Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI

Early Alzheimer's Disease Detection: A Review of Machine Learning Techniques for Forecasting Transition from Mild Cognitive Impairment

Alzheimer's disease is a weakening neurodegenerative condition with profound cognitive implications, making early and accurate detection crucial for effective treatment. In recent years, machine learning, particularly deep learning, has shown significant promise in detecting mild cognitive impairment to Alzheimer's disease conversion. This review synthesizes research on machine learning approaches for predicting conversion from mild cognitive impairment to Alzheimer's disease dementia using magnetic resonance imaging, positron emission tomography, and other biomarkers. Various techniques used in literature such as machine learning, deep learning, and transfer learning were examined in this study. Additionally, data modalities and feature extraction methods analyzed by different researchers are discussed. This review provides a comprehensive overview of the current state of research in Alzheimer's disease detection and highlights future research directions.

Proteomic analyses reveal plasma EFEMP1 and CXCL12 as biomarkers and determinants of neurodegeneration

INTRODUCTION

Plasma proteomic analyses of unique brain atrophy patterns may illuminate peripheral drivers of neurodegeneration and identify novel biomarkers for predicting clinically relevant outcomes.

METHODS

We identified proteomic signatures associated with machine learning-derived aging- and Alzheimer's disease (AD) -related brain atrophy patterns in the Baltimore Longitudinal Study of Aging (n = 815). Using data from five cohorts, we examined whether candidate proteins were associated with AD endophenotypes and long-term dementia risk.

RESULTS

Plasma proteins associated with distinct patterns of age- and AD-related atrophy were also associated with plasma/cerebrospinal fluid (CSF) AD biomarkers, cognition, AD risk, as well as mid-life (20-year) and late-life (8-year) dementia risk. EFEMP1 and CXCL12 showed the most consistent associations across cohorts and were mechanistically implicated as determinants of brain structure using genetic methods, including Mendelian randomization.

DISCUSSION

Our findings reveal plasma proteomic signatures of unique aging- and AD-related brain atrophy patterns and implicate EFEMP1 and CXCL12 as important molecular drivers of neurodegeneration.

HIGHLIGHTS

Plasma proteomic signatures are associated with unique patterns of brain atrophy. Brain atrophy-related proteins predict clinically relevant outcomes across cohorts. Genetic variation underlying plasma EFEMP1 and CXCL12 influences brain structure. EFEMP1 and CXCL12 may be important molecular drivers of neurodegeneration.

Deep grading for MRI-based differential diagnosis of Alzheimer's disease and Frontotemporal dementia

Alzheimer's disease and Frontotemporal dementia are common forms of neurodegenerative dementia. Behavioral alterations and cognitive impairments are found in the clinical courses of both diseases, and their differential diagnosis can sometimes pose challenges for physicians. Therefore, an accurate tool dedicated to this diagnostic challenge can be valuable in clinical practice. However, current structural imaging methods mainly focus on the detection of each disease but rarely on their differential diagnosis. In this paper, we propose a deep learning-based approach for both disease detection and differential diagnosis. We suggest utilizing two types of biomarkers for this application: structure grading and structure atrophy. First, we propose to train a large ensemble of 3D U-Nets to locally determine the anatomical patterns of healthy people, patients with Alzheimer's disease and patients with Frontotemporal dementia using structural MRI as input. The output of the ensemble is a 2-channel disease's coordinate map, which can be transformed into a 3D grading map that is easily interpretable for clinicians. This 2-channel disease's coordinate map is coupled with a multi-layer perceptron classifier for different classification tasks. Second, we propose to combine our deep learning framework with a traditional machine learning strategy based on volume to improve the model discriminative capacity and robustness. After both cross-validation and external validation, our experiments, based on 3319 MRIs, demonstrated that our method produces competitive results compared to state-of-the-art methods for both disease detection and differential diagnosis.

Classifying Alzheimer's disease and frontotemporal dementia using machine learning with cross-sectional and longitudinal magnetic resonance imaging data

Alzheimer's disease (AD) and frontotemporal dementia (FTD) are common causes of dementia with partly overlapping, symptoms and brain signatures. There is a need to establish an accurate diagnosis and to obtain markers for disease tracking. We combined unsupervised and supervised machine learning to discriminate between AD and FTD using brain magnetic resonance imaging (MRI). We included baseline 3T-T1 MRI data from 339 subjects: 99 healthy controls (CTR), 153 AD and 87 FTD patients; and 2-year follow-up data from 114 subjects. We obtained subcortical gray matter volumes and cortical thickness measures using FreeSurfer. We used dimensionality reduction to obtain a single feature that was later used in a support vector machine for classification. Discrimination patterns were obtained with the contribution of each region to the single feature. Our algorithm differentiated CTR versus AD and CTR versus FTD at the cross-sectional level with 83.3% and 82.1% of accuracy. These increased up to 90.0% and 88.0% with longitudinal data. When we studied the classification between AD versus FTD we obtained an accuracy of 63.3% at the cross-sectional level and 75.0% for longitudinal data. The AD versus FTD versus CTR classification has reached an accuracy of 60.7%, and 71.3% for cross-sectional and longitudinal data respectively. Disease discrimination brain maps are in concordance with previous results obtained with classical approaches. By using a single feature, we were capable to classify CTR, AD, and FTD with good accuracy, considering the inherent overlap between diseases. Importantly, the algorithm can be used with cross-sectional and longitudinal data.

A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images

Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (N_rmC) but, it still requires a lot of work to be done for MCI/ N_rmC and MCI/AD, which would help in detecting AD at its early stage.

A new strategy for the early detection of alzheimer disease stages using multifractal geometry analysis based on K-Nearest Neighbor algorithm

Alzheimer's Disease (AD) is considered one of the most diseases that much prevalent among elderly people all over the world. AD is an incurable neurodegenerative disease affecting cognitive functions and were characterized by progressive and collective functions deteriorating. Remarkably, early detection of AD is essential for the development of new and invented treatment strategies. As Dementia causes irreversible damage to the brain neurons and leads to changes in its structure that can be described adequately within the framework of multifractals. Hence, the present work focus on developing a promising and efficient computing technique to pre-process and classify the AD disease especially in the early stages using multifractal geometry to extract the most changeable features due to AD. Then, A machine learning classification algorithm (K-Nearest Neighbor) has been implemented in order to classify and detect the main four early stages of AD. Two datasets have been used to ensure the validation of the proposed methodology. The proposed technique has achieved 99.4% accuracy and 100% sensitivity. The comparative results show that the proposed classification technique outperforms is recent techniques in terms of performance measures.

Machine Learning-Based Classification of Subjective Cognitive Decline, Mild Cognitive Impairment, and Alzheimer's Dementia Using Neuroimage and Plasma Biomarkers

Alzheimer's disease (AD) progresses relentlessly from the preclinical to the dementia stage. The process begins decades before the diagnosis of dementia. Therefore, it is crucial to detect early manifestations to prevent cognitive decline. Recent advances in artificial intelligence help tackle the complex high-dimensional data encountered in clinical decision-making. In total, we recruited 206 subjects, including 69 cognitively unimpaired, 40 subjective cognitive decline (SCD), 34 mild cognitive impairment (MCI), and 63 AD dementia (ADD). We included 3 demographic, 1 clinical, 18 brain-image, and 3 plasma biomarker (Aß_1-42, Aß_1-40, and tau protein) features. We employed the linear discriminant analysis method for feature extraction to make data more distinguishable after dimension reduction. The sequential forward selection method was used for feature selection to identify the 12 best features for machine learning classifiers. We used both random forest and support vector machine as classifiers. The area under the receiver operative curve (AUROC) was close to 0.9 between diseased (combining ADD and MCI) and the controls. AUROC was higher than 0.85 between SCD and controls, 0.90 between MCI and SCD, and above 0.85 between ADD and MCI. We can differentiate between adjacent phases of the AD spectrum with blood biomarkers and brain MR images with the help of machine learning algorithms.

