Development and validation of a novel dementia of Alzheimer's type (DAT) score based on metabolism FDG-PET imaging

Diagnostic performance of molecular imaging methods in predicting the progression from mild cognitive impairment to dementia: an updated systematic review

PURPOSE

Epidemiological and logistical reasons are slowing the clinical validation of the molecular imaging biomarkers in the initial stages of neurocognitive disorders. We provide an updated systematic review of the recent advances (2017-2022), highlighting methodological shortcomings.

METHODS

Studies reporting the diagnostic accuracy values of the molecular imaging techniques (i.e., amyloid-, tau-, [18F]FDG-PETs, DaT-SPECT, and cardiac [123I]-MIBG scintigraphy) in predicting progression from mild cognitive impairment (MCI) to dementia were selected according to the Preferred Reporting Items for a Systematic Review and Meta-Analysis (PRISMA) method and evaluated with the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. Main eligibility criteria were as follows: (1) ≥ 50 subjects with MCI, (2) follow-up ≥ 3 years, (3) gold standard: progression to dementia or diagnosis on pathology, and (4) measures of prospective accuracy.

RESULTS

Sensitivity (SE) and specificity (SP) in predicting progression to dementia, mainly to Alzheimer's dementia were 43-100% and 63-94% for [18F]FDG-PET and 64-94% and 48-93% for amyloid-PET. Longitudinal studies were lacking for less common disorders (Dementia with Lewy bodies-DLB and Frontotemporal lobe degeneration-FTLD) and for tau-PET, DaT-SPECT, and [123I]-MIBG scintigraphy. Therefore, the accuracy values from cross-sectional studies in a smaller sample of subjects (n > 20, also including mild dementia stage) were chosen as surrogate outcomes. DaT-SPECT showed 47-100% SE and 71-100% SP in differentiating Lewy body disease (LBD) from non-LBD conditions; tau-PET: 88% SE and 100% SP in differentiating DLB from Posterior Cortical Atrophy. [123I]-MIBG scintigraphy differentiated LBD from non-LBD conditions with 47-100% SE and 71-100% SP.

CONCLUSION

Molecular imaging has a moderate-to-good accuracy in predicting the progression of MCI to Alzheimer's dementia. Longitudinal studies are sparse in non-AD conditions, requiring additional efforts in these settings.

Differential diagnosis of frontotemporal dementia subtypes with explainable deep learning on structural MRI

Background

Frontotemporal dementia (FTD) represents a collection of neurobehavioral and neurocognitive syndromes that are associated with a significant degree of clinical, pathological, and genetic heterogeneity. Such heterogeneity hinders the identification of effective biomarkers, preventing effective targeted recruitment of participants in clinical trials for developing potential interventions and treatments. In the present study, we aim to automatically differentiate patients with three clinical phenotypes of FTD, behavioral-variant FTD (bvFTD), semantic variant PPA (svPPA), and nonfluent variant PPA (nfvPPA), based on their structural MRI by training a deep neural network (DNN).

Methods

Data from 277 FTD patients (173 bvFTD, 63 nfvPPA, and 41 svPPA) recruited from two multi-site neuroimaging datasets: the Frontotemporal Lobar Degeneration Neuroimaging Initiative and the ARTFL-LEFFTDS Longitudinal Frontotemporal Lobar Degeneration databases. Raw T1-weighted MRI data were preprocessed and parcellated into patch-based ROIs, with cortical thickness and volume features extracted and harmonized to control the confounding effects of sex, age, total intracranial volume, cohort, and scanner difference. A multi-type parallel feature embedding framework was trained to classify three FTD subtypes with a weighted cross-entropy loss function used to account for unbalanced sample sizes. Feature visualization was achieved through post-hoc analysis using an integrated gradient approach.

Results

The proposed differential diagnosis framework achieved a mean balanced accuracy of 0.80 for bvFTD, 0.82 for nfvPPA, 0.89 for svPPA, and an overall balanced accuracy of 0.84. Feature importance maps showed more localized differential patterns among different FTD subtypes compared to groupwise statistical mapping.

Conclusion

In this study, we demonstrated the efficiency and effectiveness of using explainable deep-learning-based parallel feature embedding and visualization framework on MRI-derived multi-type structural patterns to differentiate three clinically defined subphenotypes of FTD: bvFTD, nfvPPA, and svPPA, which could help with the identification of at-risk populations for early and precise diagnosis for intervention planning.

Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review

INTRODUCTION

Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.

METHODS

We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.

RESULTS

A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.

DISCUSSION

The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.

HIGHLIGHTS

There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.

Deep learning combining FDG-PET and neurocognitive data accurately predicts MCI conversion to Alzheimer's dementia 3-year post MCI diagnosis

INTRODUCTION

This study reports a novel deep learning approach to predict mild cognitive impairment (MCI) conversion to Alzheimer's dementia (AD) within three years using whole-brain fluorodeoxyglucose (FDG) positron emission tomography (PET) and cognitive scores (CS).

