Predicting changes in brain metabolism and progression from mild cognitive impairment to dementia using multitask Deep Learning models and explainable AI.

BACKGROUND: The prediction of Alzheimer's disease (AD) progression from its early stages is a research priority. In this context, the use of Artificial Intelligence (AI) in AD has experienced a notable surge in recent years. However, existing investigations predominantly concentrate on distinguishing clinical phenotypes through cross-sectional approaches. This study aims to investigate the potential of modeling additional dimensions of the disease, such as variations in brain metabolism assessed via [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET), and utilize this information to identify patients with mild cognitive impairment (MCI) who will progress to dementia (pMCI). METHODS: We analyzed data from 1,617 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had undergone at least one FDG-PET scan. We identified the brain regions with the most significant hypometabolism in AD and used Deep Learning (DL) models to predict future changes in brain metabolism. The best-performing model was then adapted under a multi-task learning framework to identify pMCI individuals. Finally, this model underwent further analysis using eXplainable AI (XAI) techniques. RESULTS: Our results confirm a strong association between hypometabolism, disease progression, and cognitive decline. Furthermore, we demonstrated that integrating data on changes in brain metabolism during training enhanced the models' ability to detect pMCI individuals (sensitivity=88.4%, specificity=86.9%). Lastly, the application of XAI techniques enabled us to delve into the brain regions with the most significant impact on model predictions, highlighting the importance of the hippocampus, cingulate cortex, and some subcortical structures. CONCLUSION: This study introduces a novel dimension to predictive modeling in AD, emphasizing the importance of projecting variations in brain metabolism under a multi-task learning paradigm.

Diagnosis of Alzheimer's disease and behavioural variant frontotemporal dementia with machine learning-aided neuropsychological assessment using feature engineering and genetic algorithms.

BACKGROUND: Neuropsychological assessment is considered a valid tool in the diagnosis of neurodegenerative disorders. However, there is an important overlap in cognitive profiles between Alzheimer's disease (AD) and behavioural variant frontotemporal dementia (bvFTD), and the usefulness in diagnosis is uncertain. We aimed to develop machine learning-based models for the diagnosis using cognitive tests. METHODS: Three hundred and twenty-nine participants (170 AD, 72 bvFTD, 87 healthy control [HC]) were enrolled. Evolutionary algorithms, inspired by the process of natural selection, were applied for both mono-objective and multi-objective classification and feature selection. Classical algorithms (NativeBayes, Support Vector Machines, among others) were also used, and a meta-model strategy. RESULTS: Accuracies for the diagnosis of AD, bvFTD and the differential diagnosis between them were higher than 84%. Algorithms were able to significantly reduce the number of tests and scores needed. Free and Cued Selective Reminding Test, verbal fluency and Addenbrooke's Cognitive Examination were amongst the most meaningful tests. CONCLUSIONS: Our study found high levels of accuracy for diagnosis using exclusively neuropsychological tests, which supports the usefulness of cognitive assessment in diagnosis. Machine learning may have a role in improving the interpretation and test selection.

An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders.

BACKGROUND: The analysis of health and medical data is crucial for improving the diagnosis precision, treatments and prevention. In this field, machine learning techniques play a key role. However, the amount of health data acquired from digital machines has high dimensionality and not all data acquired from digital machines are relevant for a particular disease. Primary Progressive Aphasia (PPA) is a neurodegenerative syndrome including several specific diseases, and it is a good model to implement machine learning analyses. In this work, we applied five feature selection algorithms to identify the set of relevant features from 18F-fluorodeoxyglucose positron emission tomography images of the main areas affected by PPA from patient records. On the other hand, we carried out classification and clustering algorithms before and after the feature selection process to contrast both results with those obtained in a previous work. We aimed to find the best classifier and the more relevant features from the WEKA tool to propose further a framework for automatic help on diagnosis. Dataset contains data from 150 FDG-PET imaging studies of 91 patients with a clinic prognosis of PPA, which were examined twice, and 28 controls. Our method comprises six different stages: (i) feature extraction, (ii) expertise knowledge supervision (iii) classification process, (iv) comparing classification results for feature selection, (v) clustering process after feature selection, and (vi) comparing clustering results with those obtained in a previous work. RESULTS: Experimental tests confirmed clustering results from a previous work. Although classification results for some algorithms are not decisive for reducing features precisely, Principal Components Analisys (PCA) results exhibited similar or even better performances when compared to those obtained with all features. CONCLUSIONS: Although reducing the dimensionality does not means a general improvement, the set of features is almost halved and results are better or quite similar. Finally, it is interesting how these results expose a finer grain classification of patients according to the neuroanatomy of their disease.

