Multicenter stability of resting state fMRI in the detection of Alzheimer's disease and amnestic MCI

Aberrant functional connectivity between the retrosplenial cortex and hippocampal subregions in amnestic mild cognitive impairment and Alzheimer's disease

The posterior cingulate cortex and hippocampus are the core regions involved in episodic memory, and they exhibit functional connectivity changes in the development and progression of Alzheimer's disease. Previous studies have demonstrated that the posterior cingulate cortex and hippocampus are both cytoarchitectonically heterogeneous regions. Specifically, the retrosplenial cortex, typically subsumed under the posterior cingulate cortex, is an area functionally and anatomically distinct from the posterior cingulate cortex, and the hippocampus is composed of several subregions that participate in multiple cognitive processes. However, little is known about the functional connectivity patterns of the retrosplenial cortex or other parts of the posterior cingulate cortex with hippocampal subregions and their differential vulnerability to Alzheimer's disease pathology. Demographic data, neuropsychological assessments, and resting-state functional magnetic resonance imaging data were collected from 60 Alzheimer's disease participants, 60 participants with amnestic mild cognitive impairment, and 60 sex-matched normal controls. The bilateral retrosplenial cortex, other parts of the posterior cingulate cortex, and hippocampus subregions (including the bilateral anterior hippocampus and posterior hippocampus) were selected to investigate functional connectivity alterations in amnestic mild cognitive impairment and Alzheimer's disease. Resting-state functional connectivity analysis demonstrated heterogeneity in the degree of connectivity between the hippocampus and different parts of the total posterior cingulate cortex, with considerably greater functional connectivity of the retrosplenial cortex with the hippocampus compared with other parts of the posterior cingulate cortex. Furthermore, the bilateral retrosplenial cortex exhibited widespread intrinsic functional connectivity with all anterior-posterior hippocampus subregions. Compared to the normal controls, the amnestic mild cognitive impairment and Alzheimer's disease groups showed different magnitudes of decreased functional connectivity between the retrosplenial cortex and the contralateral posterior hippocampus. Additionally, diminished functional connectivity between the left retrosplenial cortex and right posterior hippocampus was correlated with clinical disease severity in amnestic mild cognitive impairment subjects, and the combination of multiple functional connectivity indicators of the retrosplenial cortex can discriminate the three groups from each other. These findings confirm and extend previous studies suggesting that the retrosplenial cortex is extensively and functionally connected with hippocampus subregions and that these functional connections are selectively affected in the Alzheimer's disease continuum, with prominent disruptions in functional connectivity between the retrosplenial cortex and contralateral posterior hippocampus underpinning episodic memory impairment associated with the disease.

Functional connectivity in complex regional pain syndrome: A bicentric study

Brain imaging studies in complex regional pain syndrome (CRPS) have found mixed evidence for functional and structural changes in CRPS. In this cross-sectional study, we evaluated two patient cohorts from different centers and examined functional connectivity (rsFC) in 51 CRPS patients and 50 matched controls. rsFC was compared in predefined ROI pairs, but also in non-hypothesis driven analyses. Resting state (rs)fMRI changes in default mode network (DMN) and the degree rank order disruption index (kD) were additionally evaluated. Finally, imaging parameters were correlated with clinical severity and somatosensory function. Among predefined pairs, we found only weakly to moderately lower functional connectivity between the right nucleus accumbens and bilateral ventromedial prefrontal cortex in the infra-slow oscillations (ISO) band. The unconstrained ROI-to-ROI analysis revealed lower rsFC between the periaqueductal gray matter (PAG) and left anterior insula, and higher rsFC between the right sensorimotor thalamus and nucleus accumbens. In the correlation analysis, pain was positively associated with insulo-prefrontal rsFC, whereas sensorimotor thalamo-cortical rsFC was positively associated with tactile spatial resolution of the affected side. In contrast to previous reports, we found no group differences for kD or rsFC in the DMN, but detected overall lower data quality in patients. In summary, while some of the previous results were not replicated despite the larger sample size, novel findings from two independent cohorts point to potential down-regulated antinociceptive modulation by the PAG and increased connectivity within the reward system as pathophysiological mechanisms in CRPS. However, in light of the detected systematic differences in data quality between patients and healthy subjects, validity of rsFC abnormalities in CRPS should be carefully scrutinized in future replication studies.

Disruptive and complementary effects of depression symptoms on spontaneous brain activity in the subcortical vascular mild cognitive impairment

Background

Although depression symptoms are commonly reported in patients with subcortical vascular mild cognitive impairment (svMCI), their impact on brain functions remains largely unknown, with diagnoses mainly dependent on behavioral assessments.

Methods

In this study, we analyzed resting-state fMRI data from a cohort of 34 svMCI patients, comprising 18 patients with depression symptoms (svMCI+D) and 16 patients without (svMCI-D), along with 34 normal controls (NC). The study used the fraction of the amplitude of low-frequency fluctuations (fALFF), resting-state functional connectivity, correlation analyses, and support vector machine (SVM) techniques.

Results

The fALFF of the right cerebellum (CERE.R) differed among the svMCI+D, svMCI-D, and NC groups. Specifically, the regional mean fALFF of CERE. R was lower in svMCI-D patients compared to NC but higher in svMCI+D patients compared to svMCI-D patients. Moreover, the adjusted fALFF of CERE. R showed a significant correlation with Montreal Cognitive Assessment (MOCA) scores in svMCI-D patients. The fALFF of the right orbital part of the superior frontal gyrus was significantly correlated with Hamilton Depression Scale scores in svMCI+D patients, whereas the fALFF of the right postcingulate cortex (PCC.R) showed a significant correlation with MOCA scores in svMCI-D patients. Furthermore, RSFC between PCC. R and right precuneus, as well as between CERE. R and the right lingual gyrus (LING.R), was significantly reduced in svMCI-D patients compared to NC. In regional analyses, the adjusted RSFC between PCC. R and PreCUN. R, as well as between CERE. R and LING. R, was decreased in svMCI-D patients compared to NC but increased in svMCI+D patients compared to svMCI-D. Further SVM analyses achieved good performances, with an area under the curve (AUC) of 0.82 for classifying svMCI+D, svMCI-D, and NC; 0.96 for classifying svMCI+D and svMCI-D; 0.82 for classifying svMCI+D and NC; and 0.92 for classifying svMCI-D and NC.

Conclusion

The study revealed disruptive effects of cognitive impairment, along with both disruptive and complementary effects of depression symptoms on spontaneous brain activity in svMCI. Moreover, these findings suggest that the identified features might serve as potential biomarkers for distinguishing between svMCI+D, svMCI-D, and NC, thereby guiding clinical treatments such as transcranial magnetic stimulation for svMCI.

Neuroimaging correlates of Alzheimer's disease biomarker concentrations in a racially diverse high-risk cohort of middle-aged adults

INTRODUCTION

In this study, we investigated biomarkers in a midlife, racially diverse, at-risk cohort to facilitate early identification and intervention. We examined neuroimaging measures, including resting state functional magnetic resonance imaging (fMRI), white matter hyperintensity vo (WMH), and hippocampal volumes, alongside cerebrospinal fluid (CSF) markers.