Distribution and inter-regional relationship of amyloid-beta plaque deposition in a 5xFAD mouse model of Alzheimer’s disease

Alzheimer’s disease (AD) is the most common form of dementia. Although previous studies have selectively investigated the localization of amyloid-beta (Aβ) deposition in certain brain regions, a comprehensive characterization of the rostro-caudal distribution of Aβ plaques in the brain and their inter-regional correlation remain unexplored. Our results demonstrated remarkable working and spatial memory deficits in 9-month-old 5xFAD mice compared to wildtype mice. High Aβ plaque load was detected in the somatosensory cortex, piriform cortex, thalamus, and dorsal/ventral hippocampus; moderate levels of Aβ plaques were observed in the motor cortex, orbital cortex, visual cortex, and retrosplenial dysgranular cortex; and low levels of Aβ plaques were located in the amygdala, and the cerebellum; but no Aβ plaques were found in the hypothalamus, raphe nuclei, vestibular nucleus, and cuneate nucleus. Interestingly, the deposition of Aβ plaques was positively associated with brain inter-regions including the prefrontal cortex, somatosensory cortex, medial amygdala, thalamus, and the hippocampus. In conclusion, this study provides a comprehensive morphological profile of Aβ deposition in the brain and its inter-regional correlation. This suggests an association between Aβ plaque deposition and specific brain regions in AD pathogenesis.

Alzheimer's disease: a scoping review of biomarker research and development for effective disease diagnosis

INTRODUCTION

Alzheimer's disease (AD) is regarded as the foremost reason for neurodegeneration that prominently affects the geriatric population. Characterized by extracellular accumulation of amyloid-beta (Aβ), intracellular aggregation of hyperphosphorylated tau (p-tau), and neuronal degeneration that causes impairment of memory and cognition. Amyloid/tau/neurodegeneration (ATN) classification is utilized for research purposes and involves amyloid, tau, and neuronal injury staging through MRI, PET scanning, and CSF protein concentration estimations. CSF sampling is invasive, and MRI and PET scanning requires sophisticated radiological facilities which limit its widespread diagnostic use. ATN classification lacks effectiveness in preclinical AD.

AREAS COVERED

This publication intends to collate and review the existing biomarker profile and the current research and development of a new arsenal of biomarkers for AD pathology from different biological samples, microRNA (miRNA), proteomics, metabolomics, artificial intelligence, and machine learning for AD screening, diagnosis, prognosis, and monitoring of AD treatments.

EXPERT OPINION

It is an accepted observation that AD-related pathological changes occur over a long period of time before the first symptoms are observed providing ample opportunity for detection of biological alterations in various biological samples that can aid in early diagnosis and modify treatment outcomes.

A Reproducible Deep-Learning-Based Computer-Aided Diagnosis Tool for Frontotemporal Dementia Using MONAI and Clinica Frameworks

Despite Artificial Intelligence (AI) being a leading technology in biomedical research, real-life implementation of AI-based Computer-Aided Diagnosis (CAD) tools into the clinical setting is still remote due to unstandardized practices during development. However, few or no attempts have been made to propose a reproducible CAD development workflow for 3D MRI data. In this paper, we present the development of an easily reproducible and reliable CAD tool using the Clinica and MONAI frameworks that were developed to introduce standardized practices in medical imaging. A Deep Learning (DL) algorithm was trained to detect frontotemporal dementia (FTD) on data from the NIFD database to ensure reproducibility. The DL model yielded 0.80 accuracy (95% confidence intervals: 0.64, 0.91), 1 sensitivity, 0.6 specificity, 0.83 F1-score, and 0.86 AUC, achieving a comparable performance with other FTD classification approaches. Explainable AI methods were applied to understand AI behavior and to identify regions of the images where the DL model misbehaves. Attention maps highlighted that its decision was driven by hallmarking brain areas for FTD and helped us to understand how to improve FTD detection. The proposed standardized methodology could be useful for benchmark comparison in FTD classification. AI-based CAD tools should be developed with the goal of standardizing pipelines, as varying pre-processing and training methods, along with the absence of model behavior explanations, negatively impact regulators' attitudes towards CAD. The adoption of common best practices for neuroimaging data analysis is a step toward fast evaluation of efficacy and safety of CAD and may accelerate the adoption of AI products in the healthcare system.

The changing landscape of neuroimaging in frontotemporal lobar degeneration: from group-level observations to single-subject data interpretation

INTRODUCTION

While the imaging signatures of frontotemporal lobar degeneration (FTLD) phenotypes and genotypes are well-characterised based on group-level descriptive analyses, the meaningful interpretation of single MRI scans remains challenging. Single-subject MRI classification frameworks rely on complex computational models and large training datasets to categorise individual patients into diagnostic subgroups based on distinguishing imaging features. Reliable individual subject data interpretation is hugely important in the clinical setting to expedite the diagnosis and classify individuals into relevant prognostic categories.

AREAS COVERED

This article reviews (1) the neuroimaging studies that propose single-subject MRI classification strategies in symptomatic and pre-symptomatic FTLD, (2) potential practical implications and (3) the limitations of current single-subject data interpretation models.

EXPERT OPINION

Classification studies in FTLD have demonstrated the feasibility of categorising individual subjects into diagnostic groups based on multiparametric imaging data. Preliminary data indicate that pre-symptomatic FTLD mutation carriers may also be reliably distinguished from controls. Despite momentous advances in the field, significant further improvements are needed before these models can be developed into viable clinical applications.

White matter microstructure alterations in frontotemporal dementia: Phenotype-associated signatures and single-subject interpretation

BACKGROUND

Frontotemporal dementias (FTD) include a genetically heterogeneous group of conditions with distinctive molecular, radiological and clinical features. The majority of radiology studies in FTD compare FTD subgroups to healthy controls to describe phenotype- or genotype-associated imaging signatures. While the characterization of group-specific imaging traits is academically important, the priority of clinical imaging is the meaningful interpretation of individual datasets.

METHODS

To demonstrate the feasibility of single-subject magnetic resonance imaging (MRI) interpretation, we have evaluated the white matter profile of 60 patients across the clinical spectrum of FTD. A z-score-based approach was implemented, where the diffusivity metrics of individual patients were appraised with reference to demographically matched healthy controls. Fifty white matter tracts were systematically evaluated in each subject with reference to normative data.

RESULTS

The z-score-based approach successfully detected white matter pathology in single subjects, and group-level inferences were analogous to the outputs of standard track-based spatial statistics.

CONCLUSIONS

Our findings suggest that it is possible to meaningfully evaluate the diffusion profile of single FTD patients if large normative datasets are available. In contrast to the visual review of FLAIR and T2-weighted images, computational imaging offers objective, quantitative insights into white matter integrity changes even at single-subject level.