METHODS

This analysis consisted of 150 normal controls (CN), 257 MCI, and 205  AD subjects from ADNI. FDG-PET and CS were obtained at MCI diagnosis to predict AD conversion within three years of MCI diagnosis using convolutional neural networks.

RESULTS

Neurocognitive scores predicted better than FDG-PET per se, but the best model was a combination of FDG-PET, age, and neurocognitive data, yielding an AUC of 0.785 ± 0.096 and a balanced accuracy of 0.733 ± 0.098. Saliency maps highlighted putamen, thalamus, inferior frontal gyrus, parietal operculum, precuneus cortices, calcarine cortices, temporal gyrus, and planum temporale to be important for prediction.

DISCUSSION

Deep learning accurately predicts MCI conversion to AD and provides neural correlates of brain regions associated with AD conversion.

Longitudinal Spatial Relationships Between Atrophy and Hypometabolism Across the Alzheimer's Disease Continuum

BACKGROUND

The A/T/N framework allows for the assessment of pathology-specific markers of MRI-derived structural atrophy and hypometabolism on 18FDG-PET. However, how these measures relate to each other locally and distantly across pathology-defined A/T/N groups is currently unclear.

OBJECTIVE

To determine the regions of association between atrophy and hypometabolism in A/T/N groups both within and across time points.

METHODS

We examined multivariate multimodal neuroimaging relationships between MRI and 18FDG-PET among suspected non-Alzheimer's disease pathology (SNAP) (A-T/N+; n = 14), Amyloid Only (A+T-N-; n = 24) and Probable AD (A+T+N+; n = 77) groups. Sparse canonical correlation analyses were employed to model spatially disjointed regions of association between MRI and 18FDG-PET data. These relationships were assessed at three combinations of time points -cross-sectionally, between baseline visits and between month 12 (M-12) follow-up visits, as well as longitudinally between baseline and M-12 follow-up.

RESULTS

In the SNAP group, spatially overlapping relationships between atrophy and hypometabolism were apparent in the bilateral temporal lobes when both modalities were assessed at the M-12 timepoint. Amyloid-Only subjects showed spatially discordant distributed atrophy-hypometabolism relationships at all time points assessed. In Probable AD subjects, local correlations were evident in the bilateral temporal lobes when both modalities were assessed at baseline and at M-12. Across groups, hypometabolism at baseline correlated with non-local, or distant, atrophy at M-12.

CONCLUSION

These results support the view that local concordance of atrophy and hypometabolism is the result of a tau-mediated process driving neurodegeneration.

Predicting time-to-conversion for dementia of Alzheimer's type using multi-modal deep survival analysis

Dementia of Alzheimer's Type (DAT) is a complex disorder influenced by numerous factors, and it is difficult to predict individual progression trajectory from normal or mildly impaired cognition to DAT. An in-depth examination of multiple modalities of data may yield an accurate estimate of time-to-conversion to DAT for preclinical subjects at various stages of disease development. We used a deep-learning model designed for survival analyses to predict subjects' time-to-conversion to DAT using the baseline data of 401 subjects with 63 features from MRI, genetic, and CDC (Cognitive tests, Demographic, and CSF) data in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our study demonstrated that CDC data outperform genetic or MRI data in predicting DAT time-to-conversion for subjects with Mild Cognitive Impairment (MCI). On the other hand, genetic data provided the most predictive power for subjects with Normal Cognition (NC) at the time of the visit. Furthermore, combining MRI and genetic features improved the time-to-event prediction over using either modality alone. Finally, adding CDC to any combination of features only worked as well as using only the CDC features.

Detection of Association Features Based on Gene Eigenvalues and MRI Imaging Using Genetic Weighted Random Forest

In the studies of Alzheimer's disease (AD), jointly analyzing imaging data and genetic data provides an effective method to explore the potential biomarkers of AD. AD can be separated into healthy controls (HC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI) and AD. In the meantime, identifying the important biomarkers of AD progression, and analyzing these biomarkers in AD provide valuable insights into understanding the mechanism of AD. In this paper, we present a novel data fusion method and a genetic weighted random forest method to mine important features. Specifically, we amplify the difference among AD, LMCI, EMCI and HC by introducing eigenvalues calculated from the gene p-value matrix for feature fusion. Furthermore, we construct the genetic weighted random forest using the resulting fused features. Genetic evolution is used to increase the diversity among decision trees and the decision trees generated are weighted by weights. After training, the genetic weighted random forest is analyzed further to detect the significant fused features. The validation experiments highlight the performance and generalization of our proposed model. We analyze the biological significance of the results and identify some significant genes (CSMD1, CDH13, PTPRD, MACROD2 and WWOX). Furthermore, the calcium signaling pathway, arrhythmogenic right ventricular cardiomyopathy and the glutamatergic synapse pathway were identified. The investigational findings demonstrate that our proposed model presents an accurate and efficient approach to identifying significant biomarkers in AD.

