightweight network architecture for the early diagnosis of AD. In contrast to analogous methodologies, the proposed method yields acceptable results.

Poor sleep quality is associated with decreased regional brain glucose metabolism in healthy middle-aged adults

Sleep disturbance is associated with the development of neurodegenerative disease. We aimed to address the effects of sleep quality on brain glucose metabolism measured by 18F-Fl uorodeoxyglucose (18F-FDG) positron emission tomography (PET) in healthy middle-aged adults. A total of 378 healthy men (mean age: 42.8±3.6 years) were included in this study. Participants underwent brain 18F-FDG PET and completed the Korean version of the Pittsburgh Sleep Quality Index (PSQI-K). Additionally, anthropometric measurements were obtained. PETs were spatially normalized to MNI space using PET templates from SPM5 with PMOD. The Automated Anatomical Labeling 2 atlas was used to define regions of interest (ROIs). The mean uptake of each ROI was scaled to the mean of the global cortical uptake of each individual and defined as the standardized uptake value ratio (SUVR). After the logarithmic transformation of the regional SUVR, the effects of the PSQI-K on the regional SUVR were investigated using Bayesian hierarchical modeling. Brain glucose metabolism of the posterior cingulate, precuneus, and thalamus showed a negative association with total PSQI-K scores in the Bayesian model ROI-based analysis. Voxel-based analysis using statistical parametric mapping revealed a negative association between the total PSQI-K scores and brain glucose metabolism of the precuneus, postcentral gyrus, posterior cingulate, and thalamus. Poor sleep quality is negatively associated with brain glucose metabolism in the precuneus, posterior cingulate, and thalamus. Therefore, the importance of sleep should not be overlooked, even in healthy middle-aged adults.

Recent advances in Alzheimer's disease: Mechanisms, clinical trials and new drug development strategies

Alzheimer's disease (AD) stands as the predominant form of dementia, presenting significant and escalating global challenges. Its etiology is intricate and diverse, stemming from a combination of factors such as aging, genetics, and environment. Our current understanding of AD pathologies involves various hypotheses, such as the cholinergic, amyloid, tau protein, inflammatory, oxidative stress, metal ion, glutamate excitotoxicity, microbiota-gut-brain axis, and abnormal autophagy. Nonetheless, unraveling the interplay among these pathological aspects and pinpointing the primary initiators of AD require further elucidation and validation. In the past decades, most clinical drugs have been discontinued due to limited effectiveness or adverse effects. Presently, available drugs primarily offer symptomatic relief and often accompanied by undesirable side effects. However, recent approvals of aducanumab (1) and lecanemab (2) by the Food and Drug Administration (FDA) present the potential in disrease-modifying effects. Nevertheless, the long-term efficacy and safety of these drugs need further validation. Consequently, the quest for safer and more effective AD drugs persists as a formidable and pressing task. This review discusses the current understanding of AD pathogenesis, advances in diagnostic biomarkers, the latest updates of clinical trials, and emerging technologies for AD drug development. We highlight recent progress in the discovery of selective inhibitors, dual-target inhibitors, allosteric modulators, covalent inhibitors, proteolysis-targeting chimeras (PROTACs), and protein-protein interaction (PPI) modulators. Our goal is to provide insights into the prospective development and clinical application of novel AD drugs.

Deuterium Metabolic Imaging of Alzheimer Disease at 3-T Magnetic Field Strength: A Pilot Case-Control Study

Background Impaired glucose metabolism is characteristic of several types of dementia, preceding cognitive symptoms and structural brain changes. Reduced glucose uptake in specific brain regions, detected using fluorine 18 (18F) fluorodeoxyglucose (FDG) PET, is a valuable diagnostic marker in Alzheimer disease (AD). However, the use of 18F-FDG PET in clinical practice may be limited by equipment availability and high cost. Purpose To test the feasibility of using MRI-based deuterium (2H) metabolic imaging (DMI) at a clinical magnetic field strength (3 T) to detect and localize changes in the concentration of glucose and its metabolites in the brains of patients with a clinical diagnosis of AD. Materials and Methods Participants were recruited for this prospective case-control pilot study between March 2021 and February 2023. DMI was performed at 3 T using a custom birdcage head coil following oral administration of deuterium-labeled glucose (0.75 g/kg). Unlocalized whole-brain MR spectroscopy (MRS) and three-dimensional MR spectroscopic imaging (MRSI) (voxel size, 3.2 cm cubic) were performed. Ratios of 2H-glucose, 2H-glutamate and 2H-glutamine (2H-Glx), and 2H-lactate spectroscopic peak signals to 2H-water peak signal were calculated for the whole-brain MR spectra and for individual MRSI voxels. Results A total of 19 participants, including 10 participants with AD (mean age, 68 years ± 5 [SD]; eight males) and nine cognitively healthy control participants (mean age, 70 years ± 6; six males) were evaluated. Whole-brain spectra demonstrated a reduced ratio of 2H-Glx to 2H-glucose peak signals in participants with AD compared with control participants (0.41 ± 0.09 vs 0.58 ± 0.20, respectively; P = .04), suggesting an impairment of oxidative glucose metabolism in AD. However, there was no evidence of localization of these changes to the expected regions of metabolic impairment at MRSI, presumably due to insufficient spatial resolution. Conclusion DMI at 3 T demonstrated impairment of oxidative glucose metabolism in the brains of patients with AD but no evidence of regional signal differences. © RSNA, 2024 Supplemental material is available for this article.

Union is strength: the combination of radiomics features and 3D-deep learning in a sole model increases diagnostic accuracy in demented patients: a whole brain 18FDG PET-CT analysis

OBJECTIVE

FDG PET imaging plays a crucial role in the evaluation of demented patients by assessing regional cerebral glucose metabolism. In recent years, both radiomics and deep learning techniques have emerged as powerful tools for extracting valuable information from medical images. This article aims to provide a comparative analysis of radiomics features, 3D-deep learning convolutional neural network (CNN) and the fusion of them, in the evaluation of 18F-FDG PET whole brain images in patients with dementia and normal controls.

METHODS

18F-FDG brain PET and clinical score were collected in 85 patients with dementia and 125 healthy controls (HC). Patients were assigned to various form of dementia on the basis of clinical evaluation, follow-up and voxels comparison with HC using a two-sample Student's t -test, to determine the regions of brain involved. Radiomics analysis was performed on the whole brain after normalization to an optimized template. After selection using the minimum redundancy maximum relevance method and Pearson's correlation coefficients, the features obtained were added to a neural network model to find the accuracy in classifying HC and demented patients. Forty subjects not included in the training were used to test the models. The results of the three models (radiomics, 3D-CNN, combined model) were compared with each other.

RESULTS

Four radiomics features were selected. The sensitivity was 100% for the three models, but the specificity was higher with radiomics and combined one (100% vs. 85%). Moreover, the classification scores were significantly higher using the combined model in both normal and demented subjects.

CONCLUSION

The combination of radiomics features and 3D-CNN in a single model, applied to the whole brain 18FDG PET study, increases the accuracy in demented patients.

Mitigation of CXCL10 secretion by metabolic disorder drugs in microglial-mediated neuroinflammation

Metabolic disorders are associated with several neurodegenerative diseases. We previously identified C-X-C motif chemokine ligand 10 (CXCL10), also known as interferon gamma-induced protein 10 (IP-10), as a major contributor to the type I interferon response in microglial-mediated neuroinflammation. Therefore, we hypothesized FDA-approved metabolic disorder drugs that attenuate CXCL10 secretion may be repurposed as a treatment for neurodegenerative diseases. Screening, dose curves, and cytotoxicity assays in LPS-stimulated microglia yielded treprostinil (hypertension), pitavastatin (hyperlipidemia), and eplerenone (hypertension) as candidates that significantly reduced CXCL10 secretion (in addition to other pro-inflammatory mediators) without impacting cell viability. Altogether, these data suggest metabolic disorder drugs that attenuate CXCL10 as potential treatments for neurodegenerative disease through mitigating microglial-mediated neuroinflammation.

Cognitive Impairment in the Primary Care Clinic

Cognitive impairment is a common problem in the geriatric population and is characterized by variable symptoms of memory difficulties, executive dysfunction, language or visuospatial problems, and behavioral changes. It is imperative that primary care clinicians recognize and differentiate the variable symptoms associated with cognitive impairment from changes attributable to normal aging or secondary to other medical conditions. A thorough evaluation for potentially reversible causes of dementia is required before diagnosis with a neurodegenerative dementia. Other abnormal neurologic findings, rapid progression, or early age of onset are red flags that merit referral to neurology for more specialized evaluation and treatment.