Predicting Tau Accumulation in Cerebral Cortex with Multivariate MRI Morphometry Measurements, Sparse Coding, and Correntropy

Biomarker-assisted diagnosis and intervention in Alzheimer's disease (AD) may be the key to prevention breakthroughs. One of the hallmarks of AD is the accumulation of tau plaques in the human brain. However, current methods to detect tau pathology are either invasive (lumbar puncture) or quite costly and not widely available (Tau PET). In our previous work, structural MRI-based hippocampal multivariate morphometry statistics (MMS) showed superior performance as an effective neurodegenerative biomarker for preclinical AD and Patch Analysis-based Surface Correntropy-induced Sparse coding and max-pooling (PASCS-MP) has excellent ability to generate low-dimensional representations with strong statistical power for brain amyloid prediction. In this work, we apply this framework together with ridge regression models to predict Tau deposition in Braak12 and Braak34 brain regions separately. We evaluate our framework on 925 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Each subject has one pair consisting of a PET image and MRI scan which were collected at about the same times. Experimental results suggest that the representations from our MMS and PASCS-MP have stronger predictive power and their predicted Braak12 and Braak34 are closer to the real values compared to the measures derived from other approaches such as hippocampal surface area and volume, and shape morphometry features based on spherical harmonics (SPHARM).

Predicting Brain Amyloid Using Multivariate Morphometry Statistics, Sparse Coding, and Correntropy: Validation in 1,101 Individuals From the ADNI and OASIS Databases

Biomarker assisted preclinical/early detection and intervention in Alzheimer’s disease (AD) may be the key to therapeutic breakthroughs. One of the presymptomatic hallmarks of AD is the accumulation of beta-amyloid (Aβ) plaques in the human brain. However, current methods to detect Aβ pathology are either invasive (lumbar puncture) or quite costly and not widely available (amyloid PET). Our prior studies show that magnetic resonance imaging (MRI)-based hippocampal multivariate morphometry statistics (MMS) are an effective neurodegenerative biomarker for preclinical AD. Here we attempt to use MRI-MMS to make inferences regarding brain Aβ burden at the individual subject level. As MMS data has a larger dimension than the sample size, we propose a sparse coding algorithm, Patch Analysis-based Surface Correntropy-induced Sparse-coding and Max-Pooling (PASCS-MP), to generate a low-dimensional representation of hippocampal morphometry for each individual subject. Then we apply these individual representations and a binary random forest classifier to predict brain Aβ positivity for each person. We test our method in two independent cohorts, 841 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and 260 subjects from the Open Access Series of Imaging Studies (OASIS). Experimental results suggest that our proposed PASCS-MP method and MMS can discriminate Aβ positivity in people with mild cognitive impairment (MCI) [Accuracy (ACC) = 0.89 (ADNI)] and in cognitively unimpaired (CU) individuals [ACC = 0.79 (ADNI) and ACC = 0.81 (OASIS)]. These results compare favorably relative to measures derived from traditional algorithms, including hippocampal volume and surface area, shape measures based on spherical harmonics (SPHARM) and our prior Patch Analysis-based Surface Sparse-coding and Max-Pooling (PASS-MP) methods.

Heuristic scoring method utilizing FDG-PET statistical parametric mapping in the evaluation of suspected Alzheimer disease and frontotemporal lobar degeneration

Distinguishing frontotemporal lobar degeneration (FTLD) and Alzheimer Disease (AD) on FDG-PET based on qualitative review alone can pose a diagnostic challenge. SPM has been shown to improve diagnostic performance in research settings, but translation to clinical practice has been lacking. Our purpose was to create a heuristic scoring method based on statistical parametric mapping z-scores. We aimed to compare the performance of the scoring method to the initial qualitative read and a machine learning (ML)-based method as benchmarks. FDG-PET/CT or PET/MRI of 65 patients with suspected dementia were processed using SPM software, yielding z-scores from either whole brain (W) or cerebellar (C) normalization relative to a healthy cohort. A non-ML, heuristic scoring system was applied using region counts below a preset z-score cutoff. W z-scores, C z-scores, or WC z-scores (z-scores from both W and C normalization) served as features to build random forest models. The neurological diagnosis was used as the gold standard. The sensitivity of the non-ML scoring system and the random forest models to detect AD was higher than the initial qualitative read of the standard FDG-PET [0.89-1.00 vs. 0.22 (95% CI, 0-0.33)]. A categorical random forest model to distinguish AD, FTLD, and normal cases had similar accuracy than the non-ML scoring model (0.63 vs. 0.61). Our non-ML-based scoring system of SPM z-scores approximated the diagnostic performance of a ML-based method and demonstrated higher sensitivity in the detection of AD compared to qualitative reads. This approach may improve the diagnostic performance.

Advances in computerized MRI‐based biomarkers in Alzheimer’s disease

The use of neuroimaging examinations is crucial in Alzheimer’s disease (AD), in both research and clinical settings. Over the years, magnetic resonance imaging (MRI)–based computer‐aided diagnosis has been shown to be helpful for early screening and predicting cognitive decline. Meanwhile, an increasing number of studies have adopted machine learning for the classification of AD, with promising results. In this review article, we focus on computerized MRI‐based biomarkers of AD by reviewing representative studies that used computerized techniques to identify AD patients and predict cognitive progression. We categorized these studies based on the following applications: (1) identifying AD from normal control; (2) identifying AD from other dementia types, including vascular dementia, dementia with Lewy bodies, and frontotemporal dementia; and (3) predicting conversion from NC to mild cognitive impairment (MCI) and from MCI to AD. This systematic review could act as a state‐of‐the‐art overview of this emerging field as well as a basis for designing future studies.

Accuracy of MRI Classification Algorithms in a Tertiary Memory Center Clinical Routine Cohort

BACKGROUND

Automated volumetry software (AVS) has recently become widely available to neuroradiologists. MRI volumetry with AVS may support the diagnosis of dementias by identifying regional atrophy. Moreover, automatic classifiers using machine learning techniques have recently emerged as promising approaches to assist diagnosis. However, the performance of both AVS and automatic classifiers have been evaluated mostly in the artificial setting of research datasets.

OBJECTIVE

Our aim was to evaluate the performance of two AVS and an automatic classifier in the clinical routine condition of a memory clinic.

METHODS

We studied 239 patients with cognitive troubles from a single memory center cohort. Using clinical routine T1-weighted MRI, we evaluated the classification performance of: 1) univariate volumetry using two AVS (volBrain and Neuroreader™); 2) Support Vector Machine (SVM) automatic classifier, using either the AVS volumes (SVM-AVS), or whole gray matter (SVM-WGM); 3) reading by two neuroradiologists. The performance measure was the balanced diagnostic accuracy. The reference standard was consensus diagnosis by three neurologists using clinical, biological (cerebrospinal fluid) and imaging data and following international criteria.

RESULTS

Univariate AVS volumetry provided only moderate accuracies (46% to 71% with hippocampal volume). The accuracy improved when using SVM-AVS classifier (52% to 85%), becoming close to that of SVM-WGM (52 to 90%). Visual classification by neuroradiologists ranged between SVM-AVS and SVM-WGM.

CONCLUSION

In the routine practice of a memory clinic, the use of volumetric measures provided by AVS yields only moderate accuracy. Automatic classifiers can improve accuracy and could be a useful tool to assist diagnosis.

Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques

Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process. In this paper, we provide an in-depth review on existing computational approaches used in the whole neurodegenerative spectrum, namely for Alzheimer's, Parkinson's, and Huntington's Diseases, Amyotrophic Lateral Sclerosis, and Multiple System Atrophy. We propose a taxonomy of the specific clinical features, and of the existing computational methods. We provide a detailed analysis of the various modalities and decision systems employed for each disease. We identify and present the sleep disorders which are present in various diseases and which represent an important asset for onset detection. We overview the existing data set resources and evaluation metrics. Finally, we identify current remaining open challenges and discuss future perspectives.

Relationship Between Alzheimer's Disease and Retinal Choroidal Thickness: A Cross-Sectional Study

BACKGROUND

The choroid is involved directly or indirectly in many pathological conditions such as Alzheimer's disease (AD), Parkinson's disease (PD), and multiple sclerosis (MS).