METHODS

Our data set included 76 cognitively unimpaired, middle-aged, Black Americans (N = 29, F/M = 17/12) and Non-Hispanic White (N = 47, F/M = 27/20) individuals. We compared cerebrospinal fluid phosphorylated tau141 and amyloid beta (Aβ)42 to fMRI default mode network (DMN) subnetwork connectivity, WMH volumes, and hippocampal volumes.

RESULTS

Results revealed a significant race × Aβ42 interaction in Black Americans: lower Aβ42 was associated with reduced DMN connectivity and increased WMH volumes regions but not in non-Hispanic White individuals.

DISCUSSION

Our findings suggest that precuneus DMN connectivity and temporal WMHs may be linked to Alzheimer's disease risk pathology during middle age, particularly in Black Americans.

HIGHLIGHTS

Cerebrospinal fluid (CSF) amyloid beta (Aβ)42 relates to precuneus functional connectivity in Black, but not White, Americans. Higher white matter hyperintensity volume relates to lower CSF Aβ42 in Black Americans. Precuneus may be a hub for early Alzheimer's disease pathology changes detected by functional connectivity.

Basal forebrain activity predicts functional degeneration in the entorhinal cortex in Alzheimer's disease

Recent models of Alzheimer's disease suggest the nucleus basalis of Meynert (NbM) as an early origin of structural degeneration followed by the entorhinal cortex (EC). However, the functional properties of NbM and EC regarding amyloid-β and hyperphosphorylated tau remain unclear. We analysed resting-state functional fMRI data with CSF assays from the Alzheimer's Disease Neuroimaging Initiative (n = 71) at baseline and 2 years later. At baseline, local activity, as quantified by fractional amplitude of low-frequency fluctuations, differentiated between normal and abnormal CSF groups in the NbM but not EC. Further, NbM activity linearly decreased as a function of CSF ratio, resembling the disease status. Finally, NbM activity predicted the annual percentage signal change in EC, but not the reverse, independent from CSF ratio. Our findings give novel insights into the pathogenesis of Alzheimer's disease by showing that local activity in NbM is affected by proteinopathology and predicts functional degeneration within the EC.

Brain Functional Network Generation Using Distribution-Regularized Adversarial Graph Autoencoder with Transformer for Dementia Diagnosis

The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia disorders. The brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia disorders. However, it is challenging to access considerable amounts of brain functional network data, which hinders the widespread application of data-driven models in dementia diagnosis. In this study, a novel distribution-regularized adversarial graph auto-Encoder (DAGAE) with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset, improving the dementia diagnosis accuracy of data-driven models. Specifically, the label distribution is estimated to regularize the latent space learned by the graph encoder, which can make the learning process stable and the learned representation robust. Also, the transformer generator is devised to map the node representations into node-to-node connections by exploring the long-term dependence of highly-correlated distant brain regions. The typical topological properties and discriminative features can be preserved entirely. Furthermore, the generated brain functional networks improve the prediction performance using different classifiers, which can be applied to analyze other cognitive diseases. Attempts on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed model can generate good brain functional networks. The classification results show adding generated data can achieve the best accuracy value of 85.33%, sensitivity value of 84.00%, specificity value of 86.67%. The proposed model also achieves superior performance compared with other related augmented models. Overall, the proposed model effectively improves cognitive disease diagnosis by generating diverse brain functional networks.

Basal forebrain activity predicts functional degeneration in the entorhinal cortex and decreases with Alzheimer's Disease progression

BACKGROUND AND OBJECTIVES

Recent models of Alzheimer's Disease (AD) suggest the nucleus basalis of Meynert (NbM) as the origin of structural degeneration followed by the entorhinal cortex (EC). However, the functional properties of NbM and EC regarding amyloid-β and hyperphosphorylated tau remain unclear.

METHODS

We analyzed resting-state (rs)fMRI data with CSF assays from the Alzheimer's Disease Neuroimaging Initiative (ADNI, n=71) at baseline and two years later.

RESULTS

At baseline, local activity, as quantified by fractional amplitude of low-frequency fluctuations (fALFF), differentiated between normal and abnormal CSF groups in the NbM but not EC. Further, NbM activity linearly decreased as a function of CSF ratio, resembling the disease status. Finally, NbM activity predicted the annual percentage signal change in EC, but not the reverse, independent from CSF ratio.

DISCUSSION

Our findings give novel insights into the pathogenesis of AD by showing that local activity in NbM is affected by proteinopathology and predicts functional degeneration within the EC.

Prefrontal parvalbumin interneurons deficits mediate early emotional dysfunction in Alzheimer's disease

Alzheimer's disease (AD) is the most common neurodegenerative disease and has an insidious onset. Exploring the characteristics and mechanism of the early symptoms of AD plays a critical role in the early diagnosis and intervention of AD. Here we found that depressive-like behavior and short-term spatial memory dysfunction appeared in APPswe/PS1dE9 mice (AD mice) as early as 9-11 weeks of age. Electrophysiological analysis revealed excitatory/inhibitory (E/I) imbalance in the prefrontal cortex (PFC). This E/I imbalance was induced by significant reduction in the number and activity of parvalbumin interneurons (PV+ INs) in this region. Furthermore, optogenetic and chemogenetic activation of residual PV+ INs effectively ameliorated depressive-like behavior and rescued short-term spatial memory in AD mice. These results suggest the PFC is selectively vulnerable in the early stage of AD and prefrontal PV+ INs deficits play a key role in the occurrence and development of early symptoms of AD.

Functional magnetic resonance imaging, deep learning, and Alzheimer's disease: A systematic review

Alzheimer's disease (AD) is currently diagnosed using a mixture of psychological tests and clinical observations. However, these diagnoses are not perfect, and additional diagnostic tools (e.g., MRI) can help improve our understanding of AD as well as our ability to detect the disease. Accordingly, a large amount of research has been invested into innovative diagnostic methods for AD. Functional MRI (fMRI) is a form of neuroimaging technology that has been used to diagnose AD; however, fMRI is incredibly noisy, complex, and thus lacks clinical use. Nonetheless, recent innovations in deep learning technology could enable the simplified and streamlined analysis of fMRI. Deep learning is a form of artificial intelligence that uses computer algorithms based on human neural networks to solve complex problems. For example, in fMRI research, deep learning models can automatically denoise images and classify AD by detecting patterns in participants' brain scans. In this systematic review, we investigate how fMRI (specifically resting-state fMRI) and deep learning methods are used to diagnose AD. In turn, we outline the common deep neural network, preprocessing, and classification methods used in the literature. We also discuss the accuracy, strengths, limitations, and future direction of fMRI deep learning methods. In turn, we aim to summarize the current field for new researchers, suggest specific areas for future research, and highlight the potential of fMRI to aid AD diagnoses.

Performance of Temporal and Spatial Independent Component Analysis in Identifying and Removing Low-Frequency Physiological and Motion Effects in Resting-State fMRI

Effective separation of signal from noise (including physiological processes and head motion) is one of the chief challenges for improving the sensitivity and specificity of resting-state fMRI (rs-fMRI) measurements and has a profound impact when these noise sources vary between populations. Independent component analysis (ICA) is an approach for addressing these challenges. Conventionally, due to the lower amount of temporal than spatial information in rs-fMRI data, spatial ICA (sICA) is the method of choice. However, with recent developments in accelerated fMRI acquisitions, the temporal information is becoming enriched to the point that the temporal ICA (tICA) has become more feasible. This is particularly relevant as physiological processes and motion exhibit very different spatial and temporal characteristics when it comes to rs-fMRI applications, leading us to conduct a comparison of the performance of sICA and tICA in addressing these types of noise. In this study, we embrace the novel practice of using theory (simulations) to guide our interpretation of empirical data. We find empirically that sICA can identify more noise-related signal components than tICA. However, on the merit of functional-connectivity results, we find that while sICA is more adept at reducing whole-brain motion effects, tICA performs better in dealing with physiological effects. These interpretations are corroborated by our simulation results. The overall message of this study is that if ICA denoising is to be used for rs-fMRI, there is merit in considering a hybrid approach in which physiological and motion-related noise are each corrected for using their respective best-suited ICA approach.