Machine learning based multi-modal prediction of future decline toward Alzheimer's disease: An empirical study

Alzheimer's disease (AD) is a neurodegenerative condition that progresses over decades. Early detection of individuals at high risk of future progression toward AD is likely to be of critical significance for the successful treatment and/or prevention of this devastating disease. In this paper, we present an empirical study to characterize how predictable an individual subjects' future AD trajectory is, several years in advance, based on rich multi-modal data, and using modern deep learning methods. Crucially, the machine learning strategy we propose can handle different future time horizons and can be trained with heterogeneous data that exhibit missingness and non-uniform follow-up visit times. Our experiments demonstrate that our strategy yields predictions that are more accurate than a model trained on a single time horizon (e.g. 3 years), which is common practice in prior literature. We also provide a comparison between linear and nonlinear models, verifying the well-established insight that the latter can offer a boost in performance. Our results also confirm that predicting future decline for cognitively normal (CN) individuals is more challenging than for individuals with mild cognitive impairment (MCI). Intriguingly, however, we discover that prediction accuracy decreases with increasing time horizon for CN subjects, but the trend is in the opposite direction for MCI subjects. Additionally, we quantify the contribution of different data types in prediction, which yields novel insights into the utility of different biomarkers. We find that molecular biomarkers are not as helpful for CN individuals as they are for MCI individuals, whereas magnetic resonance imaging biomarkers (hippocampus volume, specifically) offer a significant boost in prediction accuracy for CN individuals. Finally, we show how our model's prediction reveals the evolution of individual-level progression risk over a five-year time horizon. Our code is available at https://github.com/batuhankmkaraman/mlbasedad.

Network-wise concordance of multimodal neuroimaging features across the Alzheimer's disease continuum

Background

Concordance between cortical atrophy and cortical glucose hypometabolism within distributed brain networks was evaluated among cerebrospinal fluid (CSF) biomarker-defined amyloid/tau/neurodegeneration (A/T/N) groups.

Method

We computed correlations between cortical thickness and fluorodeoxyglucose metabolism within 12 functional brain networks. Differences among A/T/N groups (biomarker normal [BN], Alzheimer's disease [AD] continuum, suspected non-AD pathologic change [SNAP]) in network concordance and relationships to longitudinal change in cognition were assessed.

Results

Network-wise markers of concordance distinguish SNAP subjects from BN subjects within the posterior multimodal and language networks. AD-continuum subjects showed increased concordance in 9/12 networks assessed compared to BN subjects, as well as widespread atrophy and hypometabolism. Baseline network concordance was associated with longitudinal change in a composite memory variable in both SNAP and AD-continuum subjects.

Conclusions

Our novel study investigates the interrelationships between atrophy and hypometabolism across brain networks in A/T/N groups, helping disentangle the structure-function relationships that contribute to both clinical outcomes and diagnostic uncertainty in AD.

Machine Learning Based Multimodal Neuroimaging Genomics Dementia Score for Predicting Future Conversion to Alzheimer's Disease

BACKGROUND

The increasing availability of databases containing both magnetic resonance imaging (MRI) and genetic data allows researchers to utilize multimodal data to better understand the characteristics of dementia of Alzheimer's type (DAT).

OBJECTIVE

The goal of this study was to develop and analyze novel biomarkers that can help predict the development and progression of DAT.

METHODS

We used feature selection and ensemble learning classifier to develop an image/genotype-based DAT score that represents a subject's likelihood of developing DAT in the future. Three feature types were used: MRI only, genetic only, and combined multimodal data. We used a novel data stratification method to better represent different stages of DAT. Using a pre-defined 0.5 threshold on DAT scores, we predicted whether a subject would develop DAT in the future.

RESULTS

Our results on Alzheimer's Disease Neuroimaging Initiative (ADNI) database showed that dementia scores using genetic data could better predict future DAT progression for currently normal control subjects (Accuracy = 0.857) compared to MRI (Accuracy = 0.143), while MRI can better characterize subjects with stable mild cognitive impairment (Accuracy = 0.614) compared to genetics (Accuracy = 0.356). Combining MRI and genetic data showed improved classification performance in the remaining stratified groups.

CONCLUSION

MRI and genetic data can contribute to DAT prediction in different ways. MRI data reflects anatomical changes in the brain, while genetic data can detect the risk of DAT progression prior to the symptomatic onset. Combining information from multimodal data appropriately can improve prediction performance.

Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods

Dementia and Alzheimer’s disease are caused by neurodegeneration and poor communication between neurons in the brain. So far, no effective medications have been discovered for dementia and Alzheimer’s disease. Thus, early diagnosis is necessary to avoid the development of these diseases. In this study, efficient machine learning algorithms were assessed to evaluate the Open Access Series of Imaging Studies (OASIS) dataset for dementia diagnosis. Two CNN models (AlexNet and ResNet-50) and hybrid techniques between deep learning and machine learning (AlexNet+SVM and ResNet-50+SVM) were also evaluated for the diagnosis of Alzheimer’s disease. For the OASIS dataset, we balanced the dataset, replaced the missing values, and applied the t-Distributed Stochastic Neighbour Embedding algorithm (t-SNE) to represent the high-dimensional data in the low-dimensional space. All of the machine learning algorithms, namely, Support Vector Machine (SVM), Decision Tree, Random Forest and K Nearest Neighbours (KNN), achieved high performance for diagnosing dementia. The random forest algorithm achieved an overall accuracy of 94% and precision, recall and F1 scores of 93%, 98% and 96%, respectively. The second dataset, the MRI image dataset, was evaluated by AlexNet and ResNet-50 models and AlexNet+SVM and ResNet-50+SVM hybrid techniques. All models achieved high performance, but the performance of the hybrid methods between deep learning and machine learning was better than that of the deep learning models. The AlexNet+SVM hybrid model achieved accuracy, sensitivity, specificity and AUC scores of 94.8%, 93%, 97.75% and 99.70%, respectively.

Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review

BACKGROUND

An increase in lifespan in our society is a double-edged sword that entails a growing number of patients with neurocognitive disorders, Alzheimer's disease being the most prevalent. Advances in medical imaging and computational power enable new methods for the early detection of neurocognitive disorders with the goal of preventing or reducing cognitive decline. Computer-aided image analysis and early detection of changes in cognition is a promising approach for patients with mild cognitive impairment, sometimes a prodromal stage of Alzheimer's disease dementia.

METHODS

We conducted a systematic review following PRISMA guidelines of studies where machine learning was applied to neuroimaging data in order to predict whether patients with mild cognitive impairment might develop Alzheimer's disease dementia or remain stable. After removing duplicates, we screened 452 studies and selected 116 for qualitative analysis.

RESULTS

Most studies used magnetic resonance image (MRI) and positron emission tomography (PET) data but also magnetoencephalography. The datasets were mainly extracted from the Alzheimer's disease neuroimaging initiative (ADNI) database with some exceptions. Regarding the algorithms used, the most common was support vector machine with a mean accuracy of 75.4%, but convolutional neural networks achieved a higher mean accuracy of 78.5%. Studies combining MRI and PET achieved overall better classification accuracy than studies that only used one neuroimaging technique. In general, the more complex models such as those based on deep learning, combined with multimodal and multidimensional data (neuroimaging, clinical, cognitive, genetic, and behavioral) achieved the best performance.

CONCLUSIONS

Although the performance of the different methods still has room for improvement, the results are promising and this methodology has a great potential as a support tool for clinicians and healthcare professionals.

Early diagnosis of Alzheimer's disease on ADNI data using novel longitudinal score based on functional principal component analysis

Methods: Alzheimer's disease (AD) is a worldwide prevalent age-related neurodegenerative disease with no available cure yet. Early prognosis is therefore crucial for planning proper clinical intervention. It is especially true for people diagnosed with mild cognitive impairment, to whom the prediction of whether and when the future disease onset would happen is particularly valuable. However, such prognostic prediction has been proven to be challenging, and previous studies have only achieved limited success. Approach: In this study, we seek to extract the principal component of the longitudinal disease progression trajectory in the early stage of AD, measured as the magnetic resonance imaging (MRI)-derived structural volume, to predict the onset of AD for mild cognitive impaired patients two years ahead. Results: Cross-validation results of LASSO regression using the longitudinal functional principal component (FPC) features show significant improved predictive power compared to training using the baseline volume 12 months before AD conversion [area under the receiver operating characteristic curve (AUC) of 0.802 versus 0.732] and 24 months before AD conversion (AUC of 0.816 versus 0.717). Conclusions: We present a framework using the FPCA to extract features from MRI-derived information collected from multiple timepoints. The results of our study demonstrate the advantageous predictive power of the population-based longitudinal features to predict the disease onset compared with using only cross-sectional data-based on volumetric features extracted from a single timepoint, demonstrating the improved prediction power using FPC-derived longitudinal features.