Cerebral Metabolic Signature of Chronic Benzodiazepine Use in Nondemented Older Adults: An FDG-PET Study in the MEMENTO Cohort

OBJECTIVE

We sought to examine the association between chronic Benzodiazepine (BZD) use and brain metabolism obtained from 2-deoxy-2-fluoro-D-glucose (FDG) positron emission tomography (PET) in the MEMENTO clinical cohort of nondemented older adults with an isolated memory complaint or mild cognitive impairment at baseline.

METHODS

Our analysis focused on 3 levels: (1) the global mean brain standardized uptake value (SUVR), (2) the Alzheimer's disease (AD)-specific regions of interest (ROIs), and (3) the ratio of total SUVR on the brain and different anatomical ROIs. Cerebral metabolism was obtained from 2-deoxy-2-fluoro-D-glucose-FDG-PET and compared between chronic BZD users and nonusers using multiple linear regressions adjusted for age, sex, education, APOE ε 4 copy number, cognitive and neuropsychiatric assessments, history of major depressive episodes and antidepressant use.

RESULTS

We found that the SUVR was significantly higher in chronic BZD users (n = 192) than in nonusers (n = 1,122) in the whole brain (beta = 0.03; p = 0.038) and in the right amygdala (beta = 0.32; p = 0.012). Trends were observed for the half-lives of BZDs (short- and long-acting BZDs) (p = 0.051) and Z-drug hypnotic treatments (p = 0.060) on the SUVR of the right amygdala. We found no significant association in the other ROIs.

CONCLUSION

Our study is the first to find a greater global metabolism in chronic BZD users and a specific greater metabolism in the right amygdala. Because the acute administration of BZDs tends to reduce brain metabolism, these findings may correspond to a compensatory mechanism while the brain adapts with global metabolism upregulation, with a specific focus on the right amygdala.

Viscous dynamics associated with hypoexcitation and structural disintegration in neurodegeneration via generative whole-brain modeling

INTRODUCTION

Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD) lack mechanistic biophysical modeling in diverse, underrepresented populations. Electroencephalography (EEG) is a high temporal resolution, cost-effective technique for studying dementia globally, but lacks mechanistic models and produces non-replicable results.

METHODS

We developed a generative whole-brain model that combines EEG source-level metaconnectivity, anatomical priors, and a perturbational approach. This model was applied to Global South participants (AD, bvFTD, and healthy controls).

RESULTS

Metaconnectivity outperformed pairwise connectivity and revealed more viscous dynamics in patients, with altered metaconnectivity patterns associated with multimodal disease presentation. The biophysical model showed that connectome disintegration and hypoexcitability triggered altered metaconnectivity dynamics and identified critical regions for brain stimulation. We replicated the main results in a second subset of participants for validation with unharmonized, heterogeneous recording settings.

DISCUSSION

The results provide a novel agenda for developing mechanistic model-inspired characterization and therapies in clinical, translational, and computational neuroscience settings.

Biophysical models applied to dementia patients reveal links between geographical origin, gender, disease duration, and loss of neural inhibition

BACKGROUND

The hypothesis of decreased neural inhibition in dementia has been sparsely studied in functional magnetic resonance imaging (fMRI) data across patients with different dementia subtypes, and the role of social and demographic heterogeneities on this hypothesis remains to be addressed.

METHODS

We inferred regional inhibition by fitting a biophysical whole-brain model (dynamic mean field model with realistic inter-areal connectivity) to fMRI data from 414 participants, including patients with Alzheimer's disease, behavioral variant frontotemporal dementia, and controls. We then investigated the effect of disease condition, and demographic and clinical variables on the local inhibitory feedback, a variable related to the maintenance of balanced neural excitation/inhibition.

RESULTS

Decreased local inhibitory feedback was inferred from the biophysical modeling results in dementia patients, specific to brain areas presenting neurodegeneration. This loss of local inhibition correlated positively with years with disease, and showed differences regarding the gender and geographical origin of the patients. The model correctly reproduced known disease-related changes in functional connectivity.

CONCLUSIONS

Results suggest a critical link between abnormal neural and circuit-level excitability levels, the loss of grey matter observed in dementia, and the reorganization of functional connectivity, while highlighting the sensitivity of the underlying biophysical mechanism to demographic and clinical heterogeneities in the patient population.

Greater accuracy of radiomics compared to deep learning to discriminate normal subjects from patients with dementia: a whole brain 18FDG PET analysis

METHODS

18F-FDG brain PET and clinical score were collected in 85 patients with dementia and 125 healthy controls (HC). Patients were assigned to various form of dementia on the basis of clinical evaluation, follow-up and voxels comparison with HC using a two-sample Student's t -test, to determine the regions of brain involved. Radiomic analysis was performed on the whole brain after normalization to an optimized template. After feature selection using the minimum redundancy maximum relevance method and Pearson's correlation coefficients, a Neural Network model was tested to find the accuracy to classify HC and demented patients. Twenty subjects not included in the training were used to test the models. The results were compared with those obtained by conventional CNN model.

RESULTS

Four radiomic features were selected. The validation and test accuracies were 100% for both models, but the probability scores were higher with radiomics, in particular for HC group ( P  = 0.0004).

CONCLUSION

Radiomic features extracted from standardized PET whole brain images seem to be more accurate than CNN to distinguish patients with and without dementia.

Mice and minipigs with compromised expression of the Alzheimer's disease gene SORL1 show cerebral metabolic disturbances on hyperpolarized [1-13C]pyruvate and sodium MRI

The sortilin-related receptor 1 (SORL1) gene, encoding the cellular endosomal sorting-related receptor with A-type repeats (SORLA), is now established as a causal gene for Alzheimer's disease. As the latest addition to the list of causal genes, the pathophysiological effects and biomarker potential of SORL1 variants remain relatively undiscovered. Metabolic dysfunction is, however, well described in patients with Alzheimer's disease and is used as an imaging biomarker in clinical diagnosis settings. To understand the metabolic consequences of loss-of-function SORL1 mutations, we applied two metabolic MRI technologies, sodium (23Na) MRI and MRI with hyperpolarized [1-13C]pyruvate, in minipigs and mice with compromised expression of SORL1. At the age analysed here, both animal models display no conventional imaging evidence of neurodegeneration but show biochemical signs of elevated amyloid production, thus representing the early preclinical disease. With hyperpolarized MRI, the exchange from [1-13C]pyruvate to [1-13C]lactate and 13C-bicarbonate was decreased by 32 and 23%, respectively, in the cerebrum of SORL1-haploinsufficient minipigs. A robust 11% decrease in the sodium content was observed with 23Na-MRI in the same minipigs. Comparably, the brain sodium concentration gradually decreased from control to SORL1 haploinsufficient (-11%) to SORL1 knockout mice (-23%), suggesting a gene dose dependence in the metabolic dysfunction. The present study highlights that metabolic MRI technologies are sensitive to the functional, metabolic consequences of Alzheimer's disease and Alzheimer's disease-linked genotypes. Further, the study suggests a potential avenue of research into the mechanisms of metabolic alterations by SORL1 mutations and their potential role in neurodegeneration.

Synthesizing images of tau pathology from cross-modal neuroimaging using deep learning

Given the prevalence of dementia and the development of pathology-specific disease-modifying therapies, high-value biomarker strategies to inform medical decision-making are critical. In vivo tau-PET is an ideal target as a biomarker for Alzheimer's disease diagnosis and treatment outcome measure. However, tau-PET is not currently widely accessible to patients compared to other neuroimaging methods. In this study, we present a convolutional neural network (CNN) model that imputes tau-PET images from more widely available cross-modality imaging inputs. Participants (n = 1192) with brain T1-weighted MRI (T1w), fluorodeoxyglucose (FDG)-PET, amyloid-PET and tau-PET were included. We found that a CNN model can impute tau-PET images with high accuracy, the highest being for the FDG-based model followed by amyloid-PET and T1w. In testing implications of artificial intelligence-imputed tau-PET, only the FDG-based model showed a significant improvement of performance in classifying tau positivity and diagnostic groups compared to the original input data, suggesting that application of the model could enhance the utility of the metabolic images. The interpretability experiment revealed that the FDG- and T1w-based models utilized the non-local input from physically remote regions of interest to estimate the tau-PET, but this was not the case for the Pittsburgh compound B-based model. This implies that the model can learn the distinct biological relationship between FDG-PET, T1w and tau-PET from the relationship between amyloid-PET and tau-PET. Our study suggests that extending neuroimaging's use with artificial intelligence to predict protein specific pathologies has great potential to inform emerging care models.

