Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer's disease

Improving Alzheimer's Disease Classification in Brain MRI Images Using a Neural Network Model Enhanced with PCA and SWLDA

The examination of Alzheimer's disease (AD) using adaptive machine learning algorithms has unveiled promising findings. However, achieving substantial credibility in medical contexts necessitates a combination of notable accuracy, minimal processing time, and universality across diverse populations. Therefore, we have formulated a hybrid methodology in this study to classify AD by employing a brain MRI image dataset. We incorporated an averaging filter during preprocessing in the initial stage to reduce extraneous details. Subsequently, a combined strategy was utilized, involving principal component analysis (PCA) in conjunction with stepwise linear discriminant analysis (SWLDA), followed by an artificial neural network (ANN). SWLDA employs a combination of forward and backward recursion methods to choose a restricted set of features. The forward recursion identifies the most interconnected features based on partial Z-test values. Conversely, the backward recursion method eliminates the least correlated features from the same feature space. After the extraction and selection of features, an optimized artificial neural network (ANN) was utilized to differentiate the various classes of AD. To demonstrate the significance of this hybrid approach, we utilized publicly available brain MRI datasets using a 10-fold cross-validation strategy. The proposed method excelled over existing state-of-the-art systems, attaining weighted average recognition rates of 99.35% and 96.66%, respectively, across all the datasets.

Integration- and separation-aware adversarial model for cerebrovascular segmentation from TOF-MRA

PURPOSE

Cerebrovascular segmentation from time-of-flight magnetic resonance angiography (TOF-MRA) is important but challenging for the simulation and measurement of cerebrovascular diseases. Recently, deep learning has promoted the rapid development of cerebrovascular segmentation. However, model optimization relies on voxel or regional punishment and lacks global awareness and interpretation from the texture and edge. To overcome the limitations of the existing methods, we propose a new cerebrovascular segmentation method to obtain more refined structures.

METHODS

In this paper, we propose a new adversarial model that achieves segmentation using segmentation model and filters the results using discriminator. Considering the sample imbalance in cerebrovascular imaging, we separated the TOF-MRA images and utilized high- and low-frequency images to enhance the texture and edge representation. The encoder weight sharing from the segmentation model not only saves the model parameters, but also strengthens the integration and separation correlation. Diversified discrimination enhances the robustness and regularization of the model.

RESULTS

The adversarial model was tested using two cerebrovascular datasets. It scored 82.26% and 73.38%, respectively, ranking first on both datasets. The results show that our method not only outperforms the recent cerebrovascular segmentation model, but also surpasses the common adversarial models.

CONCLUSION

Our adversarial model focuses on improving the extraction ability of the model on texture and edge, thereby achieving awareness of the global cerebrovascular topology. Therefore, we obtained an accurate and robust cerebrovascular segmentation. This framework has potential applications in many imaging fields, particularly in the application of sample imbalance. Our code is available at the website https://github.com/MontaEllis/ISA-model.

Deep Multi-Modal Discriminative and Interpretability Network for Alzheimer's Disease Diagnosis

Multi-modal fusion has become an important data analysis technology in Alzheimer's disease (AD) diagnosis, which is committed to effectively extract and utilize complementary information among different modalities. However, most of the existing fusion methods focus on pursuing common feature representation by transformation, and ignore discriminative structural information among samples. In addition, most fusion methods use high-order feature extraction, such as deep neural network, by which it is difficult to identify biomarkers. In this paper, we propose a novel method named deep multi-modal discriminative and interpretability network (DMDIN), which aligns samples in a discriminative common space and provides a new approach to identify significant brain regions (ROIs) in AD diagnosis. Specifically, we reconstruct each modality with a hierarchical representation through multilayer perceptron (MLP), and take advantage of the shared self-expression coefficients constrained by diagonal blocks to embed the structural information of inter-class and the intra-class. Further, the generalized canonical correlation analysis (GCCA) is adopted as a correlation constraint to generate a discriminative common space, in which samples of the same category gather while samples of different categories stay away. Finally, in order to enhance the interpretability of the deep learning model, we utilize knowledge distillation to reproduce coordinated representations and capture influence of brain regions in AD classification. Experiments show that the proposed method performs better than several state-of-the-art methods in AD diagnosis.

Challenges and opportunities of diagnostic markers of Alzheimer's disease based on structural magnetic resonance imaging

OBJECTIVES

This article aimed to carry out a narrative literature review of early diagnostic markers of Alzheimer's disease (AD) based on both micro and macro levels of pathology, indicating the shortcomings of current biomarkers and proposing a novel biomarker of structural integrity that associates the hippocampus and adjacent ventricle together. This could help to reduce the influence of individual variety and improve the accuracy and validity of structural biomarker.

METHODS

This review was based on presenting comprehensive background of early diagnostic markers of AD. We have compiled those markers into micro level and macro level, and discussed the advantages and disadvantages of them. Eventually the ratio of gray matter volume to ventricle volume was put forward.

RESULTS

The costly methodologies and related high patient burden of "micro" biomarkers (cerebrospinal fluid biomarkers) hinder the implementation in routine clinical examination. In terms of "macro" biomarkers- hippocampal volume (HV), there is a large variation of it among population, which undermines its validity Considering the gray matter atrophies while the adjacent ventricular volume enlarges, we assume the hippocampal to ventricle ratio (HVR) is a more reliable marker than HV alone the emerging evidence showed hippocampal to ventricle ratio predicts memory functions better than HV alone in elderly sample.

CONCLUSIONS

The ratio between gray matter structures and adjacent ventricular volumes counts as a promising superior diagnostic marker of early neurodegeneration.

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

Background

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

Objective

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

Material and Methods

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

Results

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

Conclusion

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

Self-supervised learning of neighborhood embedding for longitudinal MRI

In recent years, several deep learning models recommend first to represent Magnetic Resonance Imaging (MRI) as latent features before performing a downstream task of interest (such as classification or regression). The performance of the downstream task generally improves when these latent representations are explicitly associated with factors of interest. For example, we derived such a representation for capturing brain aging by applying self-supervised learning to longitudinal MRIs and then used the resulting encoding to automatically identify diseases accelerating the aging of the brain. We now propose a refinement of this representation by replacing the linear modeling of brain aging with one that is consistent in local neighborhoods in the latent space. Called Longitudinal Neighborhood Embedding (LNE), we derive an encoding so that neighborhoods are age-consistent (i.e., brain MRIs of different subjects with similar brain ages are in close proximity of each other) and progression-consistent, i.e., the latent space is defined by a smooth trajectory field where each trajectory captures changes in brain ages between a pair of MRIs extracted from a longitudinal sequence. To make the problem computationally tractable, we further propose a strategy for mini-batch sampling so that the resulting local neighborhoods accurately approximate the ones that would be defined based on the whole cohort. We evaluate LNE on three different downstream tasks: (1) to predict chronological age from T1-w MRI of 274 healthy subjects participating in a study at SRI International; (2) to distinguish Normal Control (NC) from Alzheimer's Disease (AD) and stable Mild Cognitive Impairment (sMCI) from progressive Mild Cognitive Impairment (pMCI) based on T1-w MRI of 632 participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI); and (3) to distinguish no-to-low from moderate-to-heavy alcohol drinkers based on fractional anisotropy derived from diffusion tensor MRIs of 764 adolescents recruited by the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). Across the three data sets, the visualization of the smooth trajectory vector fields and superior accuracy on downstream tasks demonstrate the strength of the proposed method over existing self-supervised methods in extracting information related to brain aging, which could help study the impact of substance use and neurodegenerative disorders. The code is available at https://github.com/ouyangjiahong/longitudinal-neighbourhood-embedding.