Machine Learning and Novel Biomarkers for the Diagnosis of Alzheimer's Disease

Background: Alzheimer’s disease (AD) is a complex and severe neurodegenerative disease that still lacks effective methods of diagnosis. The current diagnostic methods of AD rely on cognitive tests, imaging techniques and cerebrospinal fluid (CSF) levels of amyloid-β1-42 (Aβ42), total tau protein and hyperphosphorylated tau (p-tau). However, the available methods are expensive and relatively invasive. Artificial intelligence techniques like machine learning tools have being increasingly used in precision diagnosis. Methods: We conducted a meta-analysis to investigate the machine learning and novel biomarkers for the diagnosis of AD. Methods: We searched PubMed, the Cochrane Central Register of Controlled Trials, and the Cochrane Database of Systematic Reviews for reviews and trials that investigated the machine learning and novel biomarkers in diagnosis of AD. Results: In additional to Aβ and tau-related biomarkers, biomarkers according to other mechanisms of AD pathology have been investigated. Neuronal injury biomarker includes neurofiliament light (NFL). Biomarkers about synaptic dysfunction and/or loss includes neurogranin, BACE1, synaptotagmin, SNAP-25, GAP-43, synaptophysin. Biomarkers about neuroinflammation includes sTREM2, and YKL-40. Besides, d-glutamate is one of coagonists at the NMDARs. Several machine learning algorithms including support vector machine, logistic regression, random forest, and naïve Bayes) to build an optimal predictive model to distinguish patients with AD from healthy controls. Conclusions: Our results revealed machine learning with novel biomarkers and multiple variables may increase the sensitivity and specificity in diagnosis of AD. Rapid and cost-effective HPLC for biomarkers and machine learning algorithms may assist physicians in diagnosing AD in outpatient clinics.

Correlation Between Brain 18F-AV45 and 18F-FDG PET Distribution Characteristics and Cognitive Function in Patients with Mild and Moderate Alzheimer's Disease

BACKGROUND

Florbetapir (AV45) and fluorodeoxyglucose (FDG) PET imaging are valuable techniques to detect the amyloid-β (Aβ) load and brain glucose metabolism in patients with Alzheimer's disease (AD).

OBJECTIVE

The purpose of this study is to access the characteristics of Aβ load and FDG metabolism in brain for further investigating their relationships with cognitive impairment in AD patients.

METHODS

Twenty-seven patients with AD (average 70.6 years old, N = 13 male, N = 14 female) were enrolled in this study. These AD patients underwent the standard clinical assessment and received detailed imaging examinations of the nervous system by using Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MOCA), 18F-AV45, and 18F-FDG PET scans.

RESULTS

Of 27 AD patients, 22 patients (81.5%) showed significantly increases in Aβ load and 26 patients (96.3%) had significantly reductions in FDG metabolism. The moderate AD patients had more brain areas of reduced FDG metabolism and more severe reductions in some regions compared to mild AD patients, with no differences in Aβ load observed. Moreover, the range and degree of reduced FDG metabolism in several regions were positively correlated with the total score of MMSE or MOCA, whereas the range of Aβ load did not. No correlation was found between the range of Aβ load and the range of reduced FDG metabolism in this study.

CONCLUSION

The reduction in FDG metabolisms captured by 18F-FDG imaging can be used as a potential biomarker for AD diagnosis in the future. 18F-AV45 imaging did not present valuable evidence for evaluating AD patient in this study.

Blinded Clinical Evaluation for Dementia of Alzheimer's Type Classification Using FDG-PET: A Comparison Between Feature-Engineered and Non-Feature-Engineered Machine Learning Methods

BACKGROUND

Advanced machine learning methods can aid in the identification of dementia risk using neuroimaging-derived features including FDG-PET. However, to enable the translation of these methods and test their usefulness in clinical practice, it is crucial to conduct independent validation on real clinical samples, which has yet to be properly delineated in the current literature.

OBJECTIVE

In this paper, we present our efforts to enable such clinical translational through the evaluation and comparison of two machine-learning methods for discrimination between dementia of Alzheimer's type (DAT) and Non-DAT controls.

METHODS

FDG-PET-based dementia scores were generated on an independent clinical sample whose clinical diagnosis was blinded to the algorithm designers. A feature-engineered approach (multi-kernel probability classifier) and a non-feature-engineered approach (3D convolutional neural network) were analyzed. Both classifiers were pre-trained on cognitively normal subjects as well as subjects with DAT. These two methods provided a probabilistic dementia score for this previously unseen clinical data. Performance of the algorithms were compared against ground-truth dementia rating assessed by experienced nuclear physicians.

RESULTS

Blinded clinical evaluation on both classifiers showed good separation between the cognitively normal subjects and the patients diagnosed with DAT. The non-feature-engineered dementia score showed higher sensitivity among subjects whose diagnosis was in agreement between the machine-learning models, while the feature-engineered approach showed higher specificity in non-consensus cases.

CONCLUSION

In this study, we demonstrated blinded evaluation using data from an independent clinical sample for assessing the performance in DAT classification models in a clinical setting. Our results showed good generalizability for two machine-learning approaches, marking an important step for the translation of pre-trained machine-learning models into clinical practice.

Construction of MRI-Based Alzheimer's Disease Score Based on Efficient 3D Convolutional Neural Network: Comprehensive Validation on 7,902 Images from a Multi-Center Dataset

BACKGROUND

In recent years, many convolutional neural networks (CNN) have been proposed for the classification of Alzheimer's disease. Due to memory constraints, many of the proposed CNNs work at a 2D slice-level or 3D patch-level.