OBJECTIVE

The objective of this study was to investigate the association between retinal choroidal properties and the pathology of AD by determining choroidal thickness, hippocampus volume, cognitive functions, and plasma BACE1 activity.

METHODS

In this cross-sectional study, 37 patients with AD and 34 age-matched controls were included. Retinal choroidal thickness was measured via enhanced depth imaging optical coherence tomography. Hippocampal volume was measured via 3.0T MRI. Cognitive functions were evaluated using the Mini-Mental State Examination (MMSE) and Alzheimer's Disease Assessment Scale-cognitive subscale (ADAS-Cog). Plasma BACE1 activity was analyzed using a fluorescence substrate-based plasma assay, and regression model were to analyze the data.

RESULTS

Retinal choroidal thickness was significantly thinner in the AD group than in the control group [(114.81±81.30) μm versus (233.79±38.29) μm, p < 0.05]. Multivariable regression analysis indicated that the ADAS-cog scores (β=-0.772, p = 0.000) and age (β=-0.176, p = 0.015) were independently associated with choroidal thickness. The logistic regression model revealed that the subfoveal choroidal thickness was a significant predictor for AD (OR = 0.984, 95% CI: 0.972-0.997).

CONCLUSION

There was a general tendency of choroid thinning as the cognitive function declined. Although choroidal thickness was not a potential indicator for early stage AD, it was valuable in monitoring AD progression.

A novel pipeline leveraging surface-based features of small subcortical structures to classify individuals with autism spectrum disorder

Autism spectrum disorder (ASD) is accompanied with widespread impairment in social-emotional functioning. Classification of ASD using sensitive morphological features derived from structural magnetic resonance imaging (MRI) of the brain may help us to better understand ASD-related mechanisms and improve related automatic diagnosis. Previous studies using T1 MRI scans in large heterogeneous ABIDE dataset with typical development (TD) controls reported poor classification accuracies (around 60%). This may because they only considered surface-based morphometry (SBM) as scalar estimates (such as cortical thickness and surface area) and ignored the neighboring intrinsic geometry information among features. In recent years, the shape-related SBM achieves great success in discovering the disease burden and progression of other brain diseases. However, when focusing on local geometry information, its high dimensionality requires careful treatment in its application to machine learning. To address the above challenges, we propose a novel pipeline for ASD classification, which mainly includes the generation of surface-based features, patch-based surface sparse coding and dictionary learning, Max-pooling and ensemble classifiers based on adaptive optimizers. The proposed pipeline may leverage the sensitivity of brain surface morphometry statistics and the efficiency of sparse coding and Max-pooling. By introducing only the surface features of bilateral hippocampus that derived from 364 male subjects with ASD and 381 age-matched TD males, this pipeline outperformed five recent MRI-based ASD classification studies with >80% accuracy in discriminating individuals with ASD from TD controls. Our results suggest shape-related SBM features may further boost the classification performance of MRI between ASD and TD.

Differential Diagnosis of Frontotemporal Dementia, Alzheimer's Disease, and Normal Aging Using a Multi-Scale Multi-Type Feature Generative Adversarial Deep Neural Network on Structural Magnetic Resonance Images

Methods: Alzheimer's disease and Frontotemporal dementia are the first and third most common forms of dementia. Due to their similar clinical symptoms, they are easily misdiagnosed as each other even with sophisticated clinical guidelines. For disease-specific intervention and treatment, it is essential to develop a computer-aided system to improve the accuracy of their differential diagnosis. Recent advances in deep learning have delivered some of the best performance for medical image recognition tasks. However, its application to the differential diagnosis of AD and FTD pathology has not been explored. Approach: In this study, we proposed a novel deep learning based framework to distinguish between brain images of normal aging individuals and subjects with AD and FTD. Specifically, we combined the multi-scale and multi-type MRI-base image features with Generative Adversarial Network data augmentation technique to improve the differential diagnosis accuracy. Results: Each of the multi-scale, multitype, and data augmentation methods improved the ability for differential diagnosis for both AD and FTD. A 10-fold cross validation experiment performed on a large sample of 1,954 images using the proposed framework achieved a high overall accuracy of 88.28%. Conclusions: The salient contributions of this study are three-fold: (1) our experiments demonstrate that the combination of multiple structural features extracted at different scales with our proposed deep neural network yields superior performance than individual features; (2) we show that the use of Generative Adversarial Network for data augmentation could further improve the discriminant ability of the network regarding challenging tasks such as differentiating dementia sub-types; (3) and finally, we show that ensemble classifier strategy could make the network more robust and stable.

Olfactory dysfunction in frontotemporal dementia and psychiatric disorders: A systematic review

Frontotemporal dementia (FTD) is a progressive neurodegenerative disease. Diagnosis of FTD, especially the behavioural variant, is challenging because of symptomatic overlap with psychiatric disorders (depression, schizophrenia, bipolar disorder). Olfactory dysfunction is common in both FTD and psychiatric disorders, and often appears years before symptom onset. This systematic review analysed 74 studies on olfactory function in FTD, depression, schizophrenia and bipolar disorder to identify differences in olfactory dysfunction profiles, focusing on the most common smell measures: odour identification and discrimination. Results revealed that FTD patients were severely impaired in odour identification but not discrimination; in contrast, patients diagnosed with schizophrenia showed impairments in both measures, while those diagnosed with depression showed no olfactory impairments. Findings in bipolar disorder were mixed. Therefore, testing odour identification and discrimination differentiates FTD from depression and schizophrenia, but not from bipolar disorder. Given the high prevalence of odour identification impairments in FTD, and that smell dysfunction predicts neurodegeneration in other diseases, olfactory testing seems a promising avenue towards improving diagnosis between FTD and psychiatric disorders.

Radiological classification of dementia from anatomical MRI assisted by machine learning-derived maps

BACKGROUND AND PURPOSE

Many artificial intelligence tools are currently being developed to assist diagnosis of dementia from magnetic resonance imaging (MRI). However, these tools have so far been difficult to integrate in the clinical routine workflow. In this work, we propose a new simple way to use them and assess their utility for improving diagnostic accuracy.

MATERIALS AND METHODS

We studied 34 patients with early-onset Alzheimer's disease (EOAD), 49 with late-onset AD (LOAD), 39 with frontotemporal dementia (FTD) and 24 with depression from the pre-existing cohort CLIN-AD. Support vector machine (SVM) automatic classifiers using 3D T1 MRI were trained to distinguish: LOAD vs. Depression, FTD vs. LOAD, EOAD vs. Depression, EOAD vs. FTD. We extracted SVM weight maps, which are tridimensional representations of discriminant atrophy patterns used by the classifier to take its decisions and we printed posters of these maps. Four radiologists (2 senior neuroradiologists and 2 unspecialized junior radiologists) performed a visual classification of the 4 diagnostic pairs using 3D T1 MRI. Classifications were performed twice: first with standard radiological reading and then using SVM weight maps as a guide.

RESULTS

Diagnostic performance was significantly improved by the use of the weight maps for the two junior radiologists in the case of FTD vs. EOAD. Improvement was over 10 points of diagnostic accuracy.

CONCLUSION

This tool can improve the diagnostic accuracy of junior radiologists and could be integrated in the clinical routine workflow.

