Differentiating Dementia with Lewy Bodies and Alzheimer's Disease by Deep Learning to Structural MRI

Understanding machine learning applications in dementia research and clinical practice: a review for biomedical scientists and clinicians

Several (inter)national longitudinal dementia observational datasets encompassing demographic information, neuroimaging, biomarkers, neuropsychological evaluations, and muti-omics data, have ushered in a new era of potential for integrating machine learning (ML) into dementia research and clinical practice. ML, with its proficiency in handling multi-modal and high-dimensional data, has emerged as an innovative technique to facilitate early diagnosis, differential diagnosis, and to predict onset and progression of mild cognitive impairment and dementia. In this review, we evaluate current and potential applications of ML, including its history in dementia research, how it compares to traditional statistics, the types of datasets it uses and the general workflow. Moreover, we identify the technical barriers and challenges of ML implementations in clinical practice. Overall, this review provides a comprehensive understanding of ML with non-technical explanations for broader accessibility to biomedical scientists and clinicians.

AI-based differential diagnosis of dementia etiologies on multimodal data

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an artificial intelligence (AI) model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a microaveraged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the microaveraged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in clinical settings and drug trials. Further prospective studies are needed to confirm its ability to improve patient care.

AI-based differential diagnosis of dementia etiologies on multimodal data

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an AI model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations, and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a micro-averaged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the micro-averaged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in various clinical settings and drug trials, with promising implications for person-level management.

A 3D convolutional neural network to classify subjects as Alzheimer's disease, frontotemporal dementia or healthy controls using brain 18F-FDG PET

With the arrival of disease-modifying drugs, neurodegenerative diseases will require an accurate diagnosis for optimal treatment. Convolutional neural networks are powerful deep learning techniques that can provide great help to physicians in image analysis. The purpose of this study is to introduce and validate a 3D neural network for classification of Alzheimer's disease (AD), frontotemporal dementia (FTD) or cognitively normal (CN) subjects based on brain glucose metabolism. Retrospective [18F]-FDG-PET scans of 199 CE, 192 FTD and 200 CN subjects were collected from our local database, Alzheimer's disease and frontotemporal lobar degeneration neuroimaging initiatives. Training and test sets were created using randomization on a 90 %-10 % basis, and training of a 3D VGG16-like neural network was performed using data augmentation and cross-validation. Performance was compared to clinical interpretation by three specialists in the independent test set. Regions determining classification were identified in an occlusion experiment and Gradient-weighted Class Activation Mapping. Test set subjects were age- and sex-matched across categories. The model achieved an overall 89.8 % accuracy in predicting the class of test scans. Areas under the ROC curves were 93.3 % for AD, 95.3 % for FTD, and 99.9 % for CN. The physicians' consensus showed a 69.5 % accuracy, and there was substantial agreement between them (kappa = 0.61, 95 % CI: 0.49-0.73). To our knowledge, this is the first study to introduce a deep learning model able to discriminate AD and FTD based on [18F]-FDG PET scans, and to isolate CN subjects with excellent accuracy. These initial results are promising and hint at the potential for generalization to data from other centers.

Parkinson's Disease and Dementia with Lewy Bodies: One and the Same

The question whether Parkinson's disease dementia (PDD) and dementia with Lewy bodies (DLB) are expressions of the same underlying disease has been vigorously debated for decades. The recently proposed biological definitions of Lewy body disease, which do not assign any particular importance to the dopamine system over other degenerating neurotransmitter systems, has once more brought the discussion about different types of Lewy body disease to the forefront. Here, we briefly compare PDD and DLB in terms of their symptoms, imaging findings, and neuropathology, ultimately finding them to be indistinguishable. We then present a conceptual framework to demonstrate how one can view different clinical syndromes as manifestations of a shared underlying Lewy body disease. Early Parkinson's disease, isolated RBD, pure autonomic failure and other autonomic symptoms, and perhaps even psychiatric symptoms, represent diverse manifestations of the initial clinical stages of Lewy body disease. They are characterized by heterogeneous and comparatively limited neuronal dysfunction and damage. In contrast, Lewy body dementia, an encompassing term for both PDD and DLB, represents a more uniform and advanced stage of the disease. Patients in this category display extensive and severe Lewy pathology, frequently accompanied by co-existing pathologies, as well as multi-system neuronal dysfunction and degeneration. Thus, we propose that Lewy body disease should be viewed as a single encompassing disease entity. Phenotypic variance is caused by the presence of individual risk factors, disease mechanisms, and co-pathologies. Distinct subtypes of Lewy body disease can therefore be defined by subtype-specific disease mechanisms or biomarkers.