Practical Overview of 123I-Ioflupane Imaging in Parkinsonian Syndromes

Parkinsonian syndromes are a heterogeneous group of progressive neurodegenerative disorders involving the nigrostriatal dopaminergic pathway and are characterized by a wide spectrum of motor and nonmotor symptoms. These syndromes are quite common and can profoundly impact the lives of patients and their families. In addition to classic Parkinson disease, parkinsonian syndromes include multiple additional disorders known collectively as Parkinson-plus syndromes or atypical parkinsonism. These are characterized by the classic parkinsonian motor symptoms with additional distinguishing clinical features. Dopamine transporter SPECT has been developed as a diagnostic tool to assess the levels of dopamine transporters in the striatum. This imaging assessment, which uses iodine 123 (123I) ioflupane, can be useful to differentiate parkinsonian syndromes caused by nigrostriatal degeneration from other clinical mimics such as essential tremor or psychogenic tremor. Dopamine transporter imaging plays a crucial role in diagnosing parkinsonian syndromes, particularly in patients who do not clearly fulfill the clinical criteria for diagnosis. Diagnostic clarification can allow early treatment in appropriate patients and avoid misdiagnosis. At present, only the qualitative interpretation of dopamine transporter SPECT is approved by the U.S. Food and Drug Administration, but quantitative interpretation is often used to supplement qualitative interpretation. The authors provide an overview of patient preparation, common imaging findings, and potential pitfalls that radiologists and nuclear medicine physicians should know when performing and interpreting dopamine transporter examinations. Alternatives to 123I-ioflupane imaging for the evaluation of nigrostriatal degeneration are also briefly discussed. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material. See the invited commentary by Intenzo and Colarossi in this issue.

A ROI-based quantitative pipeline for 18F-FDG PET metabolism and pCASL perfusion joint analysis: Validation of the 18F-FDG PET line

In Mild Cognitive Impairment (MCI), the study of brain metabolism, provided by 18F-FluoroDeoxyGlucose Positron Emission Tomography (18F-FDG PET) can be integrated with brain perfusion through pseudo-Continuous Arterial Spin Labeling Magnetic Resonance sequences (MR pCASL). Cortical hypometabolism identification generally relies on wide control group datasets; pCASL control groups are instead not publicly available yet, due to lack of standardization in the acquisition parameters. This study presents a quantitative pipeline to be applied to PET and pCASL data to coherently analyze metabolism and perfusion inside 16 matching cortical regions of interest (ROIs) derived from the AAL3 atlas. The PET line is tuned on 36 MCI patients and 107 healthy control subjects, to agree in identifying hypometabolic regions with clinical reference methods (visual analysis supported by a vendor tool and Statistical Parametric Mapping, SPM, with two parametrizations here identified as SPM-A and SPM-B). The analysis was conducted for each ROI separately. The proposed PET analysis pipeline obtained accuracy 78 % and Cohen's к 60 % vs visual analysis, accuracy 79 % and Cohen's к 58 % vs SPM-A, accuracy 77 % and Cohen's к 54 % vs SPM-B. Cohen's к resulted not significantly different from SPM-A and SPM-B Cohen's к when assuming visual analysis as reference method (p-value 0.61 and 0.31 respectively). Considering SPM-A as reference method, Cohen's к is not significantly different from SPM-B Cohen's к as well (p-value = 1.00). The complete PET-pCASL pipeline was then preliminarily applied on 5 MCI patients and metabolism-perfusion regional correlations were assessed. The proposed approach can be considered as a promising tool for PET-pCASL joint analyses in MCI, even in the absence of a pCASL control group, to perform metabolism-perfusion regional correlation studies, and to assess and compare perfusion in hypometabolic or normo-metabolic areas.

PCA and logistic regression in 2-[18F]FDG PET neuroimaging as an interpretable and diagnostic tool for Alzheimer's disease

Objective.to develop an optimization and training pipeline for a classification model based on principal component analysis and logistic regression using neuroimages from PET with 2-[18F]fluoro-2-deoxy-D-glucose (FDG PET) for the diagnosis of Alzheimer's disease (AD).Approach.as training data, 200 FDG PET neuroimages were used, 100 from the group of patients with AD and 100 from the group of cognitively normal subjects (CN), downloaded from the repository of the Alzheimer's Disease Neuroimaging Initiative (ADNI). Regularization methods L1 and L2 were tested and their respective strength varied by the hyperparameter C. Once the best combination of hyperparameters was determined, it was used to train the final classification model, which was then applied to test data, consisting of 192 FDG PET neuroimages, 100 from subjects with no evidence of AD (nAD) and 92 from the AD group, obtained at the Centro de Diagnóstico por Imagem (CDI).Main results.the best combination of hyperparameters was L1 regularization andC≈ 0.316. The final results on test data were accuracy = 88.54%, recall = 90.22%, precision = 86.46% and AUC = 94.75%, indicating that there was a good generalization to neuroimages outside the training set. Adjusting each principal component by its respective weight, an interpretable image was obtained that represents the regions of greater or lesser probability for AD given high voxel intensities. The resulting image matches what is expected by the pathophysiology of AD.Significance.our classification model was trained on publicly available and robust data and tested, with good results, on clinical routine data. Our study shows that it serves as a powerful and interpretable tool capable of assisting in the diagnosis of AD in the possession of FDG PET neuroimages. The relationship between classification model output scores and AD progression can and should be explored in future studies.

Arterial spin labeling (ASL-MRI) versus fluorodeoxyglucose-PET (FDG-PET) in diagnosing dementia: a systematic review and meta-analysis

BACKGROUND

Dementia is generally caused by neurodegenerative diseases affecting the brain, which leads to a progressive neurocognitive decline characterized by inability to perform major higher functioning tasks. Fluorodeoxyglucose-positron emission tomography (FDG-PET) scan is one of the main imaging tests performed for diagnostic purposes. However, with FDG-PET being quite expensive and not widely available, an attempt to find an alternative is set. Arterial-spin-labelling magnetic resonance imaging (ASL-MRI) is an increasingly investigated substitute to FDG-PET for the diagnosis of dementia. Thereby, the main purpose of this systematic review and meta-analysis is to compare the diagnostic ability of FDG-PET and ASL-MRI in detecting dementia.

METHODS

PRISMA checklist for diagnostic test accuracy was employed in outlining this paper. A literature search was done using several search engines including PubMed, Core, and Cochrane. Two researchers (HH and SH) extracted the essential information from all included articles. Risk of bias was evaluated by the Quality Assessment of Diagnostic Accuracy Studies tool, version 2 (QUADAS-2). A qualitative analysis and summary of studies' results were provided. In addition, a meta-analysis was executed based on the studies which involved sensitivity and specificity measures of diagnostic accuracy.

RESULTS

Fourteen total studies were included in the given review. Qualitative analysis of the articles showed that nine studies demonstrated an overlap between metabolic and perfused brain maps as derived by FDG-PET and ASL-MRI respectively, while the remaining five studies registered significant differences across both modalities, with superiority to FDG-PET. As for the meta-analysis implemented, summary ROC-curve analysis revealed that FDG-PET performed better than ASL-MRI, with pooled sensitivity being significantly higher for FDG-PET.

CONCLUSIONS

Comparing the diagnostic value of FDG-PET and ASL-MRI, the results of this systematic review and meta-analysis indicate that FDG-PET still has an advantage over ASL-MRI. Such implication could be related to the technical differences relating to both modalities, with ASL-MRI having lower temporal resolution. It's worth mentioning that specificity was rather quite similar among both modalities and some studies found an overridden metabolic and perfused images. These findings call for future research to focus their scope of investigation while exploring the diagnostic value of ASL-MRI.