Modeling methodology for the accurate and prompt prediction of symptomatic events in chronic diseases.

Prediction of symptomatic crises in chronic diseases allows to take decisions before the symptoms occur, such as the intake of drugs to avoid the symptoms or the activation of medical alarms. The prediction horizon is in this case an important parameter in order to fulfill the pharmacokinetics of medications, or the time response of medical services. This paper presents a study about the prediction limits of a chronic disease with symptomatic crises: the migraine. For that purpose, this work develops a methodology to build predictive migraine models and to improve these predictions beyond the limits of the initial models. The maximum prediction horizon is analyzed, and its dependency on the selected features is studied. A strategy for model selection is proposed to tackle the trade off between conservative but robust predictive models, with respect to less accurate predictions with higher horizons. The obtained results show a prediction horizon close to 40min, which is in the time range of the drug pharmacokinetics. Experiments have been performed in a realistic scenario where input data have been acquired in an ambulatory clinical study by the deployment of a non-intrusive Wireless Body Sensor Network. Our results provide an effective methodology for the selection of the future horizon in the development of prediction algorithms for diseases experiencing symptomatic crises.

Proactive and reactive transmission power control for energy-efficient on-body communications.

In wireless body sensor network (WBSNs), the human body has an important effect on the performance of the communication due to the temporal variations caused and the attenuation and fluctuation of the path loss. This fact suggests that the transmission power must adapt to the current state of the link in a way that it ensures a balance between energy consumption and packet loss. In this paper, we validate our two transmission power level policies (reactive and predictive approaches) using the Castalia simulator. The integration of our experimental measurements in the simulator allows us to easily evaluate complex scenarios, avoiding the difficulties associated with a practical realization. Our results show that both schemes perform satisfactorily, providing overall energy savings of 24% and 22% for a case of study, as compared to the maximum transmission power mode.

Robust and Accurate Modeling Approaches for Migraine Per-Patient Prediction from Ambulatory Data.

Migraine is one of the most wide-spread neurological disorders, and its medical treatment represents a high percentage of the costs of health systems. In some patients, characteristic symptoms that precede the headache appear. However, they are nonspecific, and their prediction horizon is unknown and pretty variable; hence, these symptoms are almost useless for prediction, and they are not useful to advance the intake of drugs to be effective and neutralize the pain. To solve this problem, this paper sets up a realistic monitoring scenario where hemodynamic variables from real patients are monitored in ambulatory conditions with a wireless body sensor network (WBSN). The acquired data are used to evaluate the predictive capabilities and robustness against noise and failures in sensors of several modeling approaches. The obtained results encourage the development of per-patient models based on state-space models (N4SID) that are capable of providing average forecast windows of 47 min and a low rate of false positives.

Detergent-labile, supramolecular assemblies of KcsA: relative abundance and interactions involved.

In this work, we illustrate the ability of the prokaryotic potassium channel KcsA to assemble into a variety of supramolecular clusters of defined sizes containing the tetrameric KcsA as the repeating unit. Such clusters, particularly the larger ones, are markedly detergent-labile and thus, disassemble readily upon exposure to the detergents commonly used in protein purification or conventional electrophoresis analysis. This is a reversible process, as cluster re-assembly occurs upon detergent removal and without the need of added membrane lipids. Interestingly, the dimeric ensemble between two tetrameric KcsA molecules are quite resistant to detergent disassembly to individual KcsA tetramers and along with the latter, are likely the basic building blocks through which the larger clusters are organized. As to the proteins domains involved in clustering, we have observed disassembly of KcsA clusters by SDS-like alkyl sulfates. As these amphiphiles bind to inter-subunit, "non-annular" sites on the protein, these observations suggest that such sites also mediate channel-channel interactions leading to cluster assembly.