Development of a deep learning network for Alzheimer’s disease classification with evaluation of imaging modality and longitudinal data

Objective. Neuroimaging uncovers important information about disease in the brain. Yet in Alzheimer’s disease (AD), there remains a clear clinical need for reliable tools to extract diagnoses from neuroimages. Significant work has been done to develop deep learning (DL) networks using neuroimaging for AD diagnosis. However, no particular model has emerged as optimal. Due to a lack of direct comparisons and evaluations on independent data, there is no consensus on which modality is best for diagnostic models or whether longitudinal information enhances performance. The purpose of this work was (1) to develop a generalizable DL model to distinguish neuroimaging scans of AD patients from controls and (2) to evaluate the influence of imaging modality and longitudinal data on performance. Approach. We trained a 2-class convolutional neural network (CNN) with and without a cascaded recurrent neural network (RNN). We used datasets of 772 (N AD = 364, N control = 408) 3D 18F-FDG PET scans and 780 (N AD = 280, N control = 500) T1-weighted volumetric-3D MR images (containing 131 and 144 patients with multiple timepoints) from the Alzheimer’s Disease Neuroimaging Initiative, plus an independent set of 104 (N AD = 63, N NC = 41) 18F-FDG PET scans (one per patient) for validation. Main Results. ROC analysis showed that PET-trained models outperformed MRI-trained, achieving maximum AUC with the CNN + RNN model of 0.93 ± 0.08, with accuracy 82.5 ± 8.9%. Adding longitudinal information offered significant improvement to performance on 18F-FDG PET, but not on T1-MRI. CNN model validation with an independent 18F-FDG PET dataset achieved AUC of 0.99. Layer-wise relevance propagation heatmaps added CNN interpretability. Significance. The development of a high-performing tool for AD diagnosis, with the direct evaluation of key influences, reveals the advantage of using 18F-FDG PET and longitudinal data over MRI and single timepoint analysis. This has significant implications for the potential of neuroimaging for future research on AD diagnosis and clinical management of suspected AD patients.

Disentangling Normal Aging From Severity of Disease via Weak Supervision on Longitudinal MRI

The continuous progression of neurological diseases are often categorized into conditions according to their severity. To relate the severity to changes in brain morphometry, there is a growing interest in replacing these categories with a continuous severity scale that longitudinal MRIs are mapped onto via deep learning algorithms. However, existing methods based on supervised learning require large numbers of samples and those that do not, such as self-supervised models, fail to clearly separate the disease effect from normal aging. Here, we propose to explicitly disentangle those two factors via weak-supervision. In other words, training is based on longitudinal MRIs being labelled either normal or diseased so that the training data can be augmented with samples from disease categories that are not of primary interest to the analysis. We do so by encouraging trajectories of controls to be fully encoded by the direction associated with brain aging. Furthermore, an orthogonal direction linked to disease severity captures the residual component from normal aging in the diseased cohort. Hence, the proposed method quantifies disease severity and its progression speed in individuals without knowing their condition. We apply the proposed method on data from the Alzheimer's Disease Neuroimaging Initiative (ADNI, N =632 ). We then show that the model properly disentangled normal aging from the severity of cognitive impairment by plotting the resulting disentangled factors of each subject and generating simulated MRIs for a given chronological age and condition. Moreover, our representation obtains higher balanced accuracy when used for two downstream classification tasks compared to other pre-training approaches. The code for our weak-supervised approach is available at https://github.com/ouyangjiahong/longitudinal-direction-disentangle.

Use of machine learning to identify functional connectivity changes in a clinical cohort of patients at risk for dementia

Objective

Progressive conditions characterized by cognitive decline, including mild cognitive impairment (MCI) and subjective cognitive decline (SCD) are clinical conditions representing a major risk factor to develop dementia, however, the diagnosis of these pre-dementia conditions remains a challenge given the heterogeneity in clinical trajectories. Earlier diagnosis requires data-driven approaches for improved and targeted treatment modalities.

Methods

Neuropsychological tests, baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI (rsfMRI), and diffusion weighted scans were obtained from 35 patients with SCD, 19 with MCI, and 36 age-matched healthy controls (HC). A recently developed machine learning technique, Hollow Tree Super (HoTS) was utilized to classify subjects into diagnostic categories based on their FC, and derive network and parcel-based FC features contributing to each model. The same approach was used to identify features associated with performance in a range of neuropsychological tests. We concluded our analysis by looking at changes in PageRank centrality (a measure of node hubness) between the diagnostic groups.

Results

Subjects were classified into diagnostic categories with a high area under the receiver operating characteristic curve (AUC-ROC), ranging from 0.73 to 0.84. The language networks were most notably associated with classification. Several central networks and sensory brain regions were predictors of poor performance in neuropsychological tests, suggesting maladaptive compensation. PageRank analysis highlighted that basal and limbic deep brain region, along with the frontal operculum demonstrated a reduction in centrality in both SCD and MCI patients compared to controls.

Conclusion

Our methods highlight the potential to explore the underlying neural networks contributing to the cognitive changes and neuroplastic responses in prodromal dementia.

Discriminating Aging Cognitive Decline Spectrum Using PET and Magnetic Resonance Image Features

Background: The population aging increased the prevalence of brain diseases, like Alzheimer’s disease (AD), and early identification of individuals with higher odds of cognitive decline is essential to maintain quality of life. Imaging evaluation of individuals at risk of cognitive decline includes biomarkers extracted from brain positron emission tomography (PET) and structural magnetic resonance imaging (MRI). Objective: We propose investigating ensemble models to classify groups in the aging cognitive decline spectrum by combining features extracted from single imaging modalities and combinations of imaging modalities (FDG+AMY+MRI, and a PET ensemble). Methods: We group imaging data of 131 individuals into four classes related to the individuals’ cognitive assessment in baseline and follow-up: stable cognitive non-impaired; individuals converting to mild cognitive impairment (MCI) syndrome; stable MCI; and Alzheimer’s clinical syndrome. We assess the performance of four algorithms using leave-one-out cross-validation: decision tree classifier, random forest (RF), light gradient boosting machine (LGBM), and categorical boosting (CAT). The performance analysis of models is evaluated using balanced accuracy before and after using Shapley Additive exPlanations with recursive feature elimination (SHAP-RFECV) method. Results: Our results show that feature selection with CAT or RF algorithms have the best overall performance in discriminating early cognitive decline spectrum mainly using MRI imaging features. Conclusion: Use of CAT or RF algorithms with SHAP-RFECV shows good discrimination of early stages of aging cognitive decline, mainly using MRI image features. Further work is required to analyze the impact of selected brain regions and their correlation with cognitive decline spectrum.

Multi-scale discriminative regions analysis in FDG-PET imaging for early diagnosis of Alzheimer's disease

OBJECTIVE

Alzheimer's disease (AD) is a degenerative brain disorder, one of the main causes of death in elderly people, so early diagnosis of AD is vital to prompt access to medication and medical care. Fluorodeoxyglucose positron emission tomography (FDG-PET) proves to be effective to help understand neurological changes via measuring glucose uptake. Our aim is to explore information-rich regions of FDG-PET imaging, which enhance the accuracy and interpretability of AD-related diagnosis.