Major depression associated with a levonorgestrel-releasing intrauterine system mimicking frontotemporal dementia: a case report

This case illustrates the adverse cognitive and affective effects associated with the use of an intrauterine hormonal contraceptive, which could be confused with symptoms of early onset dementia. We present a case of a 42-year-old woman diagnosed with seronegative spondyloarthropathy who subsequently developed anxiety and depressive symptoms after the implantation of a Levonorgestrel-Releasing Intrauterine System (LNG-IUS). Three years later, she began to experience memory and attentional failures, refractory pain, and severe depression. The progression of psychiatric symptoms led to a diagnosis of bipolar affective disorder and treatment with antidepressants and anxiolytics. Due to cognitive and psychiatric symptoms, autoimmune encephalitis was considered, but no improvement was shown with treatment. Early onset dementia was suspected, and a brain PET scan revealed frontal lobe hypometabolism. An adverse effect of LNG-IUS was considered; after its removal, mood and cognitive function improvements were observed. This case report emphasizes the importance of considering organic causes of unexplained psychiatric manifestations and highlights the potential impact of hormonal interventions on mental health.

New Advances in the Exploration of Esterases with PET and Fluorescent Probes

Esterases are hydrolases that catalyze the hydrolysis of esters into the corresponding acids and alcohols. The development of fluorescent probes for detecting esterases is of great importance due to their wide spectrum of biological and industrial applications. These probes can provide a rapid and sensitive method for detecting the presence and activity of esterases in various samples, including biological fluids, food products, and environmental samples. Fluorescent probes can also be used for monitoring the effects of drugs and environmental toxins on esterase activity, as well as to study the functions and mechanisms of these enzymes in several biological systems. Additionally, fluorescent probes can be designed to selectively target specific types of esterases, such as those found in pathogenic bacteria or cancer cells. In this review, we summarize the recent fluorescent probes described for the visualization of cell viability and some applications for in vivo imaging. On the other hand, positron emission tomography (PET) is a nuclear-based molecular imaging modality of great value for studying the activity of enzymes in vivo. We provide some examples of PET probes for imaging acetylcholinesterases and butyrylcholinesterases in the brain, which are valuable tools for diagnosing dementia and monitoring the effects of anticholinergic drugs on the central nervous system.

Effect of Obesity and Osteocalcin on Brain Glucose Metabolism in Healthy Participants

We evaluated the effects of obesity and osteocalcin on glucose metabolism in the brain. A total of 179 healthy men were enrolled in this study. After preprocessing positron emission tomography images, including by performing coregistration, spatial normalization, and smoothing, regression analysis was conducted to identify the correlation between body mass index, osteocalcin, and brain glucose metabolism. Body mass index was positively correlated with brain glucose metabolism in the anterior lobe of the right cerebellum, the anterior and posterior lobes of the left cerebellum, the right middle frontal gyrus (Brodmann area 9), the right cingulate gyrus (Brodmann area 32), the right anterior cingulate (Brodmann area 32), the left middle frontal gyrus (Brodmann area 10), and the subgyral area of the left frontal lobe. Osteocalcin was negatively correlated with glucose metabolism in the anterior lobe of the left cerebellum. Body mass index was positively correlated with brain glucose metabolism in the prefrontal cortex and cerebellum. Osteocalcin levels were negatively correlated with brain glucose metabolism in the left cerebellum.

Model-based whole-brain perturbational landscape of neurodegenerative diseases

The treatment of neurodegenerative diseases is hindered by lack of interventions capable of steering multimodal whole-brain dynamics towards patterns indicative of preserved brain health. To address this problem, we combined deep learning with a model capable of reproducing whole-brain functional connectivity in patients diagnosed with Alzheimer's disease (AD) and behavioral variant frontotemporal dementia (bvFTD). These models included disease-specific atrophy maps as priors to modulate local parameters, revealing increased stability of hippocampal and insular dynamics as signatures of brain atrophy in AD and bvFTD, respectively. Using variational autoencoders, we visualized different pathologies and their severity as the evolution of trajectories in a low-dimensional latent space. Finally, we perturbed the model to reveal key AD- and bvFTD-specific regions to induce transitions from pathological to healthy brain states. Overall, we obtained novel insights on disease progression and control by means of external stimulation, while identifying dynamical mechanisms that underlie functional alterations in neurodegeneration.

Broad learning for early diagnosis of Alzheimer's disease using FDG-PET of the brain

Alzheimer's disease (AD) is a progressive neurodegenerative disease, and the development of AD is irreversible. However, preventive measures in the presymptomatic stage of AD can effectively slow down deterioration. Fluorodeoxyglucose positron emission tomography (FDG-PET) can detect the metabolism of glucose in patients' brains, which can help to identify changes related to AD before brain damage occurs. Machine learning is useful for early diagnosis of patients with AD using FDG-PET, but it requires a sufficiently large dataset, and it is easy for overfitting to occur in small datasets. Previous studies using machine learning for early diagnosis with FDG-PET have either involved the extraction of elaborately handcrafted features or validation on a small dataset, and few studies have explored the refined classification of early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI). This article presents a broad network-based model for early diagnosis of AD (BLADNet) through PET imaging of the brain; this method employs a novel broad neural network to enhance the features of FDG-PET extracted via 2D CNN. BLADNet can search for information over a broad space through the addition of new BLS blocks without retraining of the whole network, thus improving the accuracy of AD classification. Experiments conducted on a dataset containing 2,298 FDG-PET images of 1,045 subjects from the ADNI database demonstrate that our methods are superior to those used in previous studies on early diagnosis of AD with FDG-PET. In particular, our methods achieved state-of-the-art results in EMCI and LMCI classification with FDG-PET.

The characteristics of glucose metabolism and functional connectivity in posterior default network during nondemented aging: relationship with executive function performance

BACKGROUND

Understanding the characteristics of intrinsic connectivity networks (ICNs) in terms of both glucose metabolism and functional connectivity (FC) is important for revealing cognitive aging and neurodegeneration, but the relationships between these two aspects during aging has not been well established in older adults.

OBJECTIVE

This study is to assess the relationship between age-related glucose metabolism and FC in key ICNs, and their direct or indirect effects on cognitive deficits in older adults.

METHODS

We estimated the individual-level standard uptake value ratio (SUVr) and FC of eleven ICNs in 59 cognitively unimpaired older adults, then analyzed the associations of SUVr and FC of each ICN and their relationships with cognitive performance.

RESULTS

The results showed both the SUVr and FC in the posterior default mode network (pDMN) had a significant decline with age, and the association between them was also significant. Moreover, both decline of metabolism and FC in the pDMN were significantly correlated with executive function decline. Finally, mediation analysis revealed the glucose metabolism mediated the FC decline with age and FC mediated the executive function deficits.

CONCLUSIONS

Our findings indicated that covariance between glucose metabolism and FC in the pDMN is one of the main routes that contributes to age-related executive function decline.

An Explainable Convolutional Neural Network for the Early Diagnosis of Alzheimer's Disease from 18F-FDG PET

Convolutional Neural Networks (CNN) which support the diagnosis of Alzheimer's Disease using 18F-FDG PET images are obtaining promising results; however, one of the main challenges in this domain is the fact that these models work as black-box systems. We developed a CNN that performs a multiclass classification task of volumetric 18F-FDG PET images, and we experimented two different post hoc explanation techniques developed in the field of Explainable Artificial Intelligence: Saliency Map (SM) and Layerwise Relevance Propagation (LRP). Finally, we quantitatively analyze the explanations returned and inspect their relationship with the PET signal. We collected 2552 scans from the Alzheimer's Disease Neuroimaging Initiative labeled as Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and Alzheimer's Disease (AD) and we developed and tested a 3D CNN that classifies the 3D PET scans into its final clinical diagnosis. The model developed achieves, to the best of our knowledge, performances comparable with the relevant literature on the test set, with an average Area Under the Curve (AUC) for prediction of CN, MCI, and AD 0.81, 0.63, and 0.77 respectively. We registered the heatmaps with the Talairach Atlas to perform a regional quantitative analysis of the relationship between heatmaps and PET signals. With the quantitative analysis of the post hoc explanation techniques, we observed that LRP maps were more effective in mapping the importance metrics in the anatomic atlas. No clear relationship was found between the heatmap and the PET signal.