Genetic-based patient stratification in Alzheimer's disease.

Alzheimer's disease (AD) shows a high pathological and symptomatological heterogeneity. To study this heterogeneity, we have developed a patient stratification technique based on one of the most significant risk factors for the development of AD: genetics. We addressed this challenge by including network biology concepts, mapping genetic variants data into a brain-specific protein-protein interaction (PPI) network, and obtaining individualized PPI scores that we then used as input for a clustering technique. We then phenotyped each obtained cluster regarding genetics, sociodemographics, biomarkers, fluorodeoxyglucose-positron emission tomography (FDG-PET) imaging, and neurocognitive assessments. We found three clusters defined mainly by genetic variants found in MAPT, APP, and APOE, considering known variants associated with AD and other neurodegenerative disease genetic architectures. Profiling of these clusters revealed minimal variation in AD symptoms and pathology, suggesting different biological mechanisms may activate the neurodegeneration and pathobiological patterns behind AD and result in similar clinical and pathological presentations, even a shared disease diagnosis. Lastly, our research highlighted MAPT, APP, and APOE as key genes where these genetic distinctions manifest, suggesting them as potential targets for personalized drug development strategies to address each AD subgroup individually.

A data-driven approach to complement the A/T/(N) classification system using CSF biomarkers.

AIMS: The AT(N) classification system not only improved the biological characterization of Alzheimer's disease (AD) but also raised challenges for its clinical application. Unbiased, data-driven techniques such as clustering may help optimize it, rendering informative categories on biomarkers' values. METHODS: We compared the diagnostic and prognostic abilities of CSF biomarkers clustering results against their AT(N) classification. We studied clinical (patients from our center) and research (Alzheimer's Disease Neuroimaging Initiative) cohorts. The studied CSF biomarkers included Aß(1-42), Aß(1-42)/Aß(1-40) ratio, tTau, and pTau. RESULTS: The optimal solution yielded three clusters in both cohorts, significantly different in diagnosis, AT(N) classification, values distribution, and survival. We defined these three CSF groups as (i) non-defined or unrelated to AD, (ii) early stages and/or more delayed risk of conversion to dementia, and (iii) more severe cognitive impairment subjects with faster progression to dementia. CONCLUSION: We propose this data-driven three-group classification as a meaningful and straightforward approach to evaluating the risk of conversion to dementia, complementary to the AT(N) system classification.

Monitoring differences in the function of the autonomic nervous system in patients with chronic insomnia using a wearable device.

STUDY OBJECTIVES: to characterize possible differences in the function of the ANS in patients with chronic insomnia compared to a control group, using a wearable device, in order to determine whether those findings allow diagnosing this medical entity. METHODS: Thirty-two patients with chronic insomnia and nineteen patients without any sleep disorder, as a control group, were recruited prospectively. Both groups of patients underwent an in-patient night with simultaneous polysomnography and wearable device recording Empatica E4 a diverse array of physiological signals, including electrodermal activity, temperature, accelerometry, and photoplethysmography, providing a comprehensive resource for in-depth sleep analysis. RESULTS: In polysomnography, patients suffering from insomnia showed a significant decrease in sleep efficiency and total sleep time, prolonged sleep latency, and increased wakefulness after sleep onset. Accelerometry results were statistically significant differences in the three axis (x, y, z) just in stage N3, no differences were observed between both groups in REM sleep. The lowest temperature was reached in REM sleep in both groups. Peripheral temperature did not decrease during the different sleep phases compared to wakefulness in insomnia, unlike in the control group. Heart rate was higher in patients with insomnia than in controls during wakefulness and sleep stage. Heart rate variability was lower in stage N3 and higher in REM sleep compared to wakefulness in both groups. Sweating was significantly higher in patients with insomnia compared to the control group, as indicated by Skin Conductance Variability values and Sudomotor Nerve. CONCLUSIONS: Our study suggests that patients with insomnia have increased sympathetic activity during sleep, showing a higher heart rate. Temperature and sweating significantly influence the different sleep phases.