Correlation transfer function analysis as a biomarker for Alzheimer brain plasticity using longitudinal resting-state fMRI data

Neural plasticity is the ability of the brain to alter itself functionally and structurally as a result of its experience. However, longitudinal changes in functional connectivity of the brain are still unrevealed in Alzheimer's disease (AD). This study aims to discover the significant connections (SCs) between brain regions for AD stages longitudinally using correlation transfer function (CorrTF) as a new biomarker for the disease progression. The dataset consists of: 29 normal controls (NC), and 23, 24, and 23 for early, late mild cognitive impairments (EMCI, LMCI), and ADs, respectively, along three distant visits. The brain was divided into 116 regions using the automated anatomical labeling atlas, where the intensity time series is calculated, and the CorrTF connections are extracted for each region. Finally, the standard t-test and ANOVA test were employed to investigate the SCs for each subject's visit. No SCs, along three visits, were found For NC subjects. The most SCs were mainly directed from cerebellum in case of EMCI and LMCI. Furthermore, the hippocampus connectivity increased in LMCI compared to EMCI whereas missed in AD. Additionally, the patterns of longitudinal changes among the different AD stages compared to Pearson Correlation were similar, for SMC, VC, DMN, and Cereb networks, while differed for EAN and SN networks. Our findings define how brain changes over time, which could help detect functional changes linked to each AD stage and better understand the disease behavior.

Microglia in neurodegenerative diseases: mechanism and potential therapeutic targets

Microglia activation is observed in various neurodegenerative diseases. Recent advances in single-cell technologies have revealed that these reactive microglia were with high spatial and temporal heterogeneity. Some identified microglia in specific states correlate with pathological hallmarks and are associated with specific functions. Microglia both exert protective function by phagocytosing and clearing pathological protein aggregates and play detrimental roles due to excessive uptake of protein aggregates, which would lead to microglial phagocytic ability impairment, neuroinflammation, and eventually neurodegeneration. In addition, peripheral immune cells infiltration shapes microglia into a pro-inflammatory phenotype and accelerates disease progression. Microglia also act as a mobile vehicle to propagate protein aggregates. Extracellular vesicles released from microglia and autophagy impairment in microglia all contribute to pathological progression and neurodegeneration. Thus, enhancing microglial phagocytosis, reducing microglial-mediated neuroinflammation, inhibiting microglial exosome synthesis and secretion, and promoting microglial conversion into a protective phenotype are considered to be promising strategies for the therapy of neurodegenerative diseases. Here we comprehensively review the biology of microglia and the roles of microglia in neurodegenerative diseases, including Alzheimer's disease, Parkinson's disease, multiple system atrophy, amyotrophic lateral sclerosis, frontotemporal dementia, progressive supranuclear palsy, corticobasal degeneration, dementia with Lewy bodies and Huntington's disease. We also summarize the possible microglia-targeted interventions and treatments against neurodegenerative diseases with preclinical and clinical evidence in cell experiments, animal studies, and clinical trials.

Sex differences in dementia with Lewy bodies: Focused review of available evidence and future directions

In this review, we summarize the current knowledge on sex differences in dementia with Lewy bodies (DLB) relating to epidemiology, clinical features, neuropathology, biomarkers, disease progression, and caregiving. While many studies show a higher DLB prevalence in men, this finding is inconsistent and varies by study approach. Visual hallucinations may be more common and occur earlier in women with DLB, whereas REM sleep behavior disorder may be more common and occur earlier in men. Several studies report a higher frequency of parkinsonism in men with DLB, while the frequency of fluctuations appears similar between sexes. Women tend to be older, have greater cognitive impairment at their initial visit, and are delayed in meeting DLB criteria compared to men. Women are also more likely to have Lewy body disease with co-existing AD-related pathology than so-called "pure" Lewy body disease, while men may present with either. Research is mixed regarding the impact of sex on DLB progression. Biomarker and treatment research assessing for sex differences is lacking. Women provide the majority of caregiving in DLB but how this affects the caregiving experience is uncertain. Gaining a better understanding of sex differences will be instrumental in aiding future development of sex-specific strategies in DLB for early diagnosis, care, and drug development.