Differential Effects of Tau Stage, Lewy Body Pathology, and Substantia Nigra Degeneration on 18F-FDG PET Patterns in Clinical Alzheimer Disease

Comorbid Lewy body (LB) pathology is common in Alzheimer disease (AD). The effect of LB copathology on ¹⁸F-FDG PET patterns in AD is yet to be studied. We analyzed associations of neuropathologically assessed tau pathology, LB pathology, and substantia nigra neuronal loss (SNnl) with antemortem ¹⁸F-FDG PET hypometabolism in patients with a clinical AD presentation. Methods: Twenty-one patients with autopsy-confirmed AD without LB neuropathologic changes (LBNC) (pure-AD), 24 with AD and LBNC copathology (AD-LB), and 7 with LBNC without fulfilling neuropathologic criteria for AD (pure-LB) were studied. Pathologic groups were compared regarding regional and voxelwise ¹⁸F-FDG PET patterns, the cingulate island sign ratio (CISr), and neuropathologic ratings of SNnl. Additional analyses assessed continuous associations of Braak tangle stage and SNnl with ¹⁸F-FDG PET patterns. Results: Pure-AD and AD-LB showed highly similar patterns of AD-typical temporoparietal hypometabolism and did not differ in CISr, regional ¹⁸F-FDG SUVR, or SNnl. By contrast, pure-LB showed the expected pattern of pronounced posterior-occipital hypometabolism typical for dementia with LB (DLB), and both CISr and SNnl were significantly higher compared with the AD groups. In continuous analyses, Braak tangle stage correlated significantly with more AD-like, and SNnl with more DLB-like, ¹⁸F-FDG PET patterns. Conclusion: In autopsy-confirmed AD dementia patients, comorbid LB pathology did not have a notable effect on the regional ¹⁸F-FDG PET pattern. A more DLB-like ¹⁸F-FDG PET pattern was observed in relation to SNnl, but advanced SNnl was mostly limited to relatively pure LB cases. AD pathology may have a dominant effect over LB pathology in determining the regional neurodegeneration phenotype.

Fluid dynamics in aging-related dementias

Recent human and animal model experimental studies revealed novel pathways for fluid movement, immune cell trafficking and metabolic waste clearance in CNS. These studies raise the intriguing possibility that the newly discovered pathways, including the glymphatic system, lymphatic meningeal vessels and skull-brain communication channels, are impaired in aging and neurovascular and neurodegenerative diseases associated with dementia, including Alzheimer's disease (AD) and AD-related dementia. We provide an overview of the glymphatic and dural meningeal lymphatic systems, review current methods and approaches used to study glymphatic flow in humans and animals, and discuss current evidence and controversies related to its role in CNS flow homeostasis under physiological and pathophysiological conditions. Non-invasive imaging approaches are needed to fully understand the mechanisms and pathways driving fluid movement in CNS and their roles across lifespan including healthy aging and aging-related dementia.

Brain PET Imaging: Frontotemporal Dementia

Brain PET adds value in diagnosing neurodegenerative disorders, especially frontotemporal dementia (FTD) due to its syndromic presentation that overlaps with a variety of other neurodegenerative and psychiatric disorders. 18F-FDG-PET has improved sensitivity and specificity compared with structural MR imaging, with optimal diagnostic results achieved when both techniques are utilized. PET demonstrates superior sensitivity compared with SPECT for FTD diagnosis that is primarily a supplement to other imaging and clinical evaluations. Tau-PET and amyloid-PET primary use in FTD diagnosis is differentiation from Alzheimer disease, although these methods are limited mainly to research settings.

Cerebral vasomotor reactivity across the continuum of subjective cognitive impairment, amnestic mild cognitive impairment and probable Alzheimer's dementia: A transcranial Doppler and PET/MRI study

Cerebrovascular dysfunction has been suggested as a physiomarker of Alzheimer's disease (AD)-associated neuronal degeneration, but the underlying mechanisms are still debated. Herein cerebral vasomotor reactivity (VMR, breath-hold index: BHI), metabolic activity (lobar SUVs, FDG PET MRI), amyloid load (Centiloid score, Flutemetamol PET MRI), hemispheric cortical thickness, white matter lesion load and cerebral blood flow (ASL) were studied in 43 consecutive subjects (mean age: 64 years, female 13), diagnosed with subjective cognitive impairment (SCI, n = 10), amnestic mild cognitive impairment (aMCI, n = 15), and probable Alzheimer's dementia (AD, n = 18). BHI was significantly reduced in AD and aMCI patients compared to SCI subjects. A highly significant inverse correlation was found between BHI and the centiloid score (r = -0.648, p < 0.001). There was moderate positive correlation between BHI and frontal, temporal and parietal FDG SUV and ASL values, and a borderline negative correlation with age and white matter lesion volume. The link between amyloid burden and VMR was independent and strong in linear regression models where all these parameters were included (β from -0.580 to -0.476, p < 0.001). In conclusion, our study confirms the negative association of cerebral amyloid accumulation and vasomotor reactivity in Alzheimer's disease with the most direct data to date in humans.

Brain PET Imaging: Approach to Cognitive Impairment and Dementia

Alzheimer disease (AD) is the most common cause of dementia, accounting for 50% to 60% of cases and affecting nearly 6 million people in the United States. Definitive diagnosis requires either antemortem brain biopsy or postmortem autopsy. However, clinical neuroimaging has been playing a greater role in the diagnosis and management of AD, and several PET tracers approach the sensitivity of tissue diagnosis in identifying AD pathologic condition. This review will focus on the utility of PET imaging in the setting of cognitive impairment, with an emphasis on its role in the diagnosis of AD.

Hybrid PET/MRI with Flutemetamol and FDG in Alzheimer's Disease Clinical Continuum

AIMS

We aimed to investigate the interaction between β -amyloid (Aβ) accumulation and cerebral glucose metabolism, cerebral perfusion, and cerebral structural changes in the Alzheimer's disease (AD) clinical continuum.

BACKGROUND

Utility of positron emission tomography (PET) / magnetic resonance imaging (MRI) hybrid imaging for diagnostic categorization of the AD clinical continuum including subjective cognitive decline (SCD), amnestic mild cognitive impairment (aMCI) and Alzheimer's disease dementia (ADD) has not been fully crystallized.

OBJECTIVE

To evaluate the interaction between Aβ accumulation and cerebral glucose metabolism, cerebral perfusion, and cerebral structural changes such as cortex thickness or cerebral white matter disease burden and to detect the discriminative yields of these imaging modalities in the AD clinical continuum.

METHODS

Fifty patients (20 women and 30 men; median age: 64 years) with clinical SCD (n=11), aMCI (n=17) and ADD (n=22) underwent PET/MRI with [18F]-fluoro-D-glucose (FDG) and [18F]- Flutemetamol in addition to cerebral blood flow (CBF) and quantitative structural imaging along with detailed cognitive assessment.

RESULTS

High Aβ deposition (increased temporal [18F]-Flutemetamol standardized uptake value ratio (SUVr) and centiloid score), low glucose metabolism (decreased temporal lobe and posterior cingulate [18F]-FDG SUVr), low parietal CBF and right hemispheric cortical thickness were independent predictors of low cognitive test performance.

CONCLUSION

Integrated use of structural, metabolic, molecular (Aβ) and perfusion (CBF) parameters contribute to the discrimination of SCD, aMCI, and ADD.

Functional Correlates of Striatal Dopamine Transporter Cerebrospinal Fluid Levels in Alzheimer's Disease: A Preliminary 18F-FDG PET/CT Study

The aim of our study was to investigate regional glucose metabolism with 18F-FDG positron emission tomography/computed tomography in a population of patients with Alzheimer's disease (AD) in relation to cerebrospinal (CSF) levels of striatal dopamine transporter (DAT). All patients underwent lumbar puncture and received a biomarker-based diagnosis of AD. Differences in regional brain glucose metabolism were assessed by Statistical Parametric Mapping version 12 with the use of age, gender, and MMSE as covariates in the analysis. A positive correlation between CSF DAT levels and glucose metabolism at the level of two brain areas involved in the pathophysiological process of Alzheimer's disease, the substantia nigra and the posterior cingulate gyrus, has been highlighted. Results indicate that patients with higher CSF DAT levels have a better metabolic pattern in two key zones, suggesting less advanced disease status in patients with more conserved dopaminergic systems.

Differences in Striatal Metabolism in [18F]FDG PET in Parkinson's Disease and Atypical Parkinsonism

Neurodegenerative parkinsonisms affect mainly cognitive and motor functions and are syndromes of overlapping symptoms and clinical manifestations such as tremor, rigidness, and bradykinesia. These include idiopathic Parkinson's disease (PD) and the atypical parkinsonisms, namely progressive supranuclear palsy (PSP), corticobasal degeneration (CBD), multiple system atrophy (MSA) and dementia with Lewy body (DLB). Differences in the striatal metabolism among these syndromes are evaluated using [18F]FDG PET, caused by alterations to the dopaminergic activity and neuronal loss. A study cohort of three patients with PD, 29 with atypical parkinsonism (10 PSP, 6 CBD, 2 MSA, 7 DLB, and 4 non-classifiable), and a control group of 25 patients with normal striatal metabolism is available. Standardized uptake value ratios (SUVR) are extracted from the striatum, and the caudate and the putamen separately. SUVRs are compared among the study groups. In addition, hemispherical and caudate-putamen differences are evaluated in atypical parkinsonisms. Striatal hypermetabolism is detected in patients with PD, while atypical parkinsonisms show hypometabolism, compared to the control group. Hemispherical differences are observed in CBD, MSA and DLB, with the latter also showing statistically significant caudate-putamen asymmetry (p = 0.018). These results indicate disease-specific metabolic uptake patterns in the striatum that can support the differential diagnosis.