Comparison of Laryngeal Mask Airway Supreme and Laryngeal Mask Airway Proseal with respect to oropharyngeal leak pressure during laparoscopic cholecystectomy: a randomised controlled trial.

CONTEXT: A comparison of the efficacy and safety of the Laryngeal Mask Airway (LMA) Supreme (LMAS) versus the LMA Proseal (LMAP) in elective laparoscopic cholecystectomy. OBJECTIVES: To compare the LMAS with LMAP in terms of ventilatory efficacy, airway leak pressure (airway protection), ease-of-use and complications. DESIGN: Prospective, single-blind, randomised, controlled study. SETTING: The Hospital del Sureste and Hospital Ramon y Cajal, Madrid, between May 2009 and March 2011. The Hospital del Sureste is a secondary hospital and Hospital Ramon y Cajal is a tertiary hospital. PATIENTS: Patients undergoing elective laparoscopic cholecystectomy were studied following informed consent. Inclusion criteria were American Society of Anesthesiologists physical status I to III and age 18 or more. Exclusion criteria were BMI more than 40 kg m, symptomatic hiatus hernia or severe gastro-oesophageal reflux. INTERVENTIONS: Anaesthesiologists experienced in the use of LMAP and LMAS participated in the trial. One hundred twenty-two patients were randomly allocated to LMAS or LMAP. MAIN OUTCOME MEASURES: Our primary outcome measure was the oropharyngeal leak pressure (OLP). Secondary outcomes were the time and number of attempts for insertion, ease of insertion of the drain tube, adequacy of ventilation and the incidence of complication. Patients were interviewed postoperatively to evaluate the presence of sore throat, dysphagia or dysphonia. RESULTS: Two patients were excluded when surgery changed from laparoscopic to open. A total of 120 patients were finally included in the analysis. The mean OLP in the LMAP group was significantly higher than that in the LMAS group (30.7 ±â€Š6.2 versus 26.8 ±â€Š4.1 cmH2O;P < 0.01). This was consistent with a higher maximum tidal volume achieved with the LMAP compared to the LMAS (511 ±â€Š68 versus 475 ±â€Š55 ml; P = 0.04). The success rate of the first attempt insertion was higher for the LMAS group than the LMAP group (96.7 and 71.2%, respectively; P < 0.01). The time taken for insertion, ease of insertion of the drain tube, complications and postoperative pharyngolaryngeal adverse events were similar in both groups. CONCLUSION: The LMAP has a higher OLP and achieves a higher maximum tidal volume compared to the LMAS, in patients undergoing elective laparoscopic cholecystectomy. The success of the first attempt insertion was higher for the LMAS.

Accurate human tissue characterization for energy-efficient wireless on-body communications.

The demand for Wireless Body Sensor Networks (WBSNs) is rapidly increasing due to the revolution in wearable systems demonstrated by the penetration of on-the-body sensors in hospitals, sports medicine and general health-care practices. In WBSN, the body acts as a communication channel for the propagation of electromagnetic (EM) waves, where losses are mainly due to absorption of power in the tissue. This paper shows the effects of the dielectric properties of biological tissues in the signal strength and, for the first time, relates these effects with the human body composition. After a careful analysis of results, this work proposes a reactive algorithm for power transmission to alleviate the effect of body movement and body type. This policy achieves up to 40.8% energy savings in a realistic scenario with no performance overhead.

Power impact of loop buffer schemes for biomedical wireless sensor nodes.