APPROACH

We develop a novel method for early diagnosis of AD based on multi-scale discriminative regions in FDG-PET imaging, which considers the diagnosis interpretability. Specifically, a multi-scale region localization (MSRL) module is discussed to automatically identify disease-related discriminative regions in full-volume FDG-PET images in an unsupervised manner, upon which a confidence score is designed to evaluate the prioritization of regions according to the density distribution of anomalies. Then, the proposed multi-scale region classification (MSRC) module adaptively fuses multi-scale region representations and makes decision fusion, which not only reduces useless information but also offers complementary information. Most of previous methods concentrate on discriminating AD from cognitively normal (CN), while mild cognitive impairment (MCI), a transitional state, facilitates early diagnosis. Therefore, our method is further applied to multiple AD-related diagnosis tasks, not limited to AD vs. CN.

MAIN RESULTS

Experimental results on the ADNI dataset show that the proposed method achieves superior performance over state-of-the-art FDG-PET-based approaches. Besides, some cerebral cortices highlighted by extracted regions cohere with medical research, further demonstrating the superiority.

SIGNIFICANCE

This work offers an effective method to achieve AD diagnosis and detect disease-affected regions in FDG-PET imaging. Our results could be beneficial for providing an additional opinion on the clinical diagnosis.

Deep Learning-Based Diagnosis of Alzheimer’s Disease

Alzheimer’s disease (AD), the most familiar type of dementia, is a severe concern in modern healthcare. Around 5.5 million people aged 65 and above have AD, and it is the sixth leading cause of mortality in the US. AD is an irreversible, degenerative brain disorder characterized by a loss of cognitive function and has no proven cure. Deep learning techniques have gained popularity in recent years, particularly in the domains of natural language processing and computer vision. Since 2014, these techniques have begun to achieve substantial consideration in AD diagnosis research, and the number of papers published in this arena is rising drastically. Deep learning techniques have been reported to be more accurate for AD diagnosis in comparison to conventional machine learning models. Motivated to explore the potential of deep learning in AD diagnosis, this study reviews the current state-of-the-art in AD diagnosis using deep learning. We summarize the most recent trends and findings using a thorough literature review. The study also explores the different biomarkers and datasets for AD diagnosis. Even though deep learning has shown promise in AD diagnosis, there are still several challenges that need to be addressed.

Extracting ROI-Based Contourlet Subband Energy Feature From the sMRI Image for Alzheimer's Disease Classification

Structural magnetic resonance imaging (sMRI)-based Alzheimer's disease (AD) classification and its prodromal stage-mild cognitive impairment (MCI) classification have attracted many attentions and been widely investigated in recent years. Owing to the high dimensionality, representation of the sMRI image becomes a difficult issue in AD classification. Furthermore, regions of interest (ROI) reflected in the sMRI image are not characterized properly by spatial analysis techniques, which has been a main cause of weakening the discriminating ability of the extracted spatial feature. In this study, we propose a ROI-based contourlet subband energy (ROICSE) feature to represent the sMRI image in the frequency domain for AD classification. Specifically, a preprocessed sMRI image is first segmented into 90 ROIs by a constructed brain mask. Instead of extracting features from the 90 ROIs in the spatial domain, the contourlet transform is performed on each of these ROIs to obtain their energy subbands. And then for an ROI, a subband energy (SE) feature vector is constructed to capture its energy distribution and contour information. Afterwards, SE feature vectors of the 90 ROIs are concatenated to form a ROICSE feature of the sMRI image. Finally, support vector machine (SVM) classifier is used to classify 880 subjects from ADNI and OASIS databases. Experimental results show that the ROICSE approach outperforms six other state-of-the-art methods, demonstrating that energy and contour information of the ROI are important to capture differences between the sMRI images of AD and HC subjects. Meanwhile, brain regions related to AD can also be found using the ROICSE feature, indicating that the ROICSE feature can be a promising assistant imaging marker for the AD diagnosis via the sMRI image. Code and Sample IDs of this paper can be downloaded at https://github.com/NWPU-903PR/ROICSE.git.

Longitudinal surface-based spatial Bayesian GLM reveals complex trajectories of motor neurodegeneration in ALS

Longitudinal fMRI studies hold great promise for the study of neurodegenerative diseases, development and aging, but realizing their full potential depends on extracting accurate fMRI-based measures of brain function and organization in individual subjects over time. This is especially true for studies of rare, heterogeneous and/or rapidly progressing neurodegenerative diseases. These often involve small samples with heterogeneous functional features, making traditional group-difference analyses of limited utility. One such disease is amyotrophic lateral sclerosis (ALS), a severe disease resulting in extreme loss of motor function and eventual death. Here, we use an advanced individualized task fMRI analysis approach to analyze a rich longitudinal dataset containing 190 hand clench fMRI scans from 16 ALS patients (78 scans) and 22 age-matched healthy controls (112 scans) Specifically, we adopt our cortical surface-based spatial Bayesian general linear model (GLM), which has high power and precision to detect activations in individual subjects, and propose a novel longitudinal extension to leverage information shared across visits. We perform all analyses in native surface space to preserve individua anatomical and functional features. Using mixed-effects models to subsequently study the relationship between size of activation and ALS disease progression, we observe for the first time an inverted U-shaped trajectory o motor activations: at relatively mild motor disability we observe enlarging activations, while at higher levels of motor disability we observe severely diminished activation, reflecting progression toward complete loss of motor function. We further observe distinct trajectories depending on clinical progression rate, with faster progressors exhibiting more extreme changes at an earlier stage of disability. These differential trajectories suggest that initial hyper-activation is likely attributable to loss of inhibitory neurons, rather than functional compensation as earlier assumed. These findings substantially advance scientific understanding of the ALS disease process. This study also provides the first real-world example of how surface-based spatial Bayesian analysis of task fMRI can further scientific understanding of neurodegenerative disease and other phenomena. The surface-based spatial Bayesian GLM is implemented in the BayesfMRI R package

Searching for optimal machine learning model to classify mild cognitive impairment (MCI) subtypes using multimodal MRI data

The intervention at the stage of mild cognitive impairment (MCI) is promising for preventing Alzheimer's disease (AD). This study aims to search for the optimal machine learning (ML) model to classify early and late MCI (EMCI and LMCI) subtypes using multimodal MRI data. First, the tract-based spatial statistics (TBSS) analyses showed LMCI-related white matter changes in the Corpus Callosum. The ROI-based tractography addressed the connected cortical areas by affected callosal fibers. We then prepared two feature subsets for ML by measuring resting-state functional connectivity (TBSS-RSFC method) and graph theory metrics (TBSS-Graph method) in these cortical areas, respectively. We also prepared feature subsets of diffusion parameters in the regions of LMCI-related white matter alterations detected by TBSS analyses. Using these feature subsets, we trained and tested multiple ML models for EMCI/LMCI classification with cross-validation. Our results showed the ensemble ML model (AdaBoost) with feature subset of diffusion parameters achieved better performance of mean accuracy 70%. The useful brain regions for classification were those, including frontal, parietal lobe, Corpus Callosum, cingulate regions, insula, and thalamus regions. Our findings indicated the optimal ML model using diffusion parameters might be effective to distinguish LMCI from EMCI subjects at the prodromal stage of AD.

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.