Towards accurate and unbiased imaging-based differentiation of Parkinson's disease, progressive supranuclear palsy and corticobasal syndrome

The early and accurate differential diagnosis of parkinsonian disorders is still a significant challenge for clinicians. In recent years, a number of studies have used magnetic resonance imaging data combined with machine learning and statistical classifiers to successfully differentiate between different forms of Parkinsonism. However, several questions and methodological issues remain, to minimize bias and artefact-driven classification. In this study, we compared different approaches for feature selection, as well as different magnetic resonance imaging modalities, with well-matched patient groups and tightly controlling for data quality issues related to patient motion. Our sample was drawn from a cohort of 69 healthy controls, and patients with idiopathic Parkinson’s disease (n = 35), progressive supranuclear palsy Richardson’s syndrome (n = 52) and corticobasal syndrome (n = 36). Participants underwent standardized T1-weighted and diffusion-weighted magnetic resonance imaging. Strict data quality control and group matching reduced the control and patient numbers to 43, 32, 33 and 26, respectively. We compared two different methods for feature selection and dimensionality reduction: whole-brain principal components analysis, and an anatomical region-of-interest based approach. In both cases, support vector machines were used to construct a statistical model for pairwise classification of healthy controls and patients. The accuracy of each model was estimated using a leave-two-out cross-validation approach, as well as an independent validation using a different set of subjects. Our cross-validation results suggest that using principal components analysis for feature extraction provides higher classification accuracies when compared to a region-of-interest based approach. However, the differences between the two feature extraction methods were significantly reduced when an independent sample was used for validation, suggesting that the principal components analysis approach may be more vulnerable to overfitting with cross-validation. Both T1-weighted and diffusion magnetic resonance imaging data could be used to successfully differentiate between subject groups, with neither modality outperforming the other across all pairwise comparisons in the cross-validation analysis. However, features obtained from diffusion magnetic resonance imaging data resulted in significantly higher classification accuracies when an independent validation cohort was used. Overall, our results support the use of statistical classification approaches for differential diagnosis of parkinsonian disorders. However, classification accuracy can be affected by group size, age, sex and movement artefacts. With appropriate controls and out-of-sample cross validation, diagnostic biomarker evaluation including magnetic resonance imaging based classifiers may be an important adjunct to clinical evaluation.

Machine Learning Techniques for the Diagnosis of Alzheimer’s Disease

Alzheimer’s disease is an incurable neurodegenerative disease primarily affecting the elderly population. Efficient automated techniques are needed for early diagnosis of Alzheimer’s. Many novel approaches are proposed by researchers for classification of Alzheimer’s disease. However, to develop more efficient learning techniques, better understanding of the work done on Alzheimer’s is needed. Here, we provide a review on 165 papers from 2005 to 2019, using various feature extraction and machine learning techniques. The machine learning techniques are surveyed under three main categories: support vector machine (SVM), artificial neural network (ANN), and deep learning (DL) and ensemble methods. We present a detailed review on these three approaches for Alzheimer’s with possible future directions.

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.

Magnetic Resonance Imaging of Human Olfactory Dysfunction

Olfactory dysfunctions affect a larger portion of population (up to 15% with partial olfactory loss, and 5% with complete olfactory loss) as compared to other sensory dysfunctions (e.g. auditory or visual) and have a negative impact on the life quality. The impairment of olfactory functions may happen at each stage of the olfactory system, from epithelium to cortex. Non-invasive neuroimaging techniques such as the magnetic resonance imaging (MRI) have advanced the understanding of the advent and progress of olfactory dysfunctions in humans. The current review summarizes recent MRI studies on human olfactory dysfunction to present an updated and comprehensive picture of the structural and functional alterations in the central olfactory system as a consequence of olfactory loss and regain. Furthermore, the review also highlights recent progress on optimizing the olfactory functional MRI as well as new approaches for data processing that are promising for future clinical practice.

Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems

Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods. Nevertheless, these methods are inapplicable for small datasets, which are very common in medical problems. To this end, we propose a knowledge transfer method between diseases via the Generative Bayesian Prior network. Our approach is compared to a pre-train approach and random initialization and obtains the best results in terms of Dice Similarity Coefficient metric for the small subsets of the Brain Tumor Segmentation 2018 database (BRATS2018).

Connectivity-based characterisation of subcortical grey matter pathology in frontotemporal dementia and ALS: a multimodal neuroimaging study

Frontotemporal dementia (FTD) phenotypes have distinctive and well-established cortical signatures, but their subcortical grey matter profiles are poorly characterised. The comprehensive characterisation of striatal and thalamic pathology along the ALS-FTD spectrum is particularly timely, as dysfunction of frontostriatal and cortico-thalamic networks contribute to phenotype-defining cognitive, behavioral, and motor deficits. Ten patients with behavioral-variant FTD, 11 patients with non-fluent-variant primary progressive aphasia, 5 patients with semantic-variant primary progressive aphasia, 14 ALS-FTD patients with C9orf72 hexanucleotide expansions, 12 ALS-FTD patients without hexanucleotide repeats, 36 ALS patients without cognitive impairment and 50 healthy controls were included in a prospective neuroimaging study. Striatal, thalamic, hippocampal and amygdala pathology was evaluated using volume measurements, density analyses and connectivity-based segmentation. Significant volume reductions were identified in the thalamus and putamen of non-fluent-variant PPA patients. Marked nucleus accumbens and hippocampal atrophy was observed in the behavioral-variant FTD cohort. Semantic-variant PPA patients only exhibited volumetric changes in the left hippocampus. C9-positive ALS-FTD patients showed preferential density reductions in thalamic sub-regions connected to motor and sensory cortical areas. C9-negative ALS-FTD patients exhibited striatal pathology in sub-regions projecting to rostral-motor and executive cortical areas. The bulk of striatal and thalamic pathology in non-fluent-variant PPA patients was identified in foci projecting to motor areas. Subcortical density alterations in svPPA patients were limited to basal ganglia regions with parietal projections. Striatal and thalamic changes in FTD exhibit selective, network-defined vulnerability patterns mirroring cortical pathology. Multi-modal cortico-basal imaging analyses confirm that the subcortical grey matter profiles of FTD phenotypes are just as distinct as their cortical signatures. Our findings support emerging concepts of network-wise degeneration, preferential circuit vulnerability and disease propagation along connectivity patterns.

Machine learning based hierarchical classification of frontotemporal dementia and Alzheimer's disease

Background

In a clinical setting, an individual subject classification model rather than a group analysis would be more informative. Specifically, the subtlety of cortical atrophy in some frontotemporal dementia (FTD) patients and overlapping patterns of atrophy among three FTD clinical syndromes including behavioral variant FTD (bvFTD), non-fluent/agrammatic variant primary progressive aphasia (nfvPPA), and semantic variant PPA (svPPA) give rise to the need for classification models at the individual level. In this study, we aimed to classify each individual subject into one of the diagnostic categories in a hierarchical manner by employing a machine learning-based classification method.

Methods

We recruited 143 patients with FTD, 50 patients with Alzheimer's disease (AD) dementia, and 146 cognitively normal subjects. All subjects underwent a three-dimensional volumetric brain magnetic resonance imaging (MRI) scan, and cortical thickness was measured using FreeSurfer. We applied the Laplace Beltrami operator to reduce noise in the cortical thickness data and to reduce the dimension of the feature vector. Classifiers were constructed by applying both principal component analysis and linear discriminant analysis to the cortical thickness data. For the hierarchical classification, we trained four classifiers using different pairs of groups: Step 1 - CN vs. FTD + AD, Step 2 - FTD vs. AD, Step 3 - bvFTD vs. PPA, Step 4 - svPPA vs. nfvPPA. To evaluate the classification performance for each step, we used a10-fold cross-validation approach, performed 1000 times for reliability.

Results

The classification accuracy of the entire hierarchical classification tree was 75.8%, which was higher than that of the non-hierarchical classifier (73.0%). The classification accuracies of steps 1–4 were 86.1%, 90.8%, 86.9%, and 92.1%, respectively. Changes in the right frontotemporal area were critical for discriminating behavioral variant FTD from PPA. The left frontal lobe discriminated nfvPPA from svPPA, while the bilateral anterior temporal regions were critical for identifying svPPA.