Multi-centre classification of functional neurological disorders based on resting-state functional connectivity

•

Using machine learning on multi-centre data, FND patients were successfully classified with an accuracy of 72%.

•

The angular- and supramarginal gyri, cingular- and insular cortex, and the hippocampus were the most discriminant regions.

•

To provide diagnostic utility, future studies must include patients with similar symptoms but different diagnoses.

Background

Patients suffering from functional neurological disorder (FND) experience disabling neurological symptoms not caused by an underlying classical neurological disease (such as stroke or multiple sclerosis). The diagnosis is made based on reliable positive clinical signs, but clinicians often require additional time- and cost consuming medical tests and examinations. Resting-state functional connectivity (RS FC) showed its potential as an imaging-based adjunctive biomarker to help distinguish patients from healthy controls and could represent a “rule-in” procedure to assist in the diagnostic process. However, the use of RS FC depends on its applicability in a multi-centre setting, which is particularly susceptible to inter-scanner variability. The aim of this study was to test the robustness of a classification approach based on RS FC in a multi-centre setting.

Methods

This study aimed to distinguish 86 FND patients from 86 healthy controls acquired in four different centres using a multivariate machine learning approach based on whole-brain resting-state functional connectivity. First, previously published results were replicated in each centre individually (intra-centre cross-validation) and its robustness across inter-scanner variability was assessed by pooling all the data (pooled cross-validation). Second, we evaluated the generalizability of the method by using data from each centre once as a test set, and the data from the remaining centres as a training set (inter-centre cross-validation).

Results

FND patients were successfully distinguished from healthy controls in the replication step (accuracy of 74%) as well as in each individual additional centre (accuracies of 73%, 71% and 70%). The pooled cross validation confirmed that the classifier was robust with an accuracy of 72%. The results survived post-hoc adjustment for anxiety, depression, psychotropic medication intake, and symptom severity. The most discriminant features involved the angular- and supramarginal gyri, sensorimotor cortex, cingular- and insular cortex, and hippocampal regions. The inter-centre validation step did not exceed chance level (accuracy below 50%).

Conclusions

The results demonstrate the applicability of RS FC to correctly distinguish FND patients from healthy controls in different centres and its robustness against inter-scanner variability. In order to generalize its use across different centres and aim for clinical application, future studies should work towards optimization of acquisition parameters and include neurological and psychiatric control groups presenting with similar symptoms.

APOE, TOMM40, and sex interactions on neural network connectivity

The Apolipoprotein E ε4 (APOE ε4) haplotype is the strongest genetic risk factor for late-onset Alzheimer's disease (AD). The Translocase of Outer Mitochondrial Membrane-40 (TOMM40) gene maintains cellular bioenergetics, which is disrupted in AD. TOMM40 rs2075650 ('650) G versus A carriage is consistently related to neural and cognitive outcomes, but it is unclear if and how it interacts with APOE. We examined 21 orthogonal neural networks among 8,222 middle-aged to aged participants in the UK Biobank cohort. ANOVA and multiple linear regression tested main effects and interactions with APOE and TOMM40 '650 genotypes, and if age and sex acted as moderators. APOE ε4 was associated with less strength in multiple networks, while '650 G versus A carriage was related to more language comprehension network strength. In APOE ε4 carriers, '650 G-carriage led to less network strength with increasing age, while in non-G-carriers this was only seen in women but not men. TOMM40 may shift what happens to network activity in aging APOE ε4 carriers depending on sex.

Preoperative Assessment of Language Dominance through Combined Resting-State and Task-Based Functional Magnetic Resonance Imaging

Brain lesions in language-related cortical areas remain a challenge in the clinical routine. In recent years, the resting-state fMRI (RS-fMRI) was shown to be a feasible method for preoperative language assessment. The aim of this study was to examine whether language-related resting-state components, which have been obtained using a data-driven independent-component-based identification algorithm, can be supportive in determining language dominance in the left or right hemisphere. Twenty patients suffering from brain lesions close to supposed language-relevant cortical areas were included. RS-fMRI and task-based (TB-fMRI) were performed for the purpose of preoperative language assessment. TB-fMRI included a verb generation task with an appropriate control condition (a syllable switching task) to decompose language-critical and language-supportive processes. Subsequently, the best fitting ICA component for the resting-state language network (RSLN) referential to general linear models (GLMs) of the TB-fMRI (including models with and without linguistic control conditions) was identified using an algorithm based on the Dice index. Thereby, the RSLNs associated with GLMs using a linguistic control condition led to significantly higher laterality indices than GLM baseline contrasts. LIs derived from GLM contrasts with and without control conditions alone did not differ significantly. In general, the results suggest that determining language dominance in the human brain is feasible both with TB-fMRI and RS-fMRI, and in particular, the combination of both approaches yields a higher specificity in preoperative language assessment. Moreover, we can conclude that the choice of the language mapping paradigm is crucial for the mentioned benefits.

Convergent Functional Changes of Default Mode Network in Mild Cognitive Impairment Using Activation Likelihood Estimation

Background: Mild cognitive impairment (MCI) represents a transitional state between normal aging and dementia disorders, especially Alzheimer's disease (AD). The disruption of the default mode network (DMN) is often considered to be a potential biomarker for the progression from MCI to AD. The purpose of this study was to assess MRI-specific changes of DMN in MCI patients by elucidating the convergence of brain regions with abnormal DMN function.

Methods: We systematically searched PubMed, Ovid, and Web of science for relevant articles. We identified neuroimaging studies by using amplitude of low frequency fluctuation /fractional amplitude of low frequency fluctuation (ALFF/fALFF), regional homogeneity (ReHo), and functional connectivity (FC) in MCI patients. Based on the activation likelihood estimation (ALE) algorithm, we carried out connectivity modeling of coordination-based meta-analysis and functional meta-analysis.

Results: In total, this meta-analysis includes 39 articles on functional neuroimaging studies. Using computer software analysis, we discovered that DMN changes in patients with MCI mainly occur in bilateral inferior frontal lobe, right medial frontal lobe, left inferior parietal lobe, bilateral precuneus, bilateral temporal lobe, and parahippocampal gyrus (PHG).

Conclusions: Herein, we confirmed the presence of DMN-specific damage in MCI, which is helpful in revealing pathology of MCI and further explore mechanisms of conversion from MCI to AD. Therefore, we provide a new specific target and direction for delaying conversion from MCI to AD.