Computer-Aided Diagnosis System for Alzheimer's Disease Using Positron Emission Tomography Images

Alzheimer's disease (AD) is a kind of neurological brain disease. It is an irretrievable, neurodegenerative brain disorder. There are no pills or drugs to cure AD. Therefore, an early diagnosis may help the physician to make accurate analysis and to provide better treatment. With the advent of computational intelligence techniques, machine learning models have made tremendous progress in brain images analysis using MRI, SPECT and PEI. However, accurate analysis of brain scans is an extremely challenging task. The main focus of this paper is to design a Computer Aided Diagnosis (CAD) system using Long-Term Short Memory (LSTM) to improve classification rate and determine suitable attributes that can differentiate AD from Healthy Control (HC) subjects. First, 3D PET images are preprocessed, converted into many groups of 2D images and then grouped into many subsets at certain interval. Subsequently, different features including first order statistical, Gray Level Co-occurrence Matrix and wavelet energy of all sub-bands are extracted from each group, combined and taken as feature vectors. LSTM is designed and employed for classifying PET brain images into HC and AD subjects based on the feature vectors. Finally, the developed system is validated on 18FDG-PET images collected from 188 subjects including 105 HC and 83 AD subjects from ADNI database. Efficacy of the developed CAD system is analyzed using different features. Numerical results revealed that the developed CAD system yields classification accuracy of 98.9% when using combined features, showing outstanding performance.

Longitudinal Pooling & Consistency Regularization to Model Disease Progression From MRIs

Many neurological diseases are characterized by gradual deterioration of brain structure andfunction. Large longitudinal MRI datasets have revealed such deterioration, in part, by applying machine and deep learning to predict diagnosis. A popular approach is to apply Convolutional Neural Networks (CNN) to extract informative features from each visit of the longitudinal MRI and then use those features to classify each visit via Recurrent Neural Networks (RNNs). Such modeling neglects the progressive nature of the disease, which may result in clinically implausible classifications across visits. To avoid this issue, we propose to combine features across visits by coupling feature extraction with a novel longitudinal pooling layer and enforce consistency of the classification across visits in line with disease progression. We evaluate the proposed method on the longitudinal structural MRIs from three neuroimaging datasets: Alzheimer's Disease Neuroimaging Initiative (ADNI, N=404), a dataset composed of 274 normal controls and 329 patients with Alcohol Use Disorder (AUD), and 255 youths from the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). In allthree experiments our method is superior to other widely used approaches for longitudinal classification thus making a unique contribution towards more accurate tracking of the impact of conditions on the brain. The code is available at https://github.com/ouyangjiahong/longitudinal-pooling.

Deep recurrent model for individualized prediction of Alzheimer's disease progression

Alzheimer's disease (AD) is known as one of the major causes of dementia and is characterized by slow progression over several years, with no treatments or available medicines. In this regard, there have been efforts to identify the risk of developing AD in its earliest time. While many of the previous works considered cross-sectional analysis, more recent studies have focused on the diagnosis and prognosis of AD with longitudinal or time series data in a way of disease progression modeling. Under the same problem settings, in this work, we propose a novel computational framework that can predict the phenotypic measurements of MRI biomarkers and trajectories of clinical status along with cognitive scores at multiple future time points. However, in handling time series data, it generally faces many unexpected missing observations. In regard to such an unfavorable situation, we define a secondary problem of estimating those missing values and tackle it in a systematic way by taking account of temporal and multivariate relations inherent in time series data. Concretely, we propose a deep recurrent network that jointly tackles the four problems of (i) missing value imputation, (ii) phenotypic measurements forecasting, (iii) trajectory estimation of a cognitive score, and (iv) clinical status prediction of a subject based on his/her longitudinal imaging biomarkers. Notably, the learnable parameters of all the modules in our predictive models are trained in an end-to-end manner by taking the morphological features and cognitive scores as input, with our circumspectly defined loss function. In our experiments over The Alzheimers Disease Prediction Of Longitudinal Evolution (TADPOLE) challenge cohort, we measured performance for various metrics and compared our method to competing methods in the literature. Exhaustive analyses and ablation studies were also conducted to better confirm the effectiveness of our method.

Anomaly Analysis of Alzheimer’s Disease in PET Images Using an Unsupervised Adversarial Deep Learning Model

In this study, the anomaly analysis of Alzheimer’s disease using positron emission tomography (PET) images using an unsupervised proposed adversarial model is investigated. The model consists of three parts: a parallel-network encoder, which is comprised of a convolutional pipeline and a dilated convolutional pipeline that extracts global and local features and concatenates them, a decoder that reconstructs the input image from the obtained feature vector, and a discriminator that distinguishes if the input image image is real or fake. The hypothesis is that if the proposed model is trained with only normal brain images, the corresponding construction loss for normal images should be minimal. However, if the input image belongs to a class that is designated as an anomaly that which the model is not trained with, then the construction loss will be high. This will reflect during the anomaly score comparison between the normal and the anomalous image. A multi-case analysis is performed for three major classes using the Alzheimer’s Disease Neuroimaging Initiative dataset, Alzheimer’s disease, mild cognitive impairment, and normal control. The base parallel-encoder network shows better classification accuracy than the benchmark models, and the proposed model that is built on the parallel model outperforms the benchmark anomaly detection models. The proposed model gave out 96.03% and 75.21% in classification and area under the curve score, respectively. Additionally, a qualitative evaluation done by using Fréchet inception distance gave a better score than the state-of-the-art by three points.

Diagnosis of Alzheimer's Disease Using Brain Network

Recent studies suggest the brain functional connectivity impairment is the early event occurred in case of Alzheimer’s disease (AD) as well as mild cognitive impairment (MCI). We model the brain as a graph based network to study these impairment. In this paper, we present a new diagnosis approach using graph theory based features from functional magnetic resonance (fMR) images to discriminate AD, MCI, and healthy control (HC) subjects using different classification techniques. These techniques include linear support vector machine (LSVM), and regularized extreme learning machine (RELM). We used pairwise Pearson’s correlation-based functional connectivity to construct the brain network. We compare the classification performance of brain network using Alzheimer’s disease neuroimaging initiative (ADNI) datasets. Node2vec graph embedding approach is employed to convert graph features to feature vectors. Experimental results show that the SVM with LASSO feature selection method generates better classification accuracy compared to other classification technique.

Multi-View Separable Pyramid Network for AD Prediction at MCI Stage by 18F-FDG Brain PET Imaging

Alzheimer's Disease (AD), one of the main causes of death in elderly people, is characterized by Mild Cognitive Impairment (MCI) at prodromal stage. Nevertheless, only part of MCI subjects could progress to AD. The main objective of this paper is thus to identify those who will develop a dementia of AD type among MCI patients. ¹⁸F-FluoroDeoxyGlucose Positron Emission Tomography (¹⁸F-FDG PET) serves as a neuroimaging modality for early diagnosis as it can reflect neural activity via measuring glucose uptake at resting-state. In this paper, we design a deep network on ¹⁸F-FDG PET modality to address the problem of AD identification at early MCI stage. To this end, a Multi-view Separable Pyramid Network (MiSePyNet) is proposed, in which representations are learned from axial, coronal and sagittal views of PET scans so as to offer complementary information and then combined to make a decision jointly. Different from the widely and naturally used 3D convolution operations for 3D images, the proposed architecture is deployed with separable convolution from slice-wise to spatial-wise successively, which can retain the spatial information and reduce training parameters compared to 2D and 3D networks, respectively. Experiments on ADNI dataset show that the proposed method can yield better performance than both traditional and deep learning-based algorithms for predicting the progression of Mild Cognitive Impairment, with a classification accuracy of 83.05%.