Adopting transfer learning for neuroimaging: a comparative analysis with a custom 3D convolution neural network model

BACKGROUND

In recent years, neuroimaging with deep learning (DL) algorithms have made remarkable advances in the diagnosis of neurodegenerative disorders. However, applying DL in different medical domains is usually challenged by lack of labeled data. To address this challenge, transfer learning (TL) has been applied to use state-of-the-art convolution neural networks pre-trained on natural images. Yet, there are differences in characteristics between medical and natural images, also image classification and targeted medical diagnosis tasks. The purpose of this study is to investigate the performance of specialized and TL in the classification of neurodegenerative disorders using 3D volumes of 18F-FDG-PET brain scans.

RESULTS

Results show that TL models are suboptimal for classification of neurodegenerative disorders, especially when the objective is to separate more than two disorders. Additionally, specialized CNN model provides better interpretations of predicted diagnosis.

CONCLUSIONS

TL can indeed lead to superior performance on binary classification in timely and data efficient manner, yet for detecting more than a single disorder, TL models do not perform well. Additionally, custom 3D model performs comparably to TL models for binary classification, and interestingly perform better for diagnosis of multiple disorders. The results confirm the superiority of the custom 3D-CNN in providing better explainable model compared to TL adopted ones.

A zero-dose synthetic baseline for the personalized analysis of 2-Deoxy-2-[18F]fluoroglucose: Application in Alzheimer’s disease

Purpose

Brain 2-Deoxy-2-[18F]fluoroglucose ([18F]FDG-PET) is widely used in the diagnostic workup of Alzheimer’s disease (AD). Current tools for uptake analysis rely on non-personalized templates, which poses a challenge as decreased glucose uptake could reflect neuronal dysfunction, or heterogeneous brain morphology associated with normal aging. Overcoming this, we propose a deep learning method for synthesizing a personalized [18F]FDG-PET baseline from the patient’s own MRI, and showcase its applicability in detecting AD pathology.

Methods

We included [18F]FDG-PET/MRI data from 123 patients of a local cohort and 600 patients from ADNI. A supervised, adversarial model with two connected Generative Adversarial Networks (GANs) was trained on cognitive normal (CN) patients with transfer-learning to generate full synthetic baseline volumes (sbPET) (192 × 192 × 192) which reflect healthy uptake conditioned on brain anatomy. Synthetic accuracy was measured by absolute relative %-difference (Abs%), relative %-difference (RD%), and peak signal-to-noise ratio (PSNR). Lastly, we deployed the sbPET images in a fully personalized method for localizing metabolic abnormalities.

Results

The model achieved a spatially uniform Abs% of 9.4%, RD% of 0.5%, and a PSNR of 26.3 for CN subjects. The sbPET images conformed to the anatomical information dictated by the MRI and proved robust in presence of atrophy. The personalized abnormality method correctly mapped the pathology of AD subjects while showing little to no anomalies for CN subjects.

Conclusion

This work demonstrated the feasibility of synthesizing fully personalized, healthy-appearing [18F]FDG-PET images. Using these, we showcased a promising application in diagnosing AD, and theorized the potential value of sbPET images in other neuroimaging routines.

Automated differential diagnosis of dementia syndromes using FDG PET and machine learning

BACKGROUND

Metabolic brain imaging with 2-[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography (FDG PET) is a supportive diagnostic and differential diagnostic tool for neurodegenerative dementias. In the clinic, scans are usually visually interpreted. However, computer-aided approaches can improve diagnostic accuracy. We aimed to build two machine learning classifiers, based on two sets of FDG PET-derived features, for differential diagnosis of common dementia syndromes.

METHODS

We analyzed FDG PET scans from three dementia cohorts [63 dementia due to Alzheimer's disease (AD), 79 dementia with Lewy bodies (DLB) and 23 frontotemporal dementia (FTD)], and 41 normal controls (NCs). Patients' clinical diagnosis at follow-up (25 ± 20 months after scanning) or cerebrospinal fluid biomarkers for Alzheimer's disease was considered a gold standard. FDG PET scans were first visually evaluated. Scans were pre-processed, and two sets of features extracted: (1) the expressions of previously identified metabolic brain patterns, and (2) the mean uptake value in 95 regions of interest (ROIs). Two multi-class support vector machine (SVM) classifiers were tested and their diagnostic performance assessed and compared to visual reading. Class-specific regional feature importance was assessed with Shapley Additive Explanations.

RESULTS

Pattern- and ROI-based classifier achieved higher overall accuracy than expert readers (78% and 80% respectively, vs. 71%). Both SVM classifiers performed similarly to one another and to expert readers in AD (F1 = 0.74, 0.78, and 0.78) and DLB (F1 = 0.81, 0.81, and 0.78). SVM classifiers outperformed expert readers in FTD (F1 = 0.87, 0.83, and 0.63), but not in NC (F1 = 0.71, 0.75, and 0.92). Visualization of the SVM model showed bilateral temporal cortices and cerebellum to be the most important features for AD; occipital cortices, hippocampi and parahippocampi, amygdala, and middle temporal lobes for DLB; bilateral frontal cortices, middle and anterior cingulum for FTD; and bilateral angular gyri, pons, and vermis for NC.

CONCLUSION

Multi-class SVM classifiers based on the expression of characteristic metabolic brain patterns or ROI glucose uptake, performed better than experts in the differential diagnosis of common dementias using FDG PET scans. Experts performed better in the recognition of normal scans and a combined approach may yield optimal results in the clinical setting.

Neuroimaging analyses from a randomized, controlled study to evaluate plasma exchange with albumin replacement in mild-to-moderate Alzheimer's disease: additional results from the AMBAR study

PURPOSE

This study was designed to detect structural and functional brain changes in Alzheimer's disease (AD) patients treated with therapeutic plasma exchange (PE) with albumin replacement, as part of the recent AMBAR phase 2b/3 clinical trial.

METHODS

Mild-to-moderate AD patients were randomized into four arms: three arms receiving PE with albumin (one with low-dose albumin, and two with low/high doses of albumin alternated with IVIG), and a placebo (sham PE) arm. All arms underwent 6 weeks of weekly conventional PE followed by 12 months of monthly low-volume PE. Magnetic resonance imaging (MRI) volumetric analyses and regional and statistical parametric mapping (SPM) analysis on 18F-fluorodeoxyglucose positron emission tomography (18FDG-PET) were performed.

RESULTS

MRI analyses (n = 198 patients) of selected subcortical structures showed fewer volume changes from baseline to final visit in the high albumin + IVIG treatment group (p < 0.05 in 3 structures vs. 4 to 9 in other groups). The high albumin + IVIG group showed no statistically significant reduction of right hippocampus. SPM 18FDG-PET analyses (n = 213 patients) showed a worsening of metabolic activity in the specific areas affected in AD (posterior cingulate, precuneus, and parieto-temporal regions). The high-albumin + IVIG treatment group showed the greatest metabolic stability over the course of the study, i.e., the smallest percent decline in metabolism (MaskAD), and least progression of defect compared to placebo.

CONCLUSIONS

PE with albumin replacement was associated with fewer deleterious changes in subcortical structures and less metabolic decline compared to the typical of the progression of AD. This effect was more marked in the group treated with high albumin + IVIG.

TRIAL REGISTRATION

(AMBAR trial registration: EudraCT#: 2011-001,598-25; ClinicalTrials.gov ID: NCT01561053).

Impact of normative brain volume reports on the diagnosis of neurodegenerative dementia disorders in neuroradiology: A real-world, clinical practice study

Background: Normative brain volume reports (NBVR) are becoming more available in the work-up of patients with suspected dementia disorders, potentially leveraging the value of structural MRI in clinical settings. The present study aims to investigate the impact of NBVRs on the diagnosis of neurodegenerative dementia disorders in real-world clinical practice.