OBJECTIVE

Here, we propose a subject-level 3D CNN that can extract the neurodegenerative patterns of the whole brain MRI and converted into a probabilistic Dementia score.

METHODS

We propose an efficient and lightweight subject-level 3D CNN featuring dilated convolutions. We trained our network on the ADNI data on stable Dementia of the Alzheimer's type (sDAT) from stable normal controls (sNC). To comprehensively evaluate the generalizability of our proposed network, we performed four independent tests which includes testing on images from other ADNI individuals at various stages of the dementia, images acquired from other sites (AIBL), images acquired using different protocols (OASIS), and longitudinal images acquired over a short period of time (MIRIAD).

RESULTS

We achieved a 5-fold cross-validated balanced accuracy of 88%in differentiating sDAT from sNC, and an overall specificity of 79.5%and sensitivity 79.7%on the entire set of 7,902 independent test images.

CONCLUSION

Independent testing is essential for estimating the generalization ability of the network to unseen data, but is often lacking in studies using CNN for DAT classification. This makes it difficult to compare the performances achieved using different architectures. Our comprehensive evaluation highlighting the competitive performance of our network and potential promise for generalization.

Positron Emission Tomography (PET) and Neuroimaging in the Personalized Approach to Neurodegenerative Causes of Dementia

Generally, dementia should be considered an acquired syndrome, with multiple possible causes, rather than a specific disease in itself. The leading causes of dementia are neurodegenerative and non-neurodegenerative alterations. Nevertheless, the neurodegenerative group of diseases that lead to cognitive impairment and dementia includes multiple possibilities or mixed pathologies with personalized treatment management for each cause, even if Alzheimer's disease is the most common pathology. Therefore, an accurate differential diagnosis is mandatory in order to select the most appropriate therapy approach. The role of personalized assessment in the treatment of dementia is rapidly growing. Neuroimaging is an essential tool for differential diagnosis of multiple causes of dementia and allows a personalized diagnostic and therapeutic protocol based on risk factors that may improve treatment management, especially in early diagnosis during the prodromal stage. The utility of structural and functional imaging could be increased by standardization of acquisition and analysis methods and by the development of algorithms for automated assessment. The aim of this review is to focus on the most commonly used tracers for differential diagnosis in the dementia field. Particularly, we aim to explore ¹⁸F Fluorodeoxyglucose (FDG) and amyloid positron emission tomography (PET) imaging in Alzheimer's disease and in other neurodegenerative causes of dementia.

Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases

Biomarkers for dementia of Alzheimer's type (DAT) are sought to facilitate accurate prediction of the disease onset, ideally predating the onset of cognitive deterioration. T1-weighted magnetic resonance imaging (MRI) is a commonly used neuroimaging modality for measuring brain structure in vivo, potentially providing information enabling the design of biomarkers for DAT. We propose a novel biomarker using structural MRI volume-based features to compute a similarity score for the individual's structural patterns relative to those observed in the DAT group. We employed ensemble-learning framework that combines structural features in most discriminative ROIs to create an aggregate measure of neurodegeneration in the brain. This classifier is trained on 423 stable normal control (NC) and 330 DAT subjects, where clinical diagnosis is likely to have the highest certainty. Independent validation on 8,834 unseen images from ADNI, AIBL, OASIS, and MIRIAD Alzheimer's disease (AD) databases showed promising potential to predict the development of DAT depending on the time-to-conversion (TTC). Classification performance on stable versus progressive mild cognitive impairment (MCI) groups achieved an AUC of 0.81 for TTC of 6 months and 0.73 for TTC of up to 7 years, achieving state-of-the-art results. The output score, indicating similarity to patterns seen in DAT, provides an intuitive measure of how closely the individual's brain features resemble the DAT group. This score can be used for assessing the presence of AD structural atrophy patterns in normal aging and MCI stages, as well as monitoring the progression of the individual's brain along with the disease course.

Creation of an anthropomorphic CT head phantom for verification of image segmentation

Purpose

Many methods are available to segment structural magnetic resonance (MR) images of the brain into different tissue types. These have generally been developed for research purposes but there is some clinical use in the diagnosis of neurodegenerative diseases such as dementia. The potential exists for computed tomography (CT) segmentation to be used in place of MRI segmentation, but this will require a method to verify the accuracy of CT processing, particularly if algorithms developed for MR are used, as MR has notably greater tissue contrast.

Methods

To investigate these issues we have created a three‐dimensional (3D) printed brain with realistic Hounsfield unit (HU) values based on tissue maps segmented directly from an individual T1 MRI scan of a normal subject. Several T1 MRI scans of normal subjects from the ADNI database were segmented using SPM12 and used to create stereolithography files of different tissues for 3D printing. The attenuation properties of several material blends were investigated, and three suitable formulations were used to print an object expected to have realistic geometry and attenuation properties. A skull was simulated by coating the object with plaster of Paris impregnated bandages. Using two CT scanners, the realism of the phantom was assessed by the measurement of HU values, SPM12 segmentation and comparison with the source data used to create the phantom.