Longitudinal analysis of brain structure using existence probability

INTRODUCTION

We propose a method to evaluate quantitatively the longitudinal structural changes in brain atrophy to provide early detection of Alzheimer's disease (AD) and mild cognitive impairment (MCI).

METHODS

We used existence probabilities obtained by segmenting magnetic resonance (MR) images at two different time points into four regions: gray matter, white matter, cerebrospinal fluid, and background. This method was applied to T1-weighted MR images of 110 participants with normal cognition (NL), 165 with MCI, and 82 with AD, obtained from the Japanese Alzheimer's Disease Neuroimaging Initiative database.

RESULTS

We obtained the coefficients of probability change (CPC) for each dataset. We found high area under the receiver operating characteristic curve (ROC) values (up to 0.908 of the difference of ROCs) for some CPC regions that are considered indicators of atrophy. Additionally, we attempted to establish a machine-learning algorithm to classify participants as NL or AD. The maximum accuracy was 92.1% for NL-AD classification and 81.2% for NL-MCI classification using CPC values between images acquired at first and sixth months, respectively.

CONCLUSION

These results showed that the proposed method is effective for the early detection of AD and MCI.

Classification of Alzheimer's Disease and Mild Cognitive Impairment Based on Cortical and Subcortical Features from MRI T1 Brain Images Utilizing Four Different Types of Datasets

Alzheimer's disease (AD) is one of the most common neurodegenerative illnesses (dementia) among the elderly. Recently, researchers have developed a new method for the instinctive analysis of AD based on machine learning and its subfield, deep learning. Recent state-of-the-art techniques consider multimodal diagnosis, which has been shown to achieve high accuracy compared to a unimodal prognosis. Furthermore, many studies have used structural magnetic resonance imaging (MRI) to measure brain volumes and the volume of subregions, as well as to search for diffuse changes in white/gray matter in the brain. In this study, T1-weighted structural MRI was used for the early classification of AD. MRI results in high-intensity visible features, making preprocessing and segmentation easy. To use this image modality, we acquired four types of datasets from each dataset's server. In this work, we downloaded 326 subjects from the National Research Center for Dementia homepage, 123 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) homepage, 121 subjects from the Alzheimer's Disease Repository Without Borders homepage, and 131 subjects from the National Alzheimer's Coordinating Center homepage. In our experiment, we used the multiatlas label propagation with expectation–maximization-based refinement segmentation method. We segmented the images into 138 anatomical morphometry images (in which 40 features belonged to subcortical volumes and the remaining 98 features belonged to cortical thickness). The entire dataset was split into a 70 : 30 (training and testing) ratio before classifying the data. A principal component analysis was used for dimensionality reduction. Then, the support vector machine radial basis function classifier was used for classification between two groups—AD versus health control (HC) and early mild cognitive impairment (MCI) (EMCI) versus late MCI (LMCI). The proposed method performed very well for all four types of dataset. For instance, for the AD versus HC group, the classifier achieved an area under curve (AUC) of more than 89% for each dataset. For the EMCI versus LMCI group, the classifier achieved an AUC of more than 80% for every dataset. Moreover, we also calculated Cohen kappa and Jaccard index statistical values for all datasets to evaluate the classification reliability. Finally, we compared our results with those of recently published state-of-the-art methods.

CSF glucose tracks regional tau progression based on Alzheimer's disease risk factors

INTRODUCTION

Glucose hypometabolism and tau formation are key features of Alzheimer's disease (AD). Less is known about the relationship between fasting glucose and regional tau accumulation.

METHODS

Cerebrospinal fluid (CSF) glucose was linearly regressed on regional tau (flortaucipir) among 169 Alzheimer's Disease Neuroimaging Initiative (ADNI3) participants. Flortaucipir uptake was examined by Braak stages and regions of interest (ROIs). Interactions were explored between CSF glucose and AD risk factors including regional amyloid beta (Aβ), sex, Apolipoprotein E ε4 (APOEε4) status, AD parental family history (AD FH), and cognitive impairment (CI).

RESULTS

Interactions found higher CSF glucose tracked less tau in ROIs or Braak stages I/II (women, APOE ε4+, regional Aβ), III/IV (AD FH+, regional Aβ), and V/VI (AD FH+). CI drove Braak III-VI associations.

DISCUSSION

Among women and APOE ε4 carriers, higher CSF glucose tracked less early-stage tau. Higher CSF glucose may reflect compensation against tau spreading in CI, Aβ+, or AD FH+.

Clinical impact of 18F-FDG-PET among memory clinic patients with uncertain diagnosis

Purpose

To assess the clinical impact and incremental diagnostic value of ¹⁸F-fluorodeoxyglucose (FDG-PET) among memory clinic patients with uncertain diagnosis.

Methods

The study population consisted of 277 patients who, despite extensive baseline cognitive assessment, MRI, and CSF analyses, had an uncertain diagnosis of mild cognitive impairment (MCI) (n = 177) or dementia (n = 100). After baseline diagnosis, each patient underwent an FDG-PET, followed by a post-FDG-PET diagnosis formulation. We evaluated (i) the change in diagnosis (baseline vs. post-FDG-PET), (ii) the change in diagnostic accuracy when comparing each baseline and post-FDG-PET diagnosis to a long-term follow-up (3.6 ± 1.8 years) diagnosis used as reference, and (iii) comparative FDG-PET performance testing in MCI and dementia conditions.

Results

FDG-PET led to a change in diagnosis in 86 of 277 (31%) patients, in particular in 57 of 177 (32%) MCI and in 29 of 100 (29%) dementia patients. Diagnostic change was greater than two-fold in the sub-sample of cases with dementia “of unclear etiology” (change in diagnosis in 20 of 32 (63%) patients). In the dementia group, after results of FDG-PET, diagnostic accuracy improved from 77 to 90% in Alzheimer’s disease (AD) and from 85 to 94% in frontotemporal lobar degeneration (FTLD) patients (p < 0.01). FDG-PET performed better in dementia than in MCI (positive likelihood ratios >5 and < 5, respectively).

Conclusion

Within a selected clinical population, FDG-PET has a significant clinical impact, both in early and differential diagnosis of uncertain dementia. FDG-PET provides significant incremental value to detect AD and FTLD over a clinical diagnosis of uncertain dementia.

Electronic supplementary material

The online version of this article (10.1007/s00259-020-04969-7) contains supplementary material, which is available to authorized users.

A survey on machine and statistical learning for longitudinal analysis of neuroimaging data in Alzheimer's disease

BACKGROUND AND OBJECTIVES

Recently, longitudinal studies of Alzheimer's disease have gathered a substantial amount of neuroimaging data. New methods are needed to successfully leverage and distill meaningful information on the progression of the disease from the deluge of available data. Machine learning has been used successfully for many different tasks, including neuroimaging related problems. In this paper, we review recent statistical and machine learning applications in Alzheimer's disease using longitudinal neuroimaging.

METHODS

We search for papers using longitudinal imaging data, focused on Alzheimer's Disease and published between 2007 and 2019 on four different search engines.

RESULTS

After the search, we obtain 104 relevant papers. We analyze their approach to typical challenges in longitudinal data analysis, such as missing data and variability in the number and extent of acquisitions.