Diagnostic Efficacy of Voxel-Mirrored Homotopic Connectivity in Vascular Dementia as Compared to Alzheimer's Related Neurodegenerative Diseases-A Resting State fMRI Study

Previous studies have demonstrated that functional connectivity (FC) of different brain regions in resting state function MRI were abnormal in patients suffering from mild cognitive impairment (MCI) and Alzheimer’s disease (AD) when comparing to healthy controls (HC) using seed based, independent component analysis (ICA) or small world network techniques. A new technique called voxel-mirrored homotopic connectivity (VMHC) was used in the current study to evaluate the value of interhemispheric functional connectivity (IFC) as a diagnostic tool to differentiate vascular dementia (VD) from other Alzheimer’s related neurodegenerative diseases. Eighty-three participants were recruited from the university hospital memory clinic. A multidisciplinary panel formed by a neuroradiologist and two geriatricians classified the participants into VD (13), AD (16), MCI (29), and HC (25) based on clinical history, Montreal Cognitive Assessment Hong Kong version (HK-MoCA) neuropsychological score, structural MRI, MR perfusion, and 18-F Flutametamol (amyloid) PET-CT findings of individual subjects. We adopted the calculation method used by Kelly et al. (2011) and Zuo et al. (2010) in obtaining VMHC maps. Specific patterns of VMHC maps were obtained for VD, AD, and MCI to HC comparison. VD showed significant reduction in VMHC in frontal orbital gyrus and gyrus rectus. Increased VMHC was observed in default mode network (DMN), executive control network (ECN), and the remaining salient network (SN) regions. AD showed a reduction of IFC in all DMN, ECN, and SN regions; whereas MCI showed VMHC reduction in vSN, and increased VMHC in DMN and ECN. When combining VMHC values of relevant brain regions, the accuracy was improved to 87%, 92%, and 83% for VD, AD, and MCI from HC, respectively, in receiver operating characteristic (ROC) analysis. Through studying the VMHC maps and using VMHC values in relevant brain regions, VMHC can be considered as a reliable diagnostic tool for VD, AD, and MCI from HC.

Neurofeedback and the Aging Brain: A Systematic Review of Training Protocols for Dementia and Mild Cognitive Impairment

Dementia describes a set of symptoms that occur in neurodegenerative disorders and that is characterized by gradual loss of cognitive and behavioral functions. Recently, non-invasive neurofeedback training has been explored as a potential complementary treatment for patients suffering from dementia or mild cognitive impairment. Here we systematically reviewed studies that explored neurofeedback training protocols based on electroencephalography or functional magnetic resonance imaging for these groups of patients. From a total of 1,912 screened studies, 10 were included in our final sample (N = 208 independent participants in experimental and N = 81 in the control groups completing the primary endpoint). We compared the clinical efficacy across studies, and evaluated their experimental designs and reporting quality. In most studies, patients showed improved scores in different cognitive tests. However, data from randomized controlled trials remains scarce, and clinical evidence based on standardized metrics is still inconclusive. In light of recent meta-research developments in the neurofeedback field and beyond, quality and reporting practices of individual studies are reviewed. We conclude with recommendations on best practices for future studies that investigate the effects of neurofeedback training in dementia and cognitive impairment.

Diagnostic power of resting-state fMRI for detection of network connectivity in Alzheimer's disease and mild cognitive impairment: A systematic review

Resting‐state fMRI (rs‐fMRI) detects functional connectivity (FC) abnormalities that occur in the brains of patients with Alzheimer's disease (AD) and mild cognitive impairment (MCI). FC of the default mode network (DMN) is commonly impaired in AD and MCI. We conducted a systematic review aimed at determining the diagnostic power of rs‐fMRI to identify FC abnormalities in the DMN of patients with AD or MCI compared with healthy controls (HCs) using machine learning (ML) methods. Multimodal support vector machine (SVM) algorithm was the commonest form of ML method utilized. Multiple kernel approach can be utilized to aid in the classification by incorporating various discriminating features, such as FC graphs based on “nodes” and “edges” together with structural MRI‐based regional cortical thickness and gray matter volume. Other multimodal features include neuropsychiatric testing scores, DTI features, and regional cerebral blood flow. Among AD patients, the posterior cingulate cortex (PCC)/Precuneus was noted to be a highly affected hub of the DMN that demonstrated overall reduced FC. Whereas reduced DMN FC between the PCC and anterior cingulate cortex (ACC) was observed in MCI patients. Evidence indicates that the nodes of the DMN can offer moderate to high diagnostic power to distinguish AD and MCI patients. Nevertheless, various concerns over the homogeneity of data based on patient selection, scanner effects, and the variable usage of classifiers and algorithms pose a challenge for ML‐based image interpretation of rs‐fMRI datasets to become a mainstream option for diagnosing AD and predicting the conversion of HC/MCI to AD.

A unified framework for personalized regions selection and functional relation modeling for early MCI identification

Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely adopted to investigate functional abnormalities in brain diseases. Rs-fMRI data is unsupervised in nature because the psychological and neurological labels are coarse-grained, and no accurate region-wise label is provided along with the complex co-activities of multiple regions. To the best of our knowledge, most studies regarding univariate group analysis or multivariate pattern recognition for brain disease identification have focused on discovering functional characteristics shared across subjects; however, they have paid less attention to individual properties of neural activities that result from different symptoms or degrees of abnormality. In this work, we propose a novel framework that can identify subjects with early-stage mild cognitive impairment (eMCI) and consider individual variability by learning functional relations from automatically selected regions of interest (ROIs) for each subject concurrently. In particular, we devise a deep neural network composed of a temporal embedding module, an ROI selection module, and a disease-identification module. Notably, the ROI selection module is equipped with a reinforcement learning mechanism so it adaptively selects ROIs to facilitate the learning of discriminative feature representations from a temporally embedded blood-oxygen-level-dependent signals. Furthermore, our method allows us to capture the functional relations of a subject-specific ROI subset through the use of a graph-based neural network. Our method considers individual characteristics for diagnosis, as opposed to most conventional methods that identify the same biomarkers across subjects within a group. Based on the ADNI cohort, we validate the effectiveness of our method by presenting the superior performance of our network in eMCI identification. Furthermore, we provide insightful neuroscientific interpretations by analyzing the regions selected for the eMCI classification.

Reducing Inter-Site Variability for Fluctuation Amplitude Metrics in Multisite Resting State BOLD-fMRI Data

It has been reported that resting state fluctuation amplitude (RSFA) exhibits extremely large inter-site variability, which limits its application in multisite studies. Although global normalization (GN) based approaches are efficient in reducing the site effects, they may cause spurious results. In this study, our purpose was to find alternative strategies to minimize the substantial site effects for RSFA, without the risk of introducing artificial findings. We firstly modified the ALFF algorithm so that it is conceptually validated and insensitive to data length, then found that (a) global mean amplitude of low-frequency fluctuation (ALFF) covaried only with BOLD signal intensity, while global mean fractional ALFF (fALFF) was significantly correlated with TRs across different sites; (b) The inter-site variations in raw RSFA values were significant across the entire brain and exhibited similar trends between gray matter and white matter; (c) For ALFF, signal intensity rescaling could dramatically reduce inter-site variability by several orders, but could not fully removed the globally distributed inter-site variability. For fALFF, the global site effects could be completely removed by TR controlling; (d) Meanwhile, the magnitude of the inter-site variability of fALFF could also be reduced to an acceptable level, as indicated by the detection power of fALFF in multisite data quite close to that in monosite data. Thus our findings suggest GN based harmonization methods could be replaced with only controlling for confounding factors including signal scaling, TR and full-band power.