Improving across-dataset brain tissue segmentation for MRI imaging using transformer

Brain tissue segmentation has demonstrated great utility in quantifying MRI data by serving as a precursor to further post-processing analysis. However, manual segmentation is highly labor-intensive, and automated approaches, including convolutional neural networks (CNNs), have struggled to generalize well due to properties inherent to MRI acquisition, leaving a great need for an effective segmentation tool. This study introduces a novel CNN-Transformer hybrid architecture designed to improve brain tissue segmentation by taking advantage of the increased performance and generality conferred by Transformers for 3D medical image segmentation tasks. We first demonstrate the superior performance of our model on various T1w MRI datasets. Then, we rigorously validate our model's generality applied across four multi-site T1w MRI datasets, covering different vendors, field strengths, scan parameters, and neuropsychiatric conditions. Finally, we highlight the reliability of our model on test-retest scans taken in different time points. In all situations, our model achieved the greatest generality and reliability compared to the benchmarks. As such, our method is inherently robust and can serve as a valuable tool for brain related T1w MRI studies. The code for the TABS network is available at: https://github.com/raovish6/TABS.

Deep networks for behavioral variant frontotemporal dementia identification from multiple acquisition sources

Behavioral variant frontotemporal dementia (bvFTD) is a neurodegenerative syndrome whose clinical diagnosis remains a challenging task especially in the early stage of the disease. Currently, the presence of frontal and anterior temporal lobe atrophies on magnetic resonance imaging (MRI) is part of the diagnostic criteria for bvFTD. However, MRI data processing is usually dependent on the acquisition device and mostly require human-assisted crafting of feature extraction. Following the impressive improvements of deep architectures, in this study we report on bvFTD identification using various classes of artificial neural networks, and present the results we achieved on classification accuracy and obliviousness on acquisition devices using extensive hyperparameter search. In particular, we will demonstrate the stability and generalization of different deep networks based on the attention mechanism, where data intra-mixing confers models the ability to identify the disorder even on MRI data in inter-device settings, i.e., on data produced by different acquisition devices and without model fine tuning, as shown from the very encouraging performance evaluations that dramatically reach and overcome the 90% value on the AuROC and balanced accuracy metrics.

Distinguishing Lewy Body Dementia from Alzheimer's Disease using Machine Learning on Heterogeneous Data: A Feasibility Study

Dementia with Lewy Bodies (DLB) is the second most common form of dementia, but diagnostic markers for DLB can be expensive and inaccessible, and many cases of DLB are undiagnosed. This work applies machine learning techniques to determine the feasibility of distinguishing DLB from Alzheimer's Disease (AD) using heterogeneous data features. The Repeated Incremental Pruning to Produce Error Reduction (RIPPER) algorithm was first applied using a Leave-One-Out Cross-Validation protocol to a dataset comprising DLB and AD cases. Then, interpretable association rule-based diagnostic classifiers were obtained for distinguishing DLB from AD. The various diagnostic classifiers generated by this process had high accuracy over the whole dataset (mean accuracy of 94%). The mean accuracy in classifying their out-of-sample case was 80.5%. Every classifier generated consisted of very simple structure, each using 1-2 classification rules and 1-3 data features. As a group, the classifiers were heterogeneous and used several different data features. In particular, some of the classifiers used very simple and inexpensive diagnostic features, yet with high diagnostic accuracy. This work suggests that opportunities may exist for incorporating accessible diagnostic assessments while improving diagnostic rate for DLB. Clinical Relevance- Simple and interpretable high-performing machine learning algorithms identified a variety of readily available clinical assessments for differential diagnosis of dementia offering the opportunities to incorporate various simple and inexpensive screening tests for DLB and addressing the problem of DLB underdiagnosis.