Conclusions

In the present study, our automated classifier successfully classified FTD clinical subtypes with good to excellent accuracy. Our classifier may help clinicians diagnose FTD subtypes with subtle cortical atrophy and facilitate appropriate specific interventions.

•

We developed a machine learning-based automated classifier for differential diagnosis of FTD clinical syndromes and AD.

•

Our classifier achieved good to excellent accuracy for each classification step.

•

Discriminative regions are similar to previously known cortical atrophic patterns in each clinical syndrome.

Individual Prediction of Behavioral Variant Frontotemporal Dementia Development Using Multivariate Pattern Analysis of Magnetic Resonance Imaging Data

BACKGROUND

Patients with behavioral variant of frontotemporal dementia (bvFTD) initially may only show behavioral and/or cognitive symptoms that overlap with other neurological and psychiatric disorders. The diagnostic accuracy is dependent on progressive symptoms worsening and frontotemporal abnormalities on neuroimaging findings. Predictive biomarkers could facilitate the early detection of bvFTD.

OBJECTIVE

To determine the prognostic accuracy of clinical and structural MRI data using a support vector machine (SVM) classification to predict the 2-year clinical follow-up diagnosis in a group of patients presenting late-onset behavioral changes.

METHODS

Data from 73 patients were included and divided into probable/definite bvFTD (n = 18), neurological (n = 28), and psychiatric (n = 27) groups based on 2-year follow-up diagnosis. Grey-matter volumes were extracted from baseline structural MRI scans. SVM classifiers were used to perform three binary classifications: bvFTD versus neurological and psychiatric, bvFTD versus neurological, and bvFTD versus psychiatric group(s), and one multi-class classification. Classification performance was determined for clinical and neuroimaging data separately and their combination using 5-fold cross-validation.

RESULTS

Accuracy of the binary classification tasks ranged from 72-82% (p < 0.001) with adequate sensitivity (67-79%), specificity (77-88%), and area-under-the-receiver-operator-curve (0.80-0.9). Multi-class accuracy ranged between 55-59% (p < 0.001). The combination of clinical and voxel-wise whole brain data showed the best performance overall.

CONCLUSION

These results show the potential for automated early confirmation of diagnosis for bvFTD using machine learning analysis of clinical and neuroimaging data in a diverse and clinically relevant sample of patients.

Harnessing the Power of Machine Learning in Dementia Informatics Research: Issues, Opportunities, and Challenges

Dementia is a chronic and degenerative condition affecting millions globally. The care of patients with dementia presents an ever-continuing challenge to healthcare systems in the 21st century. Medical and health sciences have generated unprecedented volumes of data related to health and wellbeing for patients with dementia due to advances in information technology, such as genetics, neuroimaging, cognitive assessment, free texts, routine electronic health records, etc. Making the best use of these diverse and strategic resources will lead to high-quality care of patients with dementia. As such, machine learning becomes a crucial factor in achieving this objective. The aim of this paper is to provide a state-of-the-art review of machine learning methods applied to health informatics for dementia care. We collate and review the existing scientific methodologies and identify the relevant issues and challenges when faced with big health data. Machine learning has demonstrated promising applications to neuroimaging data analysis for dementia care, while relatively less effort has been made to make use of integrated heterogeneous data via advanced machine learning approaches. We further indicate future potential and research directions in applying advanced machine learning, such as deep learning, to dementia informatics.

Single-subject classification of presymptomatic frontotemporal dementia mutation carriers using multimodal MRI

BACKGROUND

Classification models based on magnetic resonance imaging (MRI) may aid early diagnosis of frontotemporal dementia (FTD) but have only been applied in established FTD cases. Detection of FTD patients in earlier disease stages, such as presymptomatic mutation carriers, may further advance early diagnosis and treatment. In this study, we aim to distinguish presymptomatic FTD mutation carriers from controls on an individual level using multimodal MRI-based classification.

METHODS

Anatomical MRI, diffusion tensor imaging (DTI) and resting-state functional MRI data were collected in 55 presymptomatic FTD mutation carriers (8 microtubule-associated protein Tau, 35 progranulin, and 12 chromosome 9 open reading frame 72) and 48 familial controls. We calculated grey and white matter density features from anatomical MRI scans, diffusivity features from DTI, and functional connectivity features from resting-state functional MRI. These features were applied in a recently introduced multimodal behavioural variant FTD (bvFTD) classification model, and were subsequently used to train and test unimodal and multimodal carrier-control models. Classification performance was quantified using area under the receiver operator characteristic curves (AUC).

RESULTS

The bvFTD model was not able to separate presymptomatic carriers from controls beyond chance level (AUC = 0.582, p = 0.078). In contrast, one unimodal and several multimodal carrier-control models performed significantly better than chance level. The unimodal model included the radial diffusivity feature and had an AUC of 0.642 (p = 0.032). The best multimodal model combined radial diffusivity and white matter density features (AUC = 0.684, p = 0.004).

CONCLUSIONS

FTD mutation carriers can be separated from controls with a modest AUC even before symptom-onset, using a newly created carrier-control classification model, while this was not possible using a recent bvFTD classification model. A multimodal MRI-based classification score may therefore be a useful biomarker to aid earlier FTD diagnosis. The exclusive selection of white matter features in the best performing model suggests that the earliest FTD-related pathological processes occur in white matter.

In vivo hippocampal subfield shape related to TDP-43, amyloid beta, and tau pathologies

Despite advances in the development of biomarkers for Alzheimer's disease (AD), accurate ante-mortem diagnosis remains challenging because a variety of neuropathologic disease states can coexist and contribute to the AD dementia syndrome. Here, we report a neuroimaging study correlating hippocampal deformity with regional AD and transactive response DNA-binding protein of 43 kDA pathology burden. We used hippocampal shape analysis of ante-mortem T1-weighted structural magnetic resonance imaging images of 42 participants from two longitudinal cohort studies conducted by the Rush Alzheimer's Disease Center. Surfaces were generated for the whole hippocampus and zones approximating the underlying subfields using a previously developed automated image-segmentation pipeline. Multiple linear regression models were constructed to correlate the shape with pathology measures while accounting for covariates, with relationships mapped out onto hippocampal surface locations. A significant relationship existed between higher paired helical filaments-tau burden and inward hippocampal shape deformity in zones approximating CA1 and subiculum which persisted after accounting for coexisting pathologies. No significant patterns of inward surface deformity were associated with amyloid-beta or transactive response DNA-binding protein of 43 kDA after including covariates. Our findings indicate that hippocampal shape deformity measures in surface zones approximating CA1 may represent a biomarker for postmortem AD pathology.

A Comparative Atlas-Based Recognition of Mild Cognitive Impairment With Voxel-Based Morphometry

An accurate and reliable brain partition atlas is vital to quantitatively investigate the structural and functional abnormalities in mild cognitive impairment (MCI), generally considered to be a prodromal phase of Alzheimer's disease. In this paper, we proposed an automated structural classification method to identify MCI from healthy controls (HC) and investigated whether the classification performance was dependent on the brain parcellation schemes, including Automated Anatomical Labeling (AAL-90) atlas, Brainnetome (BN-246) atlas, and AAL-1024 atlas. In detail, structural magnetic resonance imaging (sMRI) data of 69 MCI patients and 63 HC matched well on gender, age, and education level were collected and analyzed with voxel-based morphometry method first, then the volume features of every region of interest (ROI) belonging to the above-mentioned three atlases were calculated and compared between MCI and HC groups, respectively. At last, the abnormal volume features were selected as the classification features for a proposed support vector machine based identification method. After the leave-one-out cross-validation to estimate the classification performance, our results reported accuracies of 83, 92, and 89% with AAL-90, BN-246, and AAL-1024 atlas, respectively, suggesting that future studies should pay more attention to the selection of brain partition schemes in the atlas-based studies. Furthermore, the consistent atrophic brain regions among three atlases were predominately located at bilateral hippocampus, bilateral parahippocampal, bilateral amygdala, bilateral cingulate gyrus, left angular gyrus, right superior frontal gyrus, right middle frontal gyrus, left inferior frontal gyrus, and left precentral gyrus.