Instruction memory organisations are pointed out as one of the major sources of energy consumption in embedded systems. As these systems are characterised by restrictive resources and a low-energy budget, any enhancement in this component allows not only to decrease the energy consumption but also to have a better distribution of the energy budget throughout the system. Loop buffering is an effective scheme to reduce energy consumption in instruction memory organisations. In this paper, the loop buffer concept is applied in real-life embedded applications that are widely used in biomedical Wireless Sensor Nodes, to show which scheme of loop buffer is more suitable for applications with certain behaviour. Post-layout simulations demonstrate that a trade-off exists between the complexity of the loop buffer architecture and the energy savings of utilising it. Therefore, the use of loop buffer architectures in order to optimise the instruction memory organisation from the energy efficiency point of view should be evaluated carefully, taking into account two factors: (1) the percentage of the execution time of the application that is related to the execution of the loops, and (2) the distribution of the execution time percentage over each one of the loops that form the application.

Ubiquitous green computing techniques for high demand applications in Smart environments.

Ubiquitous sensor network deployments, such as the ones found in Smart cities and Ambient intelligence applications, require constantly increasing high computational demands in order to process data and offer services to users. The nature of these applications imply the usage of data centers. Research has paid much attention to the energy consumption of the sensor nodes in WSNs infrastructures. However, supercomputing facilities are the ones presenting a higher economic and environmental impact due to their very high power consumption. The latter problem, however, has been disregarded in the field of smart environment services. This paper proposes an energy-minimization workload assignment technique, based on heterogeneity and application-awareness, that redistributes low-demand computational tasks from high-performance facilities to idle nodes with low and medium resources in the WSN infrastructure. These non-optimal allocation policies reduce the energy consumed by the whole infrastructure and the total execution time.

Cluster-Then-Classify Methodology for the Identification of Pain Episodes in Chronic Diseases.

Chronic diseases benefit of the advances on personalize medicine coming out of the integrative convergence of significant developments in systems biology, the Internet of Things and Artificial Intelligence. 70% to 80% of all healthcare costs in the EU and US are currently spent on chronic diseases, leading to estimated costs of C=700 billion and $3.5 trillion respectively. The management of symptomatic pain crises in chronic diseases is based on general clinical guidelines that do not take into account the singularities of the crises, such as their intensity or duration, so that the pain of those particular crises may cause the medication to be ineffective and lead the patient to overmedication. Knowing in detail the characteristics of the pain would help the physician to objectively prescribe personalized treatments for each patient and crisis. In this manuscript, we make a step further on the prediction of symptomatic crisis from ambulatory collected data in chronic diseases. We propose a categorization of pain types according to subjective symptoms of real patients. Our approach has been evaluated in the migraine disease. The migraine is one of the most disabling neurological diseases that affects over 12% of the population worldwide and leads to high economic costs for private and public health systems. This study aims to classify pain episodes by the characterization of pain curves reported by patients in real time. Pain curves have been described as a set of morphological features. With these features the pain episodes are clustered then classified by unsupervised and supervised machine learning models. It is shown that the evolution of different pain episodes in chronic diseases can be modeled and clustered. Over a population of 51 migraine patients, it has been found that there are 4 clusters of pain types that can be classified using 4 morphological features with an accuracy of 99.0% using a Logistic Model Tree algorithm.

On the limits of graph neural networks for the early diagnosis of Alzheimer's disease.

Alzheimer's disease (AD) is a neurodegenerative disease whose molecular mechanisms are activated several years before cognitive symptoms appear. Genotype-based prediction of the phenotype is thus a key challenge for the early diagnosis of AD. Machine learning techniques that have been proposed to address this challenge do not consider known biological interactions between the genes used as input features, thus neglecting important information about the disease mechanisms at play. To mitigate this, we first extracted AD subnetworks from several protein-protein interaction (PPI) databases and labeled these with genotype information (number of missense variants) to make them patient-specific. Next, we trained Graph Neural Networks (GNNs) on the patient-specific networks for phenotype prediction. We tested different PPI databases and compared the performance of the GNN models to baseline models using classical machine learning techniques, as well as randomized networks and input datasets. The overall results showed that GNNs could not outperform a baseline predictor only using the APOE gene, suggesting that missense variants are not sufficient to explain disease risk beyond the APOE status. Nevertheless, our results show that GNNs outperformed other machine learning techniques and that protein-protein interactions lead to superior results compared to randomized networks. These findings highlight that gene interactions are a valuable source of information in predicting disease status.