Methods: We retrospectively analyzed data of 112 memory clinic patients, who were consecutively referred for MRI and 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) during a 12-month period. Structural MRI was assessed by two residents with 2 and 3 years of neuroimaging experience. Statements and diagnostic confidence regarding the presence of a neurodegenerative disorder in general (first level) and Alzheimer’s disease (AD) pattern in particular (second level) were recorded without and with NBVR information. FDG-PET served as the reference standard.

Results: Overall, despite a trend towards increased accuracy, the impact of NBVRs on diagnostic accuracy was low and non-significant. We found a significant drop of sensitivity (0.75–0.58; p < 0.001) and increase of specificity (0.62–0.85; p < 0.001) for rater 1 at identifying patients with neurodegenerative dementia disorders. Diagnostic confidence increased for rater 2 (p < 0.001).

Conclusions: Overall, NBVRs had a limited impact on diagnostic accuracy in real-world clinical practice. Potentially, NBVR might increase diagnostic specificity and confidence of neuroradiology residents. To this end, a well-defined framework for integration of NBVR in the diagnostic process and improved algorithms of NBVR generation are essential.

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

Multimodality Imaging in Primary Progressive Aphasia

Primary progressive aphasia is a clinically and neuropathologically heterogeneous group of progressive neurodegenerative disorders, characterized by language-predominant impairment and commonly associated with atrophy of the dominant language hemisphere. While this clinical entity has been recognized dating back to the 19th century, important advances have been made in defining our current understanding of primary progressive aphasia, with 3 recognized subtypes to date: logopenic variant, semantic variant, and nonfluent/agrammatic variant. Given the ongoing progress in our understanding of the neurobiology and genomics of these rare neurodegenerative conditions, accurate imaging diagnoses are of the utmost importance and carry implications for future therapeutic triaging. This review covers the diverse spectrum of primary progressive aphasia and its multimodal imaging features, including structural, functional, and molecular neuroimaging findings; it also highlights currently recognized diagnostic criteria, clinical presentations, histopathologic biomarkers, and treatment options of these 3 primary progressive aphasia subtypes.

PET Imaging of Dementia: Update 2022

ABSTRACT

PET imaging plays an essential role in achieving earlier and more specific diagnoses of dementia syndromes, important for clinical prognostication and optimal medical management. This has become especially vital with the recent development of pathology-specific disease-modifying therapy for Alzheimer disease, which will continue to evolve and require methods to select appropriate treatment candidates. Techniques that began as research tools such as amyloid and tau PET have now entered clinical use, making nuclear medicine physicians and radiologists essential members of the care team. This review discusses recent changes in the understanding of dementia and examines the roles of nuclear medicine imaging in clinical practice. Within this framework, multiple cases will be shown to illustrate a systematic approach of FDG PET interpretation and integration of PET imaging of specific molecular pathology including dopamine transporters, amyloid, and tau. The approach presented here incorporates contemporary understanding of both common and uncommon dementia syndromes, intended as an updated practical guide to assist with the sophisticated interpretation of nuclear medicine examinations in the context of this rapidly and continually developing area of imaging.

Convolution Neural Networks for the Automatic Segmentation of 18F-FDG PET Brain as an Aid to Alzheimer’s Disease Diagnosis

Our work aims to exploit deep learning (DL) models to automatically segment diagnostic regions involved in Alzheimer’s disease (AD) in 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) volumetric scans in order to provide a more objective diagnosis of this disease and to reduce the variability induced by manual segmentation. The dataset used in this study consists of 102 volumes (40 controls, 39 with established Alzheimer’s disease (AD), and 23 with established mild cognitive impairment (MCI)). The ground truth was generated by an expert user who identified six regions in original scans, including temporal lobes, parietal lobes, and frontal lobes. The implemented architectures are the U-Net3D and V-Net networks, which were appropriately adapted to our data to optimize performance. All trained segmentation networks were tested on 22 subjects using the Dice similarity coefficient (DSC) and other similarity indices, namely the overlapping area coefficient (AOC) and the extra area coefficient (EAC), to evaluate automatic segmentation. The results of each labeled brain region demonstrate an improvement of 50%, with DSC from about 0.50 for V-Net-based networks to about 0.77 for U-Net3D-based networks. The best performance was achieved by using U-Net3D, with DSC on average equal to 0.76 for frontal lobes, 0.75 for parietal lobes, and 0.76 for temporal lobes. U-Net3D is very promising and is able to segment each region and each class of subjects without being influenced by the presence of hypometabolic regions.

Incremental diagnostic value of 18F-Fluetemetamol PET in differential diagnoses of Alzheimer's Disease-related neurodegenerative diseases from an unselected memory clinic cohort

To evaluate the incremental diagnostic value of 18F-Flutemetamol PET following MRI measurements on an unselected prospective cohort collected from a memory clinic. A total of 84 participants was included in this study. A stepwise study design was performed including initial analysis (based on clinical assessments), interim analysis (revision of initial analysis post-MRI) and final analysis (revision of interim analysis post-18F-Flutemetamol PET). At each time of evaluation, every participant was categorized into SCD, MCI or dementia syndromal group and further into AD-related, non-AD related or non-specific type etiological subgroup. Post 18F-Flutemetamol PET, the significant changes were seen in the syndromal MCI group (57%, p < 0.001) involving the following etiological subgroups: AD-related MCI (57%, p < 0.01) and non-specific MCI (100%, p < 0.0001); and syndromal dementia group (61%, p < 0.0001) consisting of non-specific dementia subgroup (100%, p < 0.0001). In the binary regression model, amyloid status significantly influenced the diagnostic results of interim analysis (p < 0.01). 18F-Flutemetamol PET can have incremental value following MRI measurements, particularly reflected in the change of diagnosis of individuals with unclear etiology and AD-related-suspected patients due to the role in complementing AD-related pathological information.

Metabolic brain pattern in dementia with Lewy bodies: Relationship to Alzheimer's disease topography

PURPOSE

Dementia with Lewy bodies (DLB) is the second most common neurodegenerative dementia, that shares clinical and metabolic similarities with both Alzheimer's and Parkinson's disease. In this study we aimed to identify a DLB-related pattern (DLBRP), study its relationship with other metabolic brain patterns and explore its diagnostic and prognostic value.

METHODS

A cohort of 79 participants with DLB, 63 with dementia due to Alzheimer's disease (AD) and 41 normal controls (NCs) and their 2-[¹⁸F]FDG PET scans were analysed for identification and validation of DLBRP. Voxel-wise correlation and multiple linear regression were used to study the relation between DLBRP and Alzheimer's disease-related pattern (ADRP), Parkinson's disease-related pattern (PDRP) and PD-related cognitive pattern (PDCP). Diagnostic and prognostic value of DLBRP and of modified DLBRP after accounting for ADRP overlap (DLBRP ⊥ ADRP), were explored.

RESULTS

The newly identified DLBRP shared topographic similarities with ADRP (R² = 24%) and PDRP (R² = 37%), but not with PDCP. We could accurately discriminate between DLB and NC (AUC = 0.99) based on DLBRP expression, and between DLB and AD (AUC = 0.87) based on DLBRP ⊥ ADRP expression. DLBRP expression correlated with cognitive impairment, but the correlation was lost after accounting for ADRP overlap. DLBRP and DLBRP ⊥ ADRP correlated with patients' survival time.

CONCLUSION

DLBRP has proven to be a specific metabolic brain biomarker of DLB, sharing similarities with ADRP and PDRP, but not PDCP. We observed a similar metabolic mechanism underlying cognitive impairment in DLB and AD. DLB-specific metabolic changes were more detrimental for overall survival.

The Value of Neuroimaging in Dementia Diagnosis

PURPOSE OF REVIEW

This article discusses neuroimaging in dementia diagnosis, with a focus on new applications of MRI and positron emission tomography (PET).

RECENT FINDINGS

Although the historical use of MRI in dementia diagnosis has been supportive to exclude structural etiologies, recent innovations allow for quantification of atrophy patterns that improve sensitivity for supporting the diagnosis of dementia causes. Neuronuclear approaches allow for localization of specific amyloid and tau neuropathology on PET and are available for clinical use, in addition to dopamine transporter scans in dementia with Lewy bodies and metabolic studies with fludeoxyglucose PET (FDG-PET).