CONCLUSIONS

Reviewed works show that machine learning methods using longitudinal data have potential for disease progression modelling and computer-aided diagnosis. We compare results and models, and propose future research directions in the field.

Predicting MCI progression with FDG-PET and cognitive scores: a longitudinal study

BACKGROUND

Mild cognitive impairment (MCI) is an intermediate stage between normal aging and dementia. Studies on MCI progression are important for Alzheimer's disease (AD) prevention. 18F fluoro-deoxy-glucose positron emission tomography (FDG-PET) has been proven to be a powerful tool for measuring cerebral glucose metabolism. In this study, we proposed a classification framework for MCI prediction with both baseline and multiple follow-up FDG-PET scans as well as cognitive scores of 33 progressive MCI (pMCI) patients and 46 stable MCI (sMCI) patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI).

METHOD

First, PET images were normalized using the Yakushev normalization procedure and registered to the Brainnetome Atlas (BNA). The average metabolic intensities of brain regions were defined as static features. Dynamic features were the intensity variation between baseline and the other three time points and change ratios with the intensity obtained at baseline considered as reference. Mini-mental State Examination (MMSE) scores and Alzheimer's disease Assessment Scale-Cognitive section (ADAS-cog) scores of each time point were collected as cognitive features. And F-score was applied for feature selection. Finally, support vector machine (SVM) with radial basis function (RBF) kernel was used for the three above features.

RESULTS

Dynamic features showed the best classification performance in accuracy of 88.61% than static features (accuracy of 78.48%). And the combination of cognitive features and dynamic features improved the classification performance in specificity of 95.65% and Area Under Curve (AUC) of 0.9308.

CONCLUSION

Our results reported that dynamic features are more representative in longitudinal research for MCI prediction work. And dynamic features and cognitive scores complementarily enhance the classification performance in specificity and AUC. These findings may predict the disease course and clinical changes in individuals with mild cognitive impairment.

White Matter Network Alterations in Alzheimer’s Disease Patients

Previous studies have revealed the occurrence of alterations of white matter (WM) and grey matter (GM) microstructures in Alzheimer’s disease (AD) and their prodromal state amnestic mild cognitive impairment (MCI). In general, these alterations can be studied comprehensively by modeling the brain as a complex network, which describes many important topological properties, such as the small-world property, modularity, and efficiency. In this study, we systematically investigated white matter abnormalities using unbiased whole brain network analysis. We compared regional and network related WM features between groups of 19 AD and 25 MCI patients and 22 healthy controls (HC) using tract-based spatial statistics (TBSS), network based statistics (NBS) and graph theoretical analysis. We did not find significant differences in fractional anisotropy (FA) between two groups on TBSS analysis. However, observable alterations were noticed at a network level. Brain network measures such as global efficiency and small world properties were low in AD patients compared to HCs.

Quantifying Neurodegenerative Progression With DeepSymNet, an End-to-End Data-Driven Approach

Alzheimer's disease (AD) is the most common neurodegenerative disorder worldwide and is one of the leading sources of morbidity and mortality in the aging population. There is a long preclinical period followed by mild cognitive impairment (MCI). Clinical diagnosis and the rate of decline is variable. Progression monitoring remains a challenge in AD, and it is imperative to create better tools to quantify this progression. Brain magnetic resonance imaging (MRI) is commonly used for patient assessment. However, current approaches for analysis require strong a priori assumptions about regions of interest used and complex preprocessing pipelines including computationally expensive non-linear registrations and iterative surface deformations. These preprocessing steps are composed of many stacked processing layers. Any error or bias in an upstream layer will be propagated throughout the pipeline. Failures or biases in the non-linear subject registration and the subjective choice of atlases of specific regions are common in medical neuroimaging analysis and may hinder the translation of many approaches to the clinical practice. Here we propose a data-driven method based on an extension of a deep learning architecture, DeepSymNet, that identifies longitudinal changes without relying on prior brain regions of interest, an atlas, or non-linear registration steps. Our approach is trained end-to-end and learns how a patient's brain structure dynamically changes between two-time points directly from the raw voxels. We compare our approach with Freesurfer longitudinal pipelines and voxel-based methods using the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our model can identify AD progression with comparable results to existing Freesurfer longitudinal pipelines without the need of predefined regions of interest, non-rigid registration algorithms, or iterative surface deformation at a fraction of the processing time. When compared to other voxel-based methods which share some of the same benefits, our model showed a statistically significant performance improvement. Additionally, we show that our model can differentiate between healthy subjects and patients with MCI. The model's decision was investigated using the epsilon layer-wise propagation algorithm. We found that the predictions were driven by the pallidum, putamen, and the superior temporal gyrus. Our novel longitudinal based, deep learning approach has the potential to diagnose patients earlier and enable new computational tools to monitor neurodegeneration in clinical practice.

Multiscale spatial gradient features for 18F-FDG PET image-guided diagnosis of Alzheimer's disease

BACKGROUND AND OBJECTIVE

¹⁸F-FluoroDeoxyGlucose Positron Emission Tomography (¹⁸F-FDG PET) is one of the imaging biomarkers to diagnose Alzheimer's Disease (AD). In ¹⁸F-FDG PET images, the changes of voxels' intensities reflect the differences of glucose rates, therefore voxel intensity is usually used as a feature to distinguish AD from Normal Control (NC), or at earlier stage to distinguish between progressive and stable Mild Cognitive Impairment (pMCI and sMCI). In this paper, ¹⁸F-FDG PET images are characterized in an alternative way-the spatial gradient, which is motivated by the observation that the changes of ¹⁸F-FDG rates also cause gradient changes.

METHODS

We improve Histogram of Oriented Gradient (HOG) descriptor to quantify spatial gradients, thereby achieving the goal of diagnosing AD. First, the spatial gradient of ¹⁸F-FDG PET image is computed, and then each subject is segmented into different regions by using an anatomical atlas. Second, two types of improved HOG features are extracted from each region, namely Small Scale HOG and Large Scale HOG, then some relevant regions are selected based on a classifier fed with spatial gradient features. Last, an ensemble classification framework is designed to make a decision, which considers the performance of both individual and concatenated selected regions.

RESULTS

the evaluation is done on ADNI dataset. The proposed method outperforms other state-of-the-art ¹⁸F-FDG PET-based algorithms for AD vs. NC with an accuracy, a sensitivity and a specificity values of 93.65%, 91.22% and 96.25%, respectively. For the case of pMCI vs. sMCI, the three metrics are 75.38%, 74.84% and 77.11%, which is significantly better than most existing methods. Besides, promising results are also achieved for multiple classifications under ¹⁸F-FDG PET modality.

CONCLUSIONS

¹⁸F-FDG PET images can be characterized by spatial gradient features for diagnosing AD and its early stage, and the proposed ensemble framework can enhance the classification performance.