Voxel-wise deviations from healthy aging for the detection of region-specific atrophy

The identification of pathological atrophy in MRI scans requires specialized training, which is scarce outside dedicated centers. We sought to investigate the clinical usefulness of computer-generated representations of local grey matter (GM) loss or increased volume of cerebral fluids (CSF) as normalized deviations (z-scores) from healthy aging to either aid human visual readings or directly detect pathological atrophy.

Two experienced neuroradiologists rated atrophy in 30 patients with Alzheimer's disease (AD), 30 patients with frontotemporal dementia (FTD), 30 with dementia due to Lewy-body disease (LBD) and 30 healthy controls (HC) on a three-point scale in 10 anatomical regions as reference gold standard. Seven raters, varying in their experience with MRI diagnostics rated all cases on the same scale once with and once without computer-generated volume deviation maps that were overlaid on anatomical slices. In addition, we investigated the predictive value of the computer generated deviation maps on their own for the detection of atrophy as identified by the gold standard raters.

Inter and intra-rater agreements of the two gold standard raters were substantial (Cohen's kappa κ > 0.62). The intra-rater agreement of the other raters ranged from fair (κ = 0.37) to substantial (κ = 0.72) and improved on average by 0.13 (0.57 < κ < 0.87) when volume deviation maps were displayed. The seven other raters showed good agreement with the gold standard in regions including the hippocampus but agreement was substantially lower in e.g. the parietal cortex and did not improve with the display of atrophy scores. Rating speed increased over the course of the study and irrespective of the presentation of voxel-wise deviations.

Automatically detected large deviations of local volume were consistently associated with gold standard atrophy reading as shown by an area under the receiver operator characteristic of up to 0.95 for the hippocampus region. When applying these test characteristics to prevalences typically found in a memory clinic, we observed a positive or negative predictive value close to or above 0.9 in the hippocampus for almost all of the expected cases. The volume deviation maps derived from CSF volume increase were generally better in detecting atrophy.

Our study demonstrates an agreement of visual ratings among non-experts not further increased by displaying, region-specific deviations of volume. The high predictive value of computer generated local deviations independent from human interaction and the consistent advantages of CSF-over GM-based estimations should be considered in the development of diagnostic tools and indicate clinical utility well beyond aiding visual assessments.

•

The visual identification of atrophy is most accurate in the temporal lobe.

•

Voxel-wise deviations of tissue volume from normal aging is easy to implement.

•

Displaying voxel-wise deviations subjectively but not objectively aids readers.

•

Voxel-wise deviations themselves show high agreement with expert readings.

•

Information on tissue deviations should be provided with cerebral MRI scans.

Morphometric MRI as a diagnostic biomarker of frontotemporal dementia: A systematic review to determine clinical applicability

Frontotemporal dementia (FTD) is difficult to diagnose, due to its heterogeneous nature and overlap in symptoms with primary psychiatric disorders. Brain MRI for atrophy is a key biomarker but lacks sensitivity in the early stage. Morphometric MRI-based measures and machine learning techniques are a promising tool to improve diagnostic accuracy. Our aim was to review the current state of the literature using morphometric MRI to classify FTD and assess its applicability for clinical practice. A search was completed using Pubmed and PsychInfo of studies which conducted a classification of subjects with FTD from non-FTD (controls or another disorder) using morphometric MRI metrics on an individual level, using single or combined approaches. 28 relevant articles were included and systematically reviewed following PRISMA guidelines. The studies were categorized based on the type of FTD subjects included and the group(s) against which they were classified. Studies varied considerably in subject selection, MRI methodology, and classification approach, and results are highly heterogeneous. Overall many studies indicate good diagnostic accuracy, with higher performance when differentiating FTD from controls (highest result was accuracy of 100%) than other dementias (highest result was AUC of 0.874). Very few machine learning algorithms have been tested in prospective replication. In conclusion, morphometric MRI with machine learning shows potential as an early diagnostic biomarker of FTD, however studies which use rigorous methodology and validate findings in an independent real-life cohort are necessary before this method can be recommended for use clinically.

Single-subject classification of presymptomatic frontotemporal dementia mutation carriers using multimodal MRI

Background

Classification models based on magnetic resonance imaging (MRI) may aid early diagnosis of frontotemporal dementia (FTD) but have only been applied in established FTD cases. Detection of FTD patients in earlier disease stages, such as presymptomatic mutation carriers, may further advance early diagnosis and treatment. In this study, we aim to distinguish presymptomatic FTD mutation carriers from controls on an individual level using multimodal MRI-based classification.

Methods

Anatomical MRI, diffusion tensor imaging (DTI) and resting-state functional MRI data were collected in 55 presymptomatic FTD mutation carriers (8 microtubule-associated protein Tau, 35 progranulin, and 12 chromosome 9 open reading frame 72) and 48 familial controls. We calculated grey and white matter density features from anatomical MRI scans, diffusivity features from DTI, and functional connectivity features from resting-state functional MRI. These features were applied in a recently introduced multimodal behavioural variant FTD (bvFTD) classification model, and were subsequently used to train and test unimodal and multimodal carrier-control models. Classification performance was quantified using area under the receiver operator characteristic curves (AUC).

Results

The bvFTD model was not able to separate presymptomatic carriers from controls beyond chance level (AUC = 0.570, p = 0.11). In contrast, one unimodal and several multimodal carrier-control models performed significantly better than chance level. The unimodal model included the radial diffusivity feature and had an AUC of 0.646 (p = 0.021). The best multimodal model combined radial diffusivity and white matter density features (AUC = 0.680, p = 0.005).

Conclusions

FTD mutation carriers can be separated from controls with a modest AUC even before symptom-onset, using a newly created carrier-control classification model, while this was not possible using a recent bvFTD classification model. A multimodal MRI-based classification score may therefore be a useful biomarker to aid earlier FTD diagnosis. The exclusive selection of white matter features in the best performing model suggests that the earliest FTD-related pathological processes occur in white matter.

Data-Driven Differential Diagnosis of Dementia Using Multiclass Disease State Index Classifier

Clinical decision support systems (CDSSs) hold potential for the differential diagnosis of neurodegenerative diseases. We developed a novel CDSS, the PredictND tool, designed for differential diagnosis of different types of dementia. It combines information obtained from multiple diagnostic tests such as neuropsychological tests, MRI and cerebrospinal fluid samples. Here we evaluated how the classifier used in it performs in differentiating between controls with subjective cognitive decline, dementia due to Alzheimer's disease, vascular dementia, frontotemporal lobar degeneration and dementia with Lewy bodies. We used the multiclass Disease State Index classifier, which is the classifier used by the PredictND tool, to differentiate between controls and patients with the four different types of dementia. The multiclass Disease State Index classifier is an extension of a previously developed two-class Disease State Index classifier. As the two-class Disease State Index classifier, the multiclass Disease State Index classifier also offers a visualization of its decision making process, which makes it especially suitable for medical decision support where interpretability of the results is highly important. A subset of the Amsterdam Dementia cohort, consisting of 504 patients (age 65 ± 8 years, 44% females) with data from neuropsychological tests, cerebrospinal fluid samples and both automatic and visual MRI quantifications, was used for the evaluation. The Disease State Index classifier was highly accurate in separating the five classes from each other (balanced accuracy 82.3%). Accuracy was highest for vascular dementia and lowest for dementia with Lewy bodies. For the 50% of patients for which the classifier was most confident on the classification the balanced accuracy was 93.6%. Data-driven CDSSs can be of aid in differential diagnosis in clinical practice. The decision support system tested in this study was highly accurate in separating the different dementias and controls from each other. In addition to the predicted class, it also provides a confidence measure for the classification.