Results

Realistic relative HU values were measured although a subtraction of 60 was required to obtain equivalence with the expected values (gray matter 32.9–35.8 phantom, 29.9–34.2 literature). Segmentation of images acquired at different kVps/mAs showed excellent agreement with the source data (Dice Similarity Coefficient 0.79 for gray matter). The performance of two scanners with two segmentation methods was compared, with the scanners found to have similar performance and with one segmentation method clearly superior to the other.

Conclusion

The ability to use 3D printing to create a realistic (in terms of geometry and attenuation properties) head phantom has been demonstrated and used in an initial assessment of CT segmentation accuracy using freely available software developed for MRI.

Quantifying brain metabolism from FDG-PET images into a probability of Alzheimer's dementia score

18 F-fluorodeoxyglucose positron emission tomography (FDG-PET) enables in-vivo capture of the topographic metabolism patterns in the brain. These images have shown great promise in revealing the altered metabolism patterns in Alzheimer's disease (AD). The AD pathology is progressive, and leads to structural and functional alterations that lie on a continuum. There is a need to quantify the altered metabolism patterns that exist on a continuum into a simple measure. This work proposes a 3D convolutional neural network with residual connections that generates a probability score useful for interpreting the FDG-PET images along the continuum of AD. This network is trained and tested on images of stable normal control and stable Dementia of the Alzheimer's type (sDAT) subjects, achieving an AUC of 0.976 via repeated fivefold cross-validation. An independent test set consisting of images in between the two extreme ends of the DAT spectrum is used to further test the generalization performance of the network. Classification performance of 0.811 AUC is achieved in the task of predicting conversion of mild cognitive impairment to DAT for conversion time of 0-3 years. The saliency and class activation maps, which highlight the regions of the brain that are most important to the classification task, implicate many known regions affected by DAT including the posterior cingulate cortex, precuneus, and hippocampus.

Grant Report on PREDICT-ADFTD: Multimodal Imaging Prediction of AD/FTD and Differential Diagnosis

We report on the ongoing project "PREDICT-ADFTD: Multimodal Imaging Prediction of AD/FTD and Differential Diagnosis" describing completed and future work supported by this grant. This project is a multi-site, multi-study collaboration effort with research spanning seven sites across the US and Canada. The overall goal of the project is to study neurodegeneration within Alzheimer's Disease, Frontotemporal Dementia, and related neurodegenerative disorders, using a variety of brain imaging and computational techniques to develop methods for the early and accurate prediction of disease and its course. The overarching goal of the project is to develop the earliest and most accurate biomarker that can differentiate clinical diagnoses to inform clinical trials and patient care. In its third year, this project has already completed several projects to achieve this goal, focusing on (1) structural MRI (2) machine learning and (3) FDG-PET and multimodal imaging. Studies utilizing structural MRI have identified key features of underlying pathology by studying hippocampal deformation that is unique to clinical diagnosis and also post-mortem confirmed neuropathology. Several machine learning experiments have shown high classification accuracy in the prediction of disease based on Convolutional Neural Networks utilizing MRI images as input. In addition, we have also achieved high accuracy in predicting conversion to DAT up to five years in the future. Further, we evaluated multimodal models that combine structural and FDG-PET imaging, in order to compare the predictive power of multimodal to unimodal models. Studies utilizing FDG-PET have shown significant predictive ability in the prediction and progression of disease.

Diffusion MRI Indices and Their Relation to Cognitive Impairment in Brain Aging: The Updated Multi-protocol Approach in ADNI3

Brain imaging with diffusion-weighted MRI (dMRI) is sensitive to microstructural white matter (WM) changes associated with brain aging and neurodegeneration. In its third phase, the Alzheimer's Disease Neuroimaging Initiative (ADNI3) is collecting data across multiple sites and scanners using different dMRI acquisition protocols, to better understand disease effects. It is vital to understand when data can be pooled across scanners, and how the choice of dMRI protocol affects the sensitivity of extracted measures to differences in clinical impairment. Here, we analyzed ADNI3 data from 317 participants (mean age: 75.4 ± 7.9 years; 143 men/174 women), who were each scanned at one of 47 sites with one of six dMRI protocols using scanners from three different manufacturers. We computed four standard diffusion tensor imaging (DTI) indices including fractional anisotropy (FA^DTI) and mean, radial, and axial diffusivity, and one FA index based on the tensor distribution function (FA^TDF), in 24 bilaterally averaged WM regions of interest. We found that protocol differences significantly affected dMRI indices, in particular FA^DTI. We ranked the diffusion indices for their strength of association with four clinical assessments. In addition to diagnosis, we evaluated cognitive impairment as indexed by three commonly used screening tools for detecting dementia and AD: the AD Assessment Scale (ADAS-cog), the Mini-Mental State Examination (MMSE), and the Clinical Dementia Rating scale sum-of-boxes (CDR-sob). Using a nested random-effects regression model to account for protocol and site, we found that across all dMRI indices and clinical measures, the hippocampal-cingulum and fornix (crus)/stria terminalis regions most consistently showed strong associations with clinical impairment. Overall, the greatest effect sizes were detected in the hippocampal-cingulum (CGH) and uncinate fasciculus (UNC) for associations between axial or mean diffusivity and CDR-sob. FA^TDF detected robust widespread associations with clinical measures, while FA^DTI was the weakest of the five indices for detecting associations. Ultimately, we were able to successfully pool dMRI data from multiple acquisition protocols from ADNI3 and detect consistent and robust associations with clinical impairment and age.