Identification of Alzheimer’s Disease on the Basis of a Voxel-Wise Approach

Robust prediction of Alzheimer’s disease (AD) helps in the early diagnosis of AD and may support the treatment of AD patients. In this study, for early detection of AD and prediction of mild cognitive impairment (MCI) conversion, we develop an automatic computer-aided diagnosis (CAD) framework based on a merit-based feature selection method through a whole-brain voxel-wise analysis using baseline magnetic resonance imaging (MRI) data. We also explore the impact of different MRI spatial resolution on the voxel-wise metric AD classification and MCI conversion prediction. We assessed the proposed CAD framework using the whole-brain voxel-wise MRI features of 507 J-ADNI participants (146 healthy controls [HCs], 102 individuals with stable MCI [sMCI], 112 with progressive MCI [pMCI], and 147 with AD) among four clinically relevant pairs of diagnostic groups at different imaging resolutions (i.e., 2, 4, 8, and 16 mm). Using a support vector machine classifier through a 10-fold cross-validation strategy at a spatial resolution of 2 mm, the proposed CAD framework yielded classification accuracies of 91.13%, 74.77%, 81.12%, and 81.78% in identifying AD/healthy control, sMCI/pMCI, sMCI/AD, and pMCI/HC, respectively. The experimental results show that a lower spatial resolution (i.e., 2 mm) may provide more robust information to trace the neuronal loss-related brain atrophy in AD.

Alzheimer's Disease Diagnosis Based on Cortical and Subcortical Features

Alzheimer's disease (AD) is a common neurodegenerative disease with an often seen prodromal mild cognitive impairment (MCI) phase, where memory loss is the main complaint progressively worsening with behavior issues and poor self-care. However, not all patients clinically diagnosed with MCI progress to the AD. Currently, several high-dimensional classification techniques have been developed to automatically distinguish among AD, MCI, and healthy control (HC) patients based on T1-weighted MRI. However, these method features are based on wavelets, contourlets, gray-level co-occurrence matrix, etc., rather than using clinical features which helps doctors to understand the pathological mechanism of the AD. In this study, a new approach is proposed using cortical thickness and subcortical volume for distinguishing binary and tertiary classification of the National Research Center for Dementia dataset (NRCD), which consists of 326 subjects. Five classification experiments are performed: binary classification, i.e., AD vs HC, HC vs mAD (MCI due to the AD), and mAD vs aAD (asymptomatic AD), and tertiary classification, i.e., AD vs HC vs mAD and AD vs HC vs aAD using cortical and subcortical features. Datasets were divided in a 70/30 ratio, and later, 70% were used for training and the remaining 30% were used to get an unbiased estimation performance of the suggested methods. For dimensionality reduction purpose, principal component analysis (PCA) was used. After that, the output of PCA was passed to various types of classifiers, namely, softmax, support vector machine (SVM), k-nearest neighbors, and naïve Bayes (NB) to check the performance of the model. Experiments on the NRCD dataset demonstrated that the softmax classifier is best suited for the AD vs HC classification with an F1 score of 99.06, whereas for other groups, the SVM classifier is best suited for the HC vs mAD, mAD vs aAD, and AD vs HC vs mAD classifications with the F1 scores being 99.51, 97.5, and 99.99, respectively. In addition, for the AD vs HC vs aAD classification, NB performed well with an F1 score of 95.88. In addition, to check our proposed model efficiency, we have also used the OASIS dataset for comparing with 9 state-of-the-art methods.

Neuroimaging and Machine Learning for Dementia Diagnosis: Recent Advancements and Future Prospects

Dementia, a chronic and progressive cognitive declination of brain function caused by disease or impairment, is becoming more prevalent due to the aging population. A major challenge in dementia is achieving accurate and timely diagnosis. In recent years, neuroimaging with computer-aided algorithms have made remarkable advances in addressing this challenge. The success of these approaches is mostly attributed to the application of machine learning techniques for neuroimaging. In this review paper, we present a comprehensive survey of automated diagnostic approaches for dementia using medical image analysis and machine learning algorithms published in the recent years. Based on the rigorous review of the existing works, we have found that, while most of the studies focused on Alzheimer's disease, recent research has demonstrated reasonable performance in the identification of other types of dementia remains a major challenge. Multimodal imaging analysis deep learning approaches have shown promising results in the diagnosis of these other types of dementia. The main contributions of this review paper are as follows. 1) Based on the detailed analysis of the existing literature, this paper discusses neuroimaging procedures for dementia diagnosis. 2) It systematically explains the most recent machine learning techniques and, in particular, deep learning approaches for early detection of dementia.

Prognosis of conversion of mild cognitive impairment to Alzheimer's dementia by voxel-wise Cox regression based on FDG PET data

Aim

The value of ¹⁸F-fluorodeoxyglucose (FDG) PET for the prognosis of conversion from mild cognitive impairment (MCI) to Alzheimer's dementia (AD) is controversial. In the present work, the identification of cerebral metabolic patterns with significant prognostic value for conversion of MCI patients to AD is investigated with voxel-based Cox regression, which in contrast to common categorical comparisons also utilizes time information.

Methods

FDG PET data of 544 MCI patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were randomly split into two equally-sized datasets (training and test). Within a median follow-up duration of 47 months (95% CI: 46–48 months) 181 patients developed AD. In the training dataset, voxel-wise Cox regressions were used to identify regions associated with conversion of MCI to AD. These were compared to regions identified by a classical group comparison (analysis of covariance (ANCOVA) with statistical parametric mapping (SPM) 8) between converters and non-converters (both adjusted for apolipoprotein E (APOE) genotype, mini-mental state examination (MMSE) score, age, sex and education). In the test dataset, normalized FDG uptake within significant brain regions from voxel-wise Cox- and ANCOVA analyses (Cox- and ANCOVA- regions of interest (ROI), respectively) and clinical variables APOE status, MMSE score and education were tested in different Cox models (adjusted for age, sex) including: (1) only clinical variables, (2) only normalized FDG uptake in ANCOVA-ROI, (3) only normalized FDG uptake from Cox-ROI, (4) clinical variables plus FDG uptake in ANCOVA-ROI, (5) clinical variables plus FDG uptake from Cox-ROI.

Results

Conversion-related regions with relative hypometabolism comprised parts of the temporo-parietal and posterior cingulate cortex/precuneus for voxel-wise ANCOVA, plus frontal regions for voxel-wise Cox regression (both p < .01, false discovery rate (FDR) corrected). The clinical-only model (1) and the models based on normalized FDG uptake from Cox-ROI only (2) and ANCOVA-ROI only (3) all significantly predicted conversion to AD (Wald Test (WT): p < .001). The clinical model (1) was significantly improved by adding imaging information in model (4) (Akaike information criterion (AIC) relative likelihood (RL) (1) vs (4): RL < 0.018). There were no significant differences between models (2) and (3), as well as (4) and (5).

Conclusions

Voxel-wise Cox regression identifies conversion-related patterns of cerebral glucose metabolism, but is not superior to classical group contrasts in this regard. With imaging information from both FDG PET patterns, the prediction of conversion to AD was improved.

•

Voxel-wise Cox regression identifies regions relevant for development AD.

•

Hypometabolism of these regions poses a significant hazard for AD development.

•

Inclusion of FDG PET data improves the accuracy of prognosis significantly.

Machine Learning for Predicting Cognitive Diseases: Methods, Data Sources and Risk Factors

Machine learning and data mining approaches are being successfully applied to different fields of life sciences for the past 20 years. Medicine is one of the most suitable application domains for these techniques since they help model diagnostic information based on causal and/or statistical data and therefore reveal hidden dependencies between symptoms and illnesses. In this paper we give a detailed overview of the recent machine learning research and its applications for predicting cognitive diseases, especially the Alzheimer's disease, mild cognitive impairment and the Parkinson's disease. We survey different state-of-the-art methodological approaches, data sources and public data, and provide their comparative analysis. We conclude by identifying the open problems within the field that include an early detection of the cognitive diseases and inclusion of machine learning tools into diagnostic practice and therapy planning.