Role of Magnetoencephalography in the Early Stages of Alzheimer Disease

As synaptic dysfunction is an early manifestation of Alzheimer disease (AD) pathology, magnetoencephalography (MEG) is capable of detecting disruptions by assessing the synchronized oscillatory activity of thousands of neurons that rely on the integrity of neural connections. MEG findings include slowness of the oscillatory activity, accompanied by a reduction of the alpha band power, and dysfunction of the functional networks. These findings are associated with the neuropathology of the disease and cognitive impairment. These neurophysiological biomarkers predict which patients with mild cognitive impairment will develop dementia. MEG has demonstrated its utility as a noninvasive biomarker for early detection of AD.

CCCDTD5: Clinical role of neuroimaging and liquid biomarkers in patients with cognitive impairment

Since 1989, four Canadian Consensus Conferences on the Diagnosis and Treatment of Dementia (CCCDTDs) have provided evidence-based dementia diagnostic and treatment guidelines for Canadian clinicians and researchers. We present the results from the Neuroimaging and Fluid Biomarkers Group of the 5th CCCDTD (CCCDTD5), which addressed topics chosen by the steering committee to reflect advances in the field and build on our previous guidelines. Recommendations on Imaging and Fluid Biomarker Use from this Conference cover a series of different fields. Prior structural imaging recommendations for both computerized tomography (CT) and magnetic resonance imaging (MRI) remain largely unchanged, but MRI is now more central to the evaluation than before, with suggested sequences described here. The use of visual rating scales for both atrophy and white matter anomalies is now included in our recommendations. Molecular imaging with [18F]-fluorodeoxyglucose ([18F]-FDG) Positron Emisson Tomography (PET) or [99mTc]-hexamethylpropyleneamine oxime/ethylene cysteinate dimer ([99mTc]-HMPAO/ECD) Single Photon Emission Tomography (SPECT), should now decidedly favor PET. The value of [18F]-FDG PET in the assessment of neurodegenerative conditions has been established with greater certainty since the previous conference, and it has now been recognized as a useful biomarker to establish the presence of neurodegeneration by a number of professional organizations around the world. Furthermore, the role of amyloid PET has been clarified and our recommendations follow those from other groups in multiple countries. SPECT with [123I]-ioflupane (DaTscanTM) is now included as a useful study in differentiating Alzheimer's disease (AD) from Lewy body disease. Finally, liquid biomarkers are in a rapid phase of development and, could lead to a revolution in the assessment AD and other neurodegenerative conditions at a reasonable cost. We hope these guidelines will be useful for clinicians, researchers, policy makers, and the lay public, to inform a current and evidence-based approach to the use of neuroimaging and liquid biomarkers in clinical dementia evaluation and management.

Spatial topography of the basal forebrain cholinergic projections: Organization and vulnerability to degeneration

The basal forebrain (BF) cholinergic system constitutes a heterogeneous cluster of large projection neurons that innervate the entire cortical mantle and amygdala. Cholinergic neuromodulation plays a critical role in regulating cognition and behavior, as well as maintenance of cellular homeostasis. Decades of postmortem histology research have demonstrated that the BF cholinergic neurons are selectively vulnerable to aging and age-related neuropathology in degenerative diseases such as Alzheimer's and Parkinson's diseases. Emerging evidence from in vivo neuroimaging research, which permits longitudinal tracking of at-risk individuals, indicates that cholinergic neurodegeneration might play an earlier and more pivotal role in these diseases than was previously appreciated. Despite these advances, our understanding of the organization and functions of the BF cholinergic system mostly derives from nonhuman animal research. In this chapter, we begin with a review of the topographical organization of the BF cholinergic system in rodent and nonhuman primate models. We then discuss basic and clinical neuroscience research in humans, which has started to translate and extend the nonhuman animal research using novel noninvasive neuroimaging techniques. We focus on converging evidence indicating that the selective vulnerability of cholinergic neurons in Alzheimer's and Parkinson's diseases is expressed along a rostral-caudal topography in the BF. We close with a discussion of why this topography of vulnerability in the BF may occur and why it is relevant to the clinician.

Association between composite scores of domain-specific cognitive functions and regional patterns of atrophy and functional connectivity in the Alzheimer's disease spectrum

BACKGROUND

Cognitive decline has been found to be associated with gray matter atrophy and disruption of functional neural networks in Alzheimer's disease (AD) in structural and functional imaging (fMRI) studies. Most previous studies have used single test scores of cognitive performance among monocentric cohorts. However, cognitive domain composite scores could be more reliable than single test scores due to the reduction of measurement error. Adopting a multicentric resting state fMRI (rs-fMRI) and cognitive domain approach, we provide a comprehensive description of the structural and functional correlates of the key cognitive domains of AD.

METHOD

We analyzed MRI, rs-fMRI and cognitive domain score data of 490 participants from an interim baseline release of the multicenter DELCODE study cohort, including 54 people with AD, 86 with Mild Cognitive Impairment (MCI), 175 with Subjective Cognitive Decline (SCD), and 175 Healthy Controls (HC) in the AD-spectrum. Resulting cognitive domain composite scores (executive, visuo-spatial, memory, working memory and language) from the DELCODE neuropsychological battery (DELCODE-NP), were previously derived using confirmatory factor analysis. Statistical analyses examined the differences between diagnostic groups, and the association of composite scores with regional atrophy and network-specific functional connectivity among the patient subgroup of SCD, MCI and AD.

RESULT

Cognitive performance, atrophy patterns and functional connectivity significantly differed between diagnostic groups in the AD-spectrum. Regional gray matter atrophy was positively associated with visuospatial and other cognitive impairments among the patient subgroup in the AD-spectrum. Except for the visual network, patterns of network-specific resting-state functional connectivity were positively associated with distinct cognitive impairments among the patient subgroup in the AD-spectrum.

CONCLUSION

Consistent associations between cognitive domain scores and both regional atrophy and network-specific functional connectivity (except for the visual network), support the utility of a multicentric and cognitive domain approach towards explicating the relationship between imaging markers and cognition in the AD-spectrum.

Predicting dysfunctional age-related task activations from resting-state network alterations

Alzheimer's disease (AD) is linked to changes in fMRI task activations and fMRI resting-state functional connectivity (restFC), which can emerge early in the illness timecourse. These fMRI correlates of unhealthy aging have been studied in largely separate subfields. Taking inspiration from neural network simulations, we propose a unifying mechanism wherein restFC alterations associated with AD disrupt the flow of activations between brain regions, leading to aberrant task activations. We apply this activity flow model in a large sample of clinically normal older adults, which was segregated into healthy (low-risk) and at-risk subgroups based on established imaging (positron emission tomography amyloid) and genetic (apolipoprotein) AD risk factors. Modeling the flow of healthy activations over at-risk AD connectivity effectively transformed the healthy aged activations into unhealthy (at-risk) aged activations. This enabled reliable prediction of at-risk AD task activations, and these predicted activations were related to individual differences in task behavior. These results support activity flow over altered intrinsic functional connections as a mechanism underlying Alzheimer's-related dysfunction, even in very early stages of the illness. Beyond these mechanistic insights, this approach raises clinical potential by enabling prediction of task activations and associated cognitive dysfunction in individuals without requiring them to perform in-scanner cognitive tasks.