A Computer Aided Diagnosis System for Identifying Alzheimer's from MRI Scan using Improved Adaboost

The recent studies in Morphometric Magnetic Resonance Imaging (MRI) have investigated the abnormalities in the brain volume that have been associated diagnosing of the Alzheimer's Disease (AD) by making use of the Voxel-Based Morphometry (VBM). The system permits the evaluation of the volumes of grey matter in subjects such as the AD or the conditions related to it and are compared in an automated manner with the healthy controls in the entire brain. The article also reviews the findings of the VBM that are related to various stages of the AD and also its prodrome known as the Mild Cognitive Impairment (MCI). For this work, the Ada Boost classifier has been proposed to be a good selector of feature that brings down the classification error's upper bound. A Principal Component Analysis (PCA) had been employed for the dimensionality reduction and for improving efficiency. The PCA is a powerful, as well as a reliable, tool in data analysis. Calculating fitness scores will be an independent process. For this reason, the Genetic Algorithm (GA) along with a greedy search may be computed easily along with some high-performance systems of computing. The primary goal of this work was to identify better collections or permutations of the classifiers that are weak to build stronger ones. The results of the experiment prove that the GAs is one more alternative technique used for boosting the permutation of weak classifiers identified in Ada Boost which can produce some better solutions compared to the classical Ada Boost.

Role of GTPases in the Regulation of Mitochondrial Dynamics in Alzheimer's Disease and CNS-Related Disorders

Data obtained from several studies have shown that mitochondria are involved and play a central role in the progression of several distinct pathological conditions. Morphological alterations and disruptions on the functionality of mitochondria may be related to metabolic and energy deficiency in neurons in a neurodegenerative disorder. Several recent studies demonstrate the linkage between neurodegeneration and mitochondrial dynamics in the spectrum of a promising era called precision mitochondrial medicine. In this review paper, an analysis of the correlation between mitochondria, Alzheimer's disease, and other central nervous system (CNS)-related disorders like the Parkinson's disease and the autism spectrum disorder is under discussion. The role of GTPases like the mfn1, mfn2, opa1, and dlp1 in mitochondrial fission and fusion is also under investigation, influencing mitochondrial population and leading to oxidative stress and neuronal damage.

Quantum Chemistry Meets Deep Learning for Complex Carbohydrate and Glycopeptide Species I

Carbohydrate complexes are crucial in many various biological and medicinal processes. The impacts of N-acetyl on the glycosidic linkage flexibility of methyl β-D-glucopyranose, and of the glycoamino acid β-D-glucopyranose-asparagine are poorly understood at the electronic level. Furthermore, the effect of D- and L-isomers of asparagine in the complexes of N-acetyl-β-D-glucopyranose-(L)-asparagine and N-acetyl-β-D-glucopyranose-(D)-asparagine is unknown. In this study, we performed density functional theory calculations of methyl β-D-glucopyranose, methyl N-acetyl-β-D-glucopyranose, and of glycoamino acids β-D-glucopyranose-asparagine, N-acetyl-β-D-glucopyranose-(L)-asparagine and N-acetyl-β-D-glucopyranose-(D)-asparagine for studying their linkage flexibilities, total solvated energies, thermochemical properties and intra-molecular hydrogen bond formations in an aqueous solution environment using the COnductor-like Screening MOdel (COSMO) for water. We linked these density functional theory calculations to deep learning via estimating the total solvated energy of each linkage torsional angle value. Our results show that deep learning methods accurately estimate the total solvated energies of complex carbohydrate and glycopeptide species and provide linkage flexibility trends for methyl β-D-glucopyranose, methyl N-acetyl-β-D-glucopyranose, and of glycoamino acids β-D-glucopyranose-asparagine, N-acetyl-β-D-glucopyranose-(L)-asparagine and N-acetyl-β-D-glucopyranose-(D)-asparagine in agreement with density functional theory results. To the best of our knowledge, this study represents the first application of density functional theory along with deep learning for complex carbohydrate and glycopeptide species in an aqueous solution medium. In addition, this study shows that a few thousands of optimization frames from DFT calculations are enough for accurate estimations by deep learning tools.