Separating Symptomatic Alzheimer's Disease from Depression based on Structural MRI

Older patients with depression or Alzheimer’s disease (AD) at the stage of early dementia or mild cognitive impairment may present with objective cognitive impairment, although the pathology and thus therapy and prognosis differ substantially. In this study, we assessed the potential of an automated algorithm to categorize a test set of 65 T1-weighted structural magnetic resonance images (MRI). A convenience sample of elderly individuals fulfilling clinical criteria of either AD (n = 28) or moderate and severe depression (n = 37) was recruited from different settings to assess the potential of the pattern recognition method to assist in the differential diagnosis of AD versus depression. We found that our algorithm learned discriminative patterns in the subject’s grey matter distribution reflected by an area under the receiver operator characteristics curve of up to 0.83 (confidence interval ranged from 0.67 to 0.92) and a balanced accuracy of 0.79 for the separation of depression from AD, evaluated by leave-one-out cross validation. The algorithm also identified consistent structural differences in a clinically more relevant scenario where the data used during training were independent from the data used for evaluation and, critically, which included five possible diagnoses (specifically AD, frontotemporal dementia, Lewy body dementia, depression, and healthy aging). While the output was insufficiently accurate to use it directly as a means for classification when multiple classes are possible, the continuous output computed by the machine learning algorithm differed between the two groups that were investigated. The automated analysis thus could complement, but not replace clinical assessments.

Biomarkers in Alzheimer's, Frontotemporal, Lewy Body, and Vascular Dementias

This article reviews the current evidence base for biomarkers of the most common causes of dementia in later life: Alzheimer's disease (AD), frontotemporal lobar degenerations, Lewy body dementias, and vascular cognitive impairment and dementia. Biomarkers are objectively measurable indicators of normal physiology, pathological processes, or response to an intervention. Ideally, they are sensitive, specific, easy to obtain, and closely reflect the underlying biological processes of interest. While such markers are well established and in broad clinical use for common disorders in general medicine (e.g., thallium stress tests for coronary artery disease or serum blood urea nitrogen and creatinine for renal failure), analogous, validated markers for AD or other common dementias are limited, although biomarkers in research settings and specialty dementia clinics are progressing toward clinical use. By way of introducing current and future biomarkers for dementias of later life, this article will benefit the practicing clinician by increasing awareness of the availability and utility of current and emerging biomarkers in dementia diagnosis and prognosis and for monitoring new disease-modifying therapeutics that arrive in the clinic over the coming decade.

Machine Learning-based Individual Assessment of Cortical Atrophy Pattern in Alzheimer's Disease Spectrum: Development of the Classifier and Longitudinal Evaluation

To develop a new method for measuring Alzheimer's disease (AD)-specific similarity of cortical atrophy patterns at the individual-level, we employed an individual-level machine learning algorithm. A total of 869 cognitively normal (CN) individuals and 473 patients with probable AD dementia who underwent high-resolution 3T brain MRI were included. We propose a machine learning-based method for measuring the similarity of an individual subject's cortical atrophy pattern with that of a representative AD patient cohort. In addition, we validated this similarity measure in two longitudinal cohorts consisting of 79 patients with amnestic-mild cognitive impairment (aMCI) and 27 patients with probable AD dementia. Surface-based morphometry classifier for discriminating AD from CN showed sensitivity and specificity values of 87.1% and 93.3%, respectively. In the longitudinal validation study, aMCI-converts had higher atrophy similarity at both baseline (p < 0.001) and first year visits (p < 0.001) relative to non-converters. Similarly, AD patients with faster decline had higher atrophy similarity than slower decliners at baseline (p = 0.042), first year (p = 0.028), and third year visits (p = 0.027). The AD-specific atrophy similarity measure is a novel approach for the prediction of dementia risk and for the evaluation of AD trajectories on an individual subject level.

Addressing Confounding in Predictive Models with an Application to Neuroimaging

Understanding structural changes in the brain that are caused by a particular disease is a major goal of neuroimaging research. Multivariate pattern analysis (MVPA) comprises a collection of tools that can be used to understand complex disease efxcfects across the brain. We discuss several important issues that must be considered when analyzing data from neuroimaging studies using MVPA. In particular, we focus on the consequences of confounding by non-imaging variables such as age and sex on the results of MVPA. After reviewing current practice to address confounding in neuroimaging studies, we propose an alternative approach based on inverse probability weighting. Although the proposed method is motivated by neuroimaging applications, it is broadly applicable to many problems in machine learning and predictive modeling. We demonstrate the advantages of our approach on simulated and real data examples.

Towards affordable biomarkers of frontotemporal dementia: A classification study via network's information sharing

Developing effective and affordable biomarkers for dementias is critical given the difficulty to achieve early diagnosis. In this sense, electroencephalographic (EEG) methods offer promising alternatives due to their low cost, portability, and growing robustness. Here, we relied on EEG signals and a novel information-sharing method to study resting-state connectivity in patients with behavioral variant frontotemporal dementia (bvFTD) and controls. To evaluate the specificity of our results, we also tested Alzheimer’s disease (AD) patients. The classification power of the ensuing connectivity patterns was evaluated through a supervised classification algorithm (support vector machine). In addition, we compared the classification power yielded by (i) functional connectivity, (ii) relevant neuropsychological tests, and (iii) a combination of both. BvFTD patients exhibited a specific pattern of hypoconnectivity in mid-range frontotemporal links, which showed no alterations in AD patients. These functional connectivity alterations in bvFTD were replicated with a low-density EEG setting (20 electrodes). Moreover, while neuropsychological tests yielded acceptable discrimination between bvFTD and controls, the addition of connectivity results improved classification power. Finally, classification between bvFTD and AD patients was better when based on connectivity than on neuropsychological measures. Taken together, such findings underscore the relevance of EEG measures as potential biomarker signatures for clinical settings.

Five-class differential diagnostics of neurodegenerative diseases using random undersampling boosting

Differentiating between different types of neurodegenerative diseases is not only crucial in clinical practice when treatment decisions have to be made, but also has a significant potential for the enrichment of clinical trials. The purpose of this study is to develop a classification framework for distinguishing the four most common neurodegenerative diseases, including Alzheimer's disease, frontotemporal lobe degeneration, Dementia with Lewy bodies and vascular dementia, as well as patients with subjective memory complaints. Different biomarkers including features from images (volume features, region-wise grading features) and non-imaging features (CSF measures) were extracted for each subject. In clinical practice, the prevalence of different dementia types is imbalanced, posing challenges for learning an effective classification model. Therefore, we propose the use of the RUSBoost algorithm in order to train classifiers and to handle the class imbalance training problem. Furthermore, a multi-class feature selection method based on sparsity is integrated into the proposed framework to improve the classification performance. It also provides a way for investigating the importance of different features and regions. Using a dataset of 500 subjects, the proposed framework achieved a high accuracy of 75.2% with a balanced accuracy of 69.3% for the five-class classification using ten-fold cross validation, which is significantly better than the results using support vector machine or random forest, demonstrating the feasibility of the proposed framework to support clinical decision making.