Diagnostic classification of autism using resting-state fMRI data improves with full correlation functional brain connectivity compared to partial correlation

BACKGROUND

Autism Spectrum Disorder (ASD) is a neurodevelopmental disability with altered connectivity in brain networks.

NEW METHOD

In this study, brain connections in Resting-state functional Magnetic Resonance Imaging (Rs-fMRI) of ASD and Typical Developing (TD) are analyzed by partial and full correlation methods such as Gaussian Graphical Least Absolute Shrinkage and Selection Operator (GLASSO), Max-Det Matrix Completion (MDMC), and Pearson Correlation Co-Efficient (PCCE). We investigated Functional Connectivity (FC) of ASD and TD brain from 238 functionally defined regions of interest. Furthermore, we constructed a series of feature sets by applying conditional random forests and conditional permutation importance. We built classifier models by Random Forest (RF), Oblique RF (ORF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) for each feature set. FC features are ranked based on p-value and we analyzed the top 20 FC features.

RESULTS

We achieved a single-trial test accuracy of 72.5 %, though MDMC-SVM and PCCE-CNN pipelines. Further, PCCE-CNN pipeline gives better average test accuracy (70.31 %) and area under the curve (0.73) compared to other pipelines. We found that top-20 PCCE based FC features are from networks such as Dorsal Attention (DA), Cingulo-Opercular Task Control (COTC), somatosensory motor hand and subcortical. In addition, among top 20 PCCE features, many FC links are found between COTC and DA (4 connections) which helped to discriminate the ASD and TD.

COMPARISON WITH EXISTING METHODS AND CONCLUSIONS

The generalized classifier models built in our study for highly heterogeneous participants perform better than previous studies with similar data sets and diagnostic groups.

Developmental pattern of the cortical topology in high-functioning individuals with autism spectrum disorder

A number of studies have indicated alterations of brain morphology in individuals with autism spectrum disorder (ASD); however, how ASD influences the topological organization of the brain cortex at different developmental stages is not yet well characterized. In this study, we used structural images of 492 high‐functioning participants in the Autism Brain Imaging Data Exchange database acquired from 17 international imaging centers, including 75 autistic children (age 7–11 years), 91 adolescents with ASD (age 12–17 years), and 80 young adults with ASD (age 18–29 years), and 246 typically developing controls (TDCs) that were age, gender, handedness, and full‐scale IQ matched. Cortical thickness (CT) and surface area (SA) were extracted and the covariance between cortical regions across participants were treated as a network to examine developmental patterns of the cortical topological organization at different stages. A center‐paired resampling strategy was developed to control the center bias during the permutation test. Compared with the TDCs, network of SA (but not CT) of individuals with ASD showed reduced small‐worldness in childhood, and the network hubs were reorganized in the adulthood such that hubs inclined to connect with nonhub nodes and demonstrated more dispersed spatial distribution. Furthermore, the SA network of the ASD cohort exhibited increased segregation of the inferior parietal lobule and prefrontal cortex, and insular‐opercular cortex in all three age groups, resulting in the emergence of two unique modules in the autistic brain. Our findings suggested that individuals with ASD may undergo remarkable remodeling of the cortical topology from childhood to adulthood, which may be associated with the altered social and cognitive functions in ASD.

Grab-AD: Generalizability and reproducibility of altered brain activity and diagnostic classification in Alzheimer's Disease

Alzheimer's disease (AD) is associated with disruptions in brain activity and networks. However, there is substantial inconsistency among studies that have investigated functional brain alterations in AD; such contradictions have hindered efforts to elucidate the core disease mechanisms. In this study, we aim to comprehensively characterize AD-associated functional brain alterations using one of the world's largest resting-state functional MRI (fMRI) biobank for the disorder. The biobank includes fMRI data from six neuroimaging centers, with a total of 252 AD patients, 221 mild cognitive impairment (MCI) patients and 215 healthy comparison individuals. Meta-analytic techniques were used to unveil reliable differences in brain function among the three groups. Relative to the healthy comparison group, AD was associated with significantly reduced functional connectivity and local activity in the default-mode network, basal ganglia and cingulate gyrus, along with increased connectivity or local activity in the prefrontal lobe and hippocampus (p < .05, Bonferroni corrected). Moreover, these functional alterations were significantly correlated with the degree of cognitive impairment (AD and MCI groups) and amyloid-β burden. Machine learning models were trained to recognize key fMRI features to predict individual diagnostic status and clinical score. Leave-one-site-out cross-validation established that diagnostic status (mean area under the receiver operating characteristic curve: 0.85) and clinical score (mean correlation coefficient between predicted and actual Mini-Mental State Examination scores: 0.56, p < .0001) could be predicted with high accuracy. Collectively, our findings highlight the potential for a reproducible and generalizable functional brain imaging biomarker to aid the early diagnosis of AD and track its progression.

Independent and reproducible hippocampal radiomic biomarkers for multisite Alzheimer's disease: diagnosis, longitudinal progress and biological basis

Hippocampal morphological change is one of the main hallmarks of Alzheimer's disease (AD). However, whether hippocampal radiomic features are robust as predictors of progression from mild cognitive impairment (MCI) to AD dementia and whether these features provide any neurobiological foundation remains unclear. The primary aim of this study was to verify whether hippocampal radiomic features can serve as robust magnetic resonance imaging (MRI) markers for AD. Multivariate classifier-based support vector machine (SVM) analysis provided individual-level predictions for distinguishing AD patients (n = 261) from normal controls (NCs; n = 231) with an accuracy of 88.21% and intersite cross-validation. Further analyses of a large, independent the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n = 1228) reinforced these findings. In MCI groups, a systemic analysis demonstrated that the identified features were significantly associated with clinical features (e.g., apolipoprotein E (APOE) genotype, polygenic risk scores, cerebrospinal fluid (CSF) Aβ, CSF Tau), and longitudinal changes in cognition ability; more importantly, the radiomic features had a consistently altered pattern with changes in the MMSE scores over 5 years of follow-up. These comprehensive results suggest that hippocampal radiomic features can serve as robust biomarkers for clinical application in AD/MCI, and further provide evidence for predicting whether an MCI subject would convert to AD based on the radiomics of the hippocampus. The results of this study are expected to have a substantial impact on the early diagnosis of AD/MCI.

Generalizable, Reproducible, and Neuroscientifically Interpretable Imaging Biomarkers for Alzheimer's Disease

Precision medicine for Alzheimer's disease (AD) necessitates the development of personalized, reproducible, and neuroscientifically interpretable biomarkers, yet despite remarkable advances, few such biomarkers are available. Also, a comprehensive evaluation of the neurobiological basis and generalizability of the end-to-end machine learning system should be given the highest priority. For this reason, a deep learning model (3D attention network, 3DAN) that can simultaneously capture candidate imaging biomarkers with an attention mechanism module and advance the diagnosis of AD based on structural magnetic resonance imaging is proposed. The generalizability and reproducibility are evaluated using cross-validation on in-house, multicenter (n = 716), and public (n = 1116) databases with an accuracy up to 92%. Significant associations between the classification output and clinical characteristics of AD and mild cognitive impairment (MCI, a middle stage of dementia) groups provide solid neurobiological support for the 3DAN model. The effectiveness of the 3DAN model is further validated by its good performance in predicting the MCI subjects who progress to AD with an accuracy of 72%. Collectively, the findings highlight the potential for structural brain imaging to provide a generalizable, and neuroscientifically interpretable imaging biomarker that can support clinicians in the early diagnosis of AD.