Multimodal deep learning for Alzheimer's disease dementia assessment

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer's disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.

Neuroimaging alterations in dementia with Lewy bodies and neuroimaging differences between dementia with Lewy bodies and Alzheimer's disease: An activation likelihood estimation meta-analysis

Aims

The aim of this study was to identify brain regions with local, structural, and functional abnormalities in dementia with Lewy bodies (DLB) and uncover the differences between DLB and Alzheimer's disease (AD). The neural networks involved in the identified abnormal brain regions were further described.

Methods

PubMed, Web of Science, OVID, Science Direct, and Cochrane Library databases were used to identify neuroimaging studies that included DLB versus healthy controls (HCs) or DLB versus AD. The coordinate‐based meta‐analysis and functional meta‐analytic connectivity modeling were performed using the activation likelihood estimation algorithm.

Results

Eleven structural studies and fourteen functional studies were included in this quantitative meta‐analysis. DLB patients showed a dysfunction in the bilateral inferior parietal lobule and right lingual gyrus compared with HC patients. DLB patients showed a relative preservation of the medial temporal lobe and a tendency of lower metabolism in the right lingual gyrus compared with AD. The frontal‐parietal, salience, and visual networks were all abnormally co‐activated in DLB, but the default mode network remained normally co‐activated compared with AD.

Conclusions

The convergence of local brain regions and co‐activation neural networks might be potential specific imaging markers in the diagnosis of DLB. This might provide a pathway for the neural regulation in DLB patients, and it might contribute to the development of specific interventions for DLB and AD.

Data-driven approaches to neuroimaging biomarkers for neurological and psychiatric disorders: emerging approaches and examples

PURPOSE OF REVIEW

The 'holy grail' of clinical applications of neuroimaging to neurological and psychiatric disorders via personalized biomarkers has remained mostly elusive, despite considerable effort. However, there are many reasons to continue to be hopeful, as the field has made remarkable advances over the past few years, fueled by a variety of converging technical and data developments.

RECENT FINDINGS

We discuss a number of advances that are accelerating the push for neuroimaging biomarkers including the advent of the 'neuroscience big data' era, biomarker data competitions, the development of more sophisticated algorithms including 'guided' data-driven approaches that facilitate automation of network-based analyses, dynamic connectivity, and deep learning. Another key advance includes multimodal data fusion approaches which can provide convergent and complementary evidence pointing to possible mechanisms as well as increase predictive accuracy.

SUMMARY

The search for clinically relevant neuroimaging biomarkers for neurological and psychiatric disorders is rapidly accelerating. Here, we highlight some of these aspects, provide recent examples from studies in our group, and link to other ongoing work in the field. It is critical that access and use of these advanced approaches becomes mainstream, this will help propel the community forward and facilitate the production of robust and replicable neuroimaging biomarkers.

Update on neuroimaging in non-Alzheimer's disease dementia: a focus on the Lewy body disease spectrum

PURPOSE OF REVIEW

An accurate differential diagnosis between Alzheimer's disease (AD) and non-AD dementia is of paramount importance to study disease mechanisms, define prognosis, and select patients for disease-specific treatments. The purpose of the present review is to describe the most recent neuroimaging studies in Lewy body disease spectrum (LBDS), focusing on differences with AD.

RECENT FINDINGS

Different neuroimaging methods are used to investigate patterns of alterations, which can be helpful to distinguish LBDS from AD. Positron emission tomography radiotracers and advanced MRI structural and functional methods discriminate these two conditions with increasing accuracy. Prodromal disease stages can be identified, allowing an increasingly earlier diagnosis.

SUMMARY

Neuroimaging biomarkers can aid in obtaining the best diagnostic accuracy in LBDS. Despite the main role of neuroimaging in clinical setting is to exclude secondary causes of dementia, structural and metabolic imaging techniques give an essential help to study in-vivo pathophysiological mechanisms of diseases. The importance of neuroimaging in LBDS is given by the increasing number of imaging biomarker developed and studied in the last years.