Multilevel Feature Representation of FDG-PET Brain Images for Diagnosing Alzheimer's Disease

Using a single imaging modality to diagnose Alzheimer's disease (AD) or mild cognitive impairment (MCI) is a challenging task. FluoroDeoxyGlucose Positron Emission Tomography (FDG-PET) is an important and effective modality used for that purpose. In this paper, we develop a novel method by using single modality (FDG-PET) but multilevel feature, which considers both region properties and connectivities between regions to classify AD or MCI from normal control. First, three levels of features are extracted: statistical, connectivity, and graph-based features. Then, the connectivity features are decomposed into three different sets of features according to a proposed similarity-driven ranking method, which can not only reduce the feature dimension but also increase the classifier's diversity. Last, after feeding the three levels of features to different classifiers, a new classifier selection strategy, maximum Mean squared Error (mMsE), is developed to select a pair of classifiers with high diversity. In order to do the majority voting, a decision-making scheme, a nested cross validation technique is applied to choose another classifier according to the accuracy. Experiments on Alzheimer's Disease Neuroimaging Initiative database show that the proposed method outperforms most FDG-PET-based classification algorithms, especially for classifying progressive MCI (pMCI) from stable MCI (sMCI).

European Association of Nuclear Medicine and European Academy of Neurology recommendations for the use of brain 18 F-fluorodeoxyglucose positron emission tomography in neurodegenerative cognitive impairment and dementia: Delphi consensus

BACKGROUND AND PURPOSE

Recommendations for using fluorodeoxyglucose positron emission tomography (FDG-PET) to support the diagnosis of dementing neurodegenerative disorders are sparse and poorly structured.

METHODS

Twenty-one questions on diagnostic issues and on semi-automated analysis to assist visual reading were defined. Literature was reviewed to assess study design, risk of bias, inconsistency, imprecision, indirectness and effect size. Critical outcomes were sensitivity, specificity, accuracy, positive/negative predictive value, area under the receiver operating characteristic curve, and positive/negative likelihood ratio of FDG-PET in detecting the target conditions. Using the Delphi method, an expert panel voted for/against the use of FDG-PET based on published evidence and expert opinion.

RESULTS

Of the 1435 papers, 58 papers provided proper quantitative assessment of test performance. The panel agreed on recommending FDG-PET for 14 questions: diagnosing mild cognitive impairment due to Alzheimer's disease (AD), frontotemporal lobar degeneration (FTLD) or dementia with Lewy bodies (DLB); diagnosing atypical AD and pseudo-dementia; differentiating between AD and DLB, FTLD or vascular dementia, between DLB and FTLD, and between Parkinson's disease and progressive supranuclear palsy; suggesting underlying pathophysiology in corticobasal degeneration and progressive primary aphasia, and cortical dysfunction in Parkinson's disease; using semi-automated assessment to assist visual reading. Panellists did not support FDG-PET use for pre-clinical stages of neurodegenerative disorders, for amyotrophic lateral sclerosis and Huntington disease diagnoses, and for amyotrophic lateral sclerosis or Huntington-disease-related cognitive decline.

CONCLUSIONS

Despite limited formal evidence, panellists deemed FDG-PET useful in the early and differential diagnosis of the main neurodegenerative disorders, and semi-automated assessment helpful to assist visual reading. These decisions are proposed as interim recommendations.

Classification of Alzheimer's Disease by Combination of Convolutional and Recurrent Neural Networks Using FDG-PET Images

Alzheimer's disease (AD) is an irreversible brain degenerative disorder affecting people aged older than 65 years. Currently, there is no effective cure for AD, but its progression can be delayed with some treatments. Accurate and early diagnosis of AD is vital for the patient care and development of future treatment. Fluorodeoxyglucose positrons emission tomography (FDG-PET) is a functional molecular imaging modality, which proves to be powerful to help understand the anatomical and neural changes of brain related to AD. Most existing methods extract the handcrafted features from images, and then design a classifier to distinguish AD from other groups. These methods highly depends on the preprocessing of brain images, including image rigid registration and segmentation. Motivated by the success of deep learning in image classification, this paper proposes a new classification framework based on combination of 2D convolutional neural networks (CNN) and recurrent neural networks (RNNs), which learns the intra-slice and inter-slice features for classification after decomposition of the 3D PET image into a sequence of 2D slices. The 2D CNNs are built to capture the features of image slices while the gated recurrent unit (GRU) of RNN is cascaded to learn and integrate the inter-slice features for image classification. No rigid registration and segmentation are required for PET images. Our method is evaluated on the baseline FDG-PET images acquired from 339 subjects including 93 AD patients, 146 mild cognitive impairments (MCI) and 100 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an area under receiver operating characteristic curve (AUC) of 95.3% for AD vs. NC classification and 83.9% for MCI vs. NC classification, demonstrating the promising classification performance.

Brain MRI analysis for Alzheimer's disease diagnosis using an ensemble system of deep convolutional neural networks

Alzheimer’s disease is an incurable, progressive neurological brain disorder. Earlier detection of Alzheimer’s disease can help with proper treatment and prevent brain tissue damage. Several statistical and machine learning models have been exploited by researchers for Alzheimer’s disease diagnosis. Analyzing magnetic resonance imaging (MRI) is a common practice for Alzheimer’s disease diagnosis in clinical research. Detection of Alzheimer’s disease is exacting due to the similarity in Alzheimer’s disease MRI data and standard healthy MRI data of older people. Recently, advanced deep learning techniques have successfully demonstrated human-level performance in numerous fields including medical image analysis. We propose a deep convolutional neural network for Alzheimer’s disease diagnosis using brain MRI data analysis. While most of the existing approaches perform binary classification, our model can identify different stages of Alzheimer’s disease and obtains superior performance for early-stage diagnosis. We conducted ample experiments to demonstrate that our proposed model outperformed comparative baselines on the Open Access Series of Imaging Studies dataset.

Classification of Alzheimer's Disease, Mild Cognitive Impairment, and Normal Controls With Subnetwork Selection and Graph Kernel Principal Component Analysis Based on Minimum Spanning Tree Brain Functional Network

Effective and accurate diagnosis of Alzheimer's disease (AD), as well as its early stage (mild cognitive impairment, MCI), has attracted more and more attention recently. Researchers have constructed threshold brain function networks and extracted various features for the classification of brain diseases. However, in the construction of the brain function network, the selection of threshold is very important, and the unreasonable setting will seriously affect the final classification results. To address this issue, in this paper, we propose a minimum spanning tree (MST) classification framework to identify Alzheimer's disease (AD), MCI, and normal controls (NCs). The proposed method mainly uses the MST method, graph-based Substructure Pattern mining (gSpan), and graph kernel Principal Component Analysis (graph kernel PCA). Specifically, MST is used to construct the brain functional connectivity network; gSpan, to extract features; and subnetwork selection and graph kernel PCA, to select features. Finally, the support vector machine is used to perform classification. We evaluate our method on MST brain functional networks of 21 AD, 25 MCI, and 22 NC subjects. The experimental results show that our proposed method achieves classification accuracy of 98.3, 91.3, and 77.3%, for MCI vs. NC, AD vs. NC, and AD vs. MCI, respectively. The results show our proposed method can achieve significantly improved classification performance compared to other state-of-the-art methods.