Pre-trained MRI-based Alzheimer's disease classification models to classify memory clinic patients

•

Multimodal MRI AD classification models were pre-trained on AD patients and controls.

•

Generalisation of these models was tested on a multi-centre memory clinic data set.

•

AD scores were assigned to AD patients, MCI patients and memory complainers.

•

Anatomical MRI performed better than diffusion MRI and resting state fMRI.

•

Combining imaging modalities did not improve the results over anatomical MRI only.

Anatomical magnetic resonance imaging (MRI), diffusion MRI and resting state functional MRI (rs-fMRI) have been used for Alzheimer’s disease (AD) classification. These scans are typically used to build models for discriminating AD patients from control subjects, but it is not clear if these models can also discriminate AD in diverse clinical populations as found in memory clinics.

To study this, we trained MRI-based AD classification models on a single centre data set consisting of AD patients (N = 76) and controls (N = 173), and used these models to assign AD scores to subjective memory complainers (N = 67), mild cognitive impairment (MCI) patients (N = 61), and AD patients (N = 61) from a multi-centre memory clinic data set. The anatomical MRI scans were used to calculate grey matter density, subcortical volumes and cortical thickness, the diffusion MRI scans were used to calculate fractional anisotropy, mean, axial and radial diffusivity, and the rs-fMRI scans were used to calculate functional connectivity between resting state networks and amplitude of low frequency fluctuations. Within the multi-centre memory clinic data set we removed scan site differences prior to applying the models.

For all models, on average, the AD patients were assigned the highest AD scores, followed by MCI patients, and later followed by SMC subjects. The anatomical MRI models performed best, and the best performing anatomical MRI measure was grey matter density, separating SMC subjects from MCI patients with an AUC of 0.69, MCI patients from AD patients with an AUC of 0.70, and SMC patients from AD patients with an AUC of 0.86. The diffusion MRI models did not generalise well to the memory clinic data, possibly because of large scan site differences. The functional connectivity model separated SMC subjects and MCI patients relatively good (AUC = 0.66). The multimodal MRI model did not improve upon the anatomical MRI model.

In conclusion, we showed that the grey matter density model generalises best to memory clinic subjects. When also considering the fact that grey matter density generally performs well in AD classification studies, this feature is probably the best MRI-based feature for AD diagnosis in clinical practice.

Low Rank Self-calibrated Brain Network Estimation and Autoweighted Centralized Multi-Task Learning for Early Mild Cognitive Impairment Diagnosis

Detection of mild cognitive impairment (MCI) is important, and appropriate interventions can be taken to delay or prevent its progression to Alzheimer's disease (AD). The construction of brain networks based on brain image data to depict the interaction of brain functions or structures at the level of brain connections has been widely used to identify individuals with MCI/AD from the normal control (NC). Exploring the structural and functional connections and interactions between brain regions is beneficial to detect MCI. For this reason, we propose a new model for automatic MCI diagnosis based on this information. Firstly, a new functional brain network estimation method is proposed. Self-calibration is introduced using quality indicators, and functional brain network estimation is performed at the same time. Then we integrate the functional and structural connected neuroimaging patterns into our multitask learning model to select informative feature. By identifying synergies and differences between different tasks, the most discriminative features are determined. Finally, the most relevant features are sent to the support vector machine classifier for diagnosis and identification of MCI. The experimental results based on the public Alzheimer's disease neuroimaging (ADNI) show that our method can effectively diagnose different stages of MCI and assist the physician to improve the MCI diagnostic accuracy. At the same time, compared with the existing classification methods, the proposed method achieves relatively high classification accuracy. In addition, it can identify the most discriminative brain regions. These findings suggest that our approach not only improves classification performance, but also successfully identifies important biomarkers associated with disease.

Estimation of Brain Functional Connectivity in Patients with Mild Cognitive Impairment

Mild cognitive impairment is defined as greater cognitive decline than expected for a person at a particular age and is sometimes considered a stage between healthy aging and Alzheimer's disease or other dementia syndromes. It is known that functional connectivity patterns change in people with this diagnosis. We studied functional connectivity patterns and functional segregation in a resting-state fMRI paradigm comparing 10 MCI patients and 10 healthy controls matched by education level, age and sex. Ninety ROIs from the automated anatomical labeling (AAL) atlas were selected for functional connectivity analysis. A correlation matrix was created for each group, and a third matrix with the correlation coefficient differences between the two matrices was created. Functional segregation was analyzed with the 3-cycle method, which is novel in studies of this topic. Finally, cluster analyses were also performed. Our results showed that the two correlation matrices were visually similar but had many differences related to different cognitive functions. Differences were especially apparent in the anterior default mode network (DMN), while the visual resting-state network (RSN) showed no differences between groups. Differences in connectivity patterns in the anterior DMN should be studied more extensively to fully understand its role in the differentiation of healthy aging and an MCI diagnosis.

ASAF: altered spontaneous activity fingerprinting in Alzheimer's disease based on multisite fMRI

Several monocentric studies have noted alterations in spontaneous brain activity in Alzheimer's disease (AD), although there is no consensus on the altered amplitude of low-frequency fluctuations in AD patients. The main aim of the present study was to identify a reliable and reproducible abnormal brain activity pattern in AD. The amplitude of local brain activity (AM), which can provide fast mapping of spontaneous brain activity across the whole brain, was evaluated based on multisite rs-fMRI data for 688 subjects (215 normal controls (NCs), 221 amnestic mild cognitive impairment (aMCI) 252 AD). Two-sample t-tests were used to detect group differences between AD patients and NCs from the same site. Differences in the AM maps were statistically analyzed via the Stouffer's meta-analysis. Consistent regions of lower spontaneous brain activity in the default mode network and increased activity in the bilateral hippocampus/parahippocampus, thalamus, caudate nucleus, orbital part of the middle frontal gyrus and left fusiform were observed in the AD patients compared with those in NCs. Significant correlations (P < 0.05, Bonferroni corrected) between the normalized amplitude index and Mini-Mental State Examination scores were found in the identified brain regions, which indicates that the altered brain activity was associated with cognitive decline in the patients. Multivariate analysis and leave-one-site-out cross-validation led to a 78.49% prediction accuracy for single-patient classification. The altered activity patterns of the identified brain regions were largely correlated with the FDG-PET results from another independent study. These results emphasized the impaired brain activity to provide a robust and reproducible imaging signature of AD.

Multicenter Resting State Functional Connectivity in Prodromal and Dementia Stages of Alzheimer's Disease

BACKGROUND

Alterations of intrinsic networks from resting state fMRI (rs-fMRI) have been suggested as functional biomarkers of Alzheimer's disease (AD).

OBJECTIVE

To determine the diagnostic accuracy of multicenter rs-fMRI for prodromal and preclinical stages of AD.

METHODS

We determined rs-fMRI functional connectivity based on Pearson's correlation coefficients and amplitude of low-frequency fluctuation in people with subjective cognitive decline, people with mild cognitive impairment, and people with AD dementia compared with healthy controls. We used data of 247 participants of the prospective DELCODE study, a longitudinal multicenter observational study, imposing a unified fMRI acquisition protocol across sites. We determined cross-validated discrimination accuracy based on penalized logistic regression to account for multicollinearity of predictors.