SUMMARY

Using computerized software programs for MRI analysis and cross-sectional and longitudinal evaluations of hippocampal, ventricular, and lobar volumes improves sensitivity in support of the diagnosis of Alzheimer disease and frontotemporal dementia. MRI protocol requirements for such quantification are three-dimensional T1-weighted volumetric imaging protocols, which may need to be specifically requested. Fluid-attenuated inversion recovery (FLAIR) and 3.0T susceptibility-weighted imaging (SWI) sequences are useful for the detection of white matter hyperintensities as well as microhemorrhages in vascular dementia and cerebral amyloid angiopathy. PET studies for amyloid and/or tau pathology can add additional specificity to the diagnosis but currently remain largely inaccessible outside of research settings because of prohibitive cost constraints in most of the world. Dopamine transporter PET scans can help identify Lewy body dementia and are thus of potential clinical value.

Deep learning-based brain age prediction in normal aging and dementia

Brain aging is accompanied by patterns of functional and structural change. Alzheimer's disease (AD), a representative neurodegenerative disease, has been linked to accelerated brain aging. Here, we developed a deep learning-based brain age prediction model using a large collection of fluorodeoxyglucose positron emission tomography and structural magnetic resonance imaging and tested how the brain age gap relates to degenerative syndromes including mild cognitive impairment, AD, frontotemporal dementia and Lewy body dementia. Occlusion analysis, performed to facilitate the interpretation of the model, revealed that the model learns an age- and modality-specific pattern of brain aging. The elevated brain age gap was highly correlated with cognitive impairment and the AD biomarker. The higher gap also showed a longitudinal predictive nature across clinical categories, including cognitively unimpaired individuals who converted to a clinical stage. However, regions generating brain age gaps were different for each diagnostic group of which the AD continuum showed similar patterns to normal aging.

Statistical Parametric Mapping in Amyloid Positron Emission Tomography

Alzheimer's disease (AD), the most common cause of dementia, has limited treatment options. Emerging disease modifying therapies are targeted at clearing amyloid-β (Aβ) aggregates and slowing the rate of amyloid deposition. However, amyloid burden is not routinely evaluated quantitatively for purposes of disease progression and treatment response assessment. Statistical Parametric Mapping (SPM) is a technique comparing single-subject Positron Emission Tomography (PET) to a healthy cohort that may improve quantification of amyloid burden and diagnostic performance. While primarily used in 2-[18F]-fluoro-2-deoxy-D-glucose (FDG)-PET, SPM's utility in amyloid PET for AD diagnosis is less established and uncertainty remains regarding optimal normal database construction. Using commercially available SPM software, we created a database of 34 non-APOE ε4 carriers with normal cognitive testing (MMSE > 25) and negative cerebrospinal fluid (CSF) AD biomarkers. We compared this database to 115 cognitively normal subjects with variable AD risk factors. We hypothesized that SPM based on our database would identify more positive scans in the test cohort than the qualitatively rated [11C]-PiB PET (QR-PiB), that SPM-based interpretation would correlate better with CSF Aβ42 levels than QR-PiB, and that regional z-scores of specific brain regions known to be involved early in AD would be predictive of CSF Aβ42 levels. Fisher's exact test and the kappa coefficient assessed the agreement between SPM, QR-PiB PET, and CSF biomarkers. Logistic regression determined if the regional z-scores predicted CSF Aβ42 levels. An optimal z-score cutoff was calculated using Youden's index. We found SPM identified more positive scans than QR-PiB PET (19.1 vs. 9.6%) and that SPM correlated more closely with CSF Aβ42 levels than QR-PiB PET (kappa 0.13 vs. 0.06) indicating that SPM may have higher sensitivity than standard QR-PiB PET images. Regional analysis demonstrated the z-scores of the precuneus, anterior cingulate and posterior cingulate were predictive of CSF Aβ42 levels [OR (95% CI) 2.4 (1.1, 5.1) p = 0.024; 1.8 (1.1, 2.8) p = 0.020; 1.6 (1.1, 2.5) p = 0.026]. This study demonstrates the utility of using SPM with a "true normal" database and suggests that SPM enhances diagnostic performance in AD in the clinical setting through its quantitative approach, which will be increasingly important with future disease-modifying therapies.

Assessment of cerebral glucose metabolism in patients with heart failure by 18F-FDG PET/CT imaging

BACKGROUND

To evaluate the cerebral metabolism in patients with heart failure (HF).

METHODS

One hundred and two HF patients were prospectively enrolled, who underwent gated 99mTc-sestamibi single photon emission computed tomography (SPECT)/CT, cardiac and cerebral 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/CT. Fifteen healthy volunteers served as controls. Patients were stratified by extent of hibernating myocardium (HM) and left ventricular ejection fraction (LVEF) into 4 groups where Group1: HM < 10% (n = 33); Group2: HM ≥ 10%, LVEF < 25% (n = 34); Group3: HM ≥ 10%, 25% ≤ LVEF ≤ 40% (n = 16) and Group 4: LVEF > 40% (n = 19). The standardized uptake value (SUV) in the whole brain (SUVwhole-brain) and the SUV ratios (SUVR) in 24 cognition-related brain regions were determined. SUVwhole-brain and SUVRs were compared between the 4 patient groups and the healthy controls.

RESULTS

SUVwhole-brain (r = 0.245, P = 0.013) and SUVRs in frontal areas, hippocampus, and para-hippocampus (r: 0.213 to 0.308, all P < 0.05) were correlated with HM. SUVwhole-brain differed between four patient groups and the healthy volunteers (P = 0.016) and SUVwhole-brain in Group 1 was lower than that in healthy volunteers (P < 0.05). SUVRs of Group 3 in frontal areas were the highest among four patient subgroups (P < 0.05).

CONCLUSIONS

Cerebral metabolism in the whole brain was reduced but maintained in cognition-related frontal areas in HF patients with HM and moderately impaired global left ventricular function.

A computational model of neurodegeneration in Alzheimer's disease

Disruption of mental functions in Alzheimer's disease (AD) and related disorders is accompanied by selective degeneration of brain regions. These regions comprise large-scale ensembles of cells organized into systems for mental functioning, however the relationship between clinical symptoms of dementia, patterns of neurodegeneration, and functional systems is not clear. Here we present a model of the association between dementia symptoms and degenerative brain anatomy using F18-fluorodeoxyglucose PET and dimensionality reduction techniques in two cohorts of patients with AD. This reflected a simple information processing-based functional description of macroscale brain anatomy which we link to AD physiology, functional networks, and mental abilities. We further apply the model to normal aging and seven degenerative diseases of mental functions. We propose a global information processing model for mental functions that links neuroanatomy, cognitive neuroscience and clinical neurology.

Assessment of the In Vivo Relationship Between Cerebral Hypometabolism, Tau Deposition, TSPO Expression, and Synaptic Density in a Tauopathy Mouse Model: a Multi-tracer PET Study

Cerebral glucose hypometabolism is a typical hallmark of Alzheimer’s disease (AD), usually associated with ongoing neurodegeneration and neuronal dysfunction. However, underlying pathological processes are not fully understood and reproducibility in animal models is not well established. The aim of the present study was to investigate the regional interrelation of glucose hypometabolism measured by [¹⁸F]FDG positron emission tomography (PET) with various molecular targets of AD pathophysiology using the PET tracers [¹⁸F]PI-2620 for tau deposition, [¹⁸F]DPA-714 for TSPO expression associated with neuroinflammation, and [¹⁸F]UCB-H for synaptic density in a transgenic tauopathy mouse model. Seven-month-old rTg4510 mice (n = 8) and non-transgenic littermates (n = 8) were examined in a small animal PET scanner with the tracers listed above. Hypometabolism was observed throughout the forebrain of rTg4510 mice. Tau pathology, increased TSPO expression, and synaptic loss were co-localized in the cortex and hippocampus and correlated with hypometabolism. In the thalamus, however, hypometabolism occurred in the absence of tau-related pathology. Thus, cerebral hypometabolism was associated with two regionally distinct forms of molecular pathology: (1) characteristic neuropathology of the Alzheimer-type including synaptic degeneration and neuroinflammation co-localized with tau deposition in the cerebral cortex, and (2) pathological changes in the thalamus in the absence of other markers of AD pathophysiology, possibly reflecting downstream or remote adaptive processes which may affect functional connectivity. Our study demonstrates the feasibility of a multitracer approach to explore complex interactions of distinct AD-pathomechanisms in vivo in a small animal model. The observations demonstrate that multiple, spatially heterogeneous pathomechanisms can contribute to hypometabolism observed in AD mouse models and they motivate future longitudinal studies as well as the investigation of possibly comparable pathomechanisms in human patients.