Body Complexion and Circulating Lipids in the Risk of TDP-43 Related Disorders.

Objective: Frontotemporal dementia (FTD) and amyotrophic lateral sclerosis (ALS) are two distinct degenerative disorders with overlapping genetics, clinical manifestations, and pathology, including the presence of TDP-43 aggregates in nearly 50% of patients with FTD and 98% of all patients with ALS. Here, we evaluate whether different genetically predicted body lipid metabolic traits are causally associated with the risk of FTD with TDP-43 aggregates, compare it to their causal role in the risk of ALS, and identify genetic variants shared between these two TDP43 related disorders in relation to lipid metabolic traits. Methods: We conducted two-sample Mendelian randomization analyses (2SMR) to evaluate the causal association of 9 body complexion and 9 circulating lipids traits with the risk of FTD with TDP-43 aggregates and the risk of ALS. The inverse-variance weighted method was the primary analysis, followed by secondary sensitive analyses. We then looked for common genetic variants between FTD and ALS in relation to lipid metabolic traits. Results: Genetically increased trunk-predicted mass, fat-free mass, and higher circulating triglycerides levels were suggestively associated with a higher risk of FTD with TDP-43 aggregates. Circulating lipids, mainly LDL cholesterol, were causally associated with a higher risk of ALS. We identified two genetic variants, EIF4ENIF1 and HNRNPK, in relation to body complexion and circulating lipids shared between FTD with TDP-43 aggregates and ALS. Conclusion: This work provides evidence that body complexion and circulating lipids traits impact differentially on the risk of FTD and ALS, suggesting new and specific interventional approaches in the control of body lipid metabolism for FTD and ALS, and identified HNRNPK as a potential link between circulating lipids levels and these disorders.

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).

Predictive and diagnosis models of stroke from hemodynamic signal monitoring.

This work presents a novel and promising approach to the clinical management of acute stroke. Using machine learning techniques, our research has succeeded in developing accurate diagnosis and prediction real-time models from hemodynamic data. These models are able to diagnose stroke subtype with 30 min of monitoring, to predict the exitus during the first 3 h of monitoring, and to predict the stroke recurrence in just 15 min of monitoring. Patients with difficult access to a CT scan and all patients that arrive at the stroke unit of a specialized hospital will benefit from these positive results. The results obtained from the real-time developed models are the following: stroke diagnosis around 98% precision (97.8% sensitivity, 99.5% specificity), exitus prediction with 99.8% precision (99.8% Sens., 99.9% Spec.), and 98% precision predicting stroke recurrence (98% Sens., 99% Spec.). Graphical abstract depicting the complete process since a patient is monitored until the data collected is used to generate models.

Genetic Algorithms for Optimized Diagnosis of Alzheimer's Disease and Frontotemporal Dementia Using Fluorodeoxyglucose Positron Emission Tomography Imaging.

Genetic algorithms have a proven capability to explore a large space of solutions, and deal with very large numbers of input features. We hypothesized that the application of these algorithms to 18F-Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) may help in diagnosis of Alzheimer's disease (AD) and Frontotemporal Dementia (FTD) by selecting the most meaningful features and automating diagnosis. We aimed to develop algorithms for the three main issues in the diagnosis: discrimination between patients with AD or FTD and healthy controls (HC), differential diagnosis between behavioral FTD (bvFTD) and AD, and differential diagnosis between primary progressive aphasia (PPA) variants. Genetic algorithms, customized with K-Nearest Neighbor and BayesNet Naives as the fitness function, were developed and compared with Principal Component Analysis (PCA). K-fold cross validation within the same sample and external validation with ADNI-3 samples were performed. External validation was performed for the algorithms distinguishing AD and HC. Our study supports the use of FDG-PET imaging, which allowed a very high accuracy rate for the diagnosis of AD, FTD, and related disorders. Genetic algorithms identified the most meaningful features with the minimum set of features, which may be relevant for automated assessment of brain FDG-PET images. Overall, our study contributes to the development of an automated, and optimized diagnosis of neurodegenerative disorders using brain metabolism.