RESULTS

Resting state functional connectivity reached significant cross-validated group discrimination only for the comparison of AD dementia cases with healthy controls, but not for the other diagnostic groups. AD dementia cases showed alterations in a large range of intrinsic resting state networks, including the default mode and salience networks, but also executive and language networks. When groups were stratified according to their CSF amyloid status that was available in a subset of cases, diagnostic accuracy was increased for amyloid positive mild cognitive impairment cases compared with amyloid negative controls, but still inferior to the accuracy of hippocampus volume.

CONCLUSION

Even when following a strictly harmonized data acquisition protocol and rigorous scan quality control, widely used connectivity measures of multicenter rs-fMRI do not reach levels of diagnostic accuracy sufficient for a useful biomarker in prodromal stages of AD.

Early Stage Alterations in White Matter and Decreased Functional Interhemispheric Hippocampal Connectivity in the 3xTg Mouse Model of Alzheimer's Disease

Alzheimer’s disease (AD) is characterized in the late stages by amyloid-β (Aβ) plaques and neurofibrillary tangles. Nevertheless, recent evidence has indicated that early changes in cerebral connectivity could compromise cognitive functions even before the appearance of the classical neuropathological features. Diffusion tensor imaging (DTI), resting-state functional magnetic resonance imaging (rs-fMRI) and volumetry were performed in the triple transgenic mouse model of AD (3xTg-AD) at 2 months of age, prior to the development of intraneuronal plaque accumulation. We found the 3xTg-AD had significant fractional anisotropy (FA) increase and radial diffusivity (RD) decrease in the cortex compared with wild-type controls, while axial diffusivity (AD) and mean diffusivity (MD) were similar. Interhemispheric hippocampal connectivity was decreased in the 3xTg-AD while connectivity in the caudate putamen (CPu) was similar to controls. Most surprising, ventricular volume in the 3xTg-AD was four times larger than controls. The results obtained in this study characterize the early stage changes in interhemispheric hippocampal connectivity in the 3xTg-AD mouse that could represent a translational biomarker to human models in preclinical stages of the AD.

Physiological significance of R-fMRI indices: Can functional metrics differentiate structural lesions (brain tumors)?

Resting-state functional MRI (R-fMRI) research has recently entered the era of “big data”, however, few studies have provided a rigorous validation of the physiological underpinnings of R-fMRI indices. Although studies have reported that various neuropsychiatric disorders exhibit abnormalities in R-fMRI measures, these “biomarkers” have not been validated in differentiating structural lesions (brain tumors) as a concept proof. We enrolled 60 patients with intracranial tumors located in the unilateral cranialcavity and 60 matched normal controls to test whether R-fMRI indices can differentiate tumors, which represents a prerequisite for adapting such indices as biomarkers for neuropsychiatric disorders. Common R-fMRI indices of tumors and their counterpart control regions, which were defined as the contralateral normal areas (for amplitude of low frequency fluctuations (ALFF), fractional ALFF (fALFF), regional homogeneity (ReHo) and degree centrality (DC)) and ipsilateral regions surrounding the tumors (for voxel-mirrored homotopic connectivity (VMHC)), were comprehensively assessed. According to robust paired t-tests with a Bonferroni correction, only VMHC (Fisher's r-to-z transformed) could successfully differentiate substantial tumors from their counterpart normal regions in patients. Furthermore, ALFF and DC were not able to differentiate tumor from normal unless Z-standardization was employed. To validate the lower power of the between-subject design compared to the within-subject design, each metric was calculated in a matched control group, and robust two-sample t-tests were used to compare the patient tumors and the normal controls at the same place. Similarly, only VMHC succeeded in differentiating significant differences between tumors and the sham tumor areas of normal controls. This study tested the premise of R-fMRI biomarkers for differentiating lesions, and brings a new understanding to physical significance of the Z-standardization.

•

R-fMRI indices could differentiate tumors, validating their physical availability.

•

ALFF and DC could not differentiate tumors unless Z-standardization was employed.

•

Within-subject design is more powerful for R-fMRI indices in differentiating tumors.

Detecting Alzheimer's Disease on Small Dataset: A Knowledge Transfer Perspective

Computer-aided diagnosis (CAD) is an attractive topic in Alzheimer's disease (AD) research. Many algorithms are based on a relatively large training dataset. However, small hospitals are usually unable to collect sufficient training samples for robust classification. Although data sharing is expanding in scientific research, it is unclear whether a model based on one dataset is well suited for other data sources. Using a small dataset from a local hospital and a large shared dataset from the AD neuroimaging initiative, we conducted a heterogeneity analysis and found that different functional magnetic resonance imaging data sources show different sample distributions in feature space. In addition, we proposed an effective knowledge transfer method to diminish the disparity among different datasets and improve the classification accuracy on datasets with insufficient training samples. The accuracy increased by approximately 20% compared with that of a model based only on the original small dataset. The results demonstrated that the proposed approach is a novel and effective method for CAD in hospitals with only small training datasets. It solved the challenge of limited sample size in detection of AD, which is a common issue but lack of adequate attention. Furthermore, this paper sheds new light on effective use of multi-source data for neurological disease diagnosis.

Can a Resting-State Functional Connectivity Index Identify Patients with Alzheimer's Disease and Mild Cognitive Impairment Across Multiple Sites?

Resting-state functional connectivity is one promising biomarker for Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, it is still not known how accurately network analysis identifies AD and MCI across multiple sites. In this study, we examined whether resting-state functional connectivity data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) could identify patients with AD and MCI at our site. We implemented an index based on the functional connectivity frequency distribution and compared performance for AD and MCI identification with multivoxel pattern analysis. The multivoxel pattern analysis using a connectivity map of the default mode network showed good performance, with an accuracy of 81.9% for AD and MCI identification within the ADNI, but the classification model obtained from the ADNI failed to classify AD, MCI, and healthy elderly adults from our site, with an accuracy of only 43.1%. In contrast, a functional connectivity index of the medial temporal lobe based on the frequency distribution showed moderate performance, with an accuracy of 76.5-80.3% for AD identification within the ADNI. The performance of this index was similar for our data, with an accuracy of 73.9-82.6%. The frequency distribution-based index of functional connectivity could be a good biomarker for AD across multiple sites.

Discriminating cognitive status in Parkinson's disease through functional connectomics and machine learning

There is growing interest in the potential of neuroimaging to help develop non-invasive biomarkers in neurodegenerative diseases. In this study, connection-wise patterns of functional connectivity were used to distinguish Parkinson’s disease patients according to cognitive status using machine learning. Two independent subject samples were assessed with resting-state fMRI. The first (training) sample comprised 38 healthy controls and 70 Parkinson’s disease patients (27 with mild cognitive impairment). The second (validation) sample included 25 patients (8 with mild cognitive impairment). The Brainnetome atlas was used to reconstruct the functional connectomes. Using a support vector machine trained on features selected through randomized logistic regression with leave-one-out cross-validation, a mean accuracy of 82.6% (p < 0.002) was achieved in separating patients with mild cognitive impairment from those without it in the training sample. The model trained on the whole training sample achieved an accuracy of 80.0% when used to classify the validation sample (p = 0.006). Correlation analyses showed that the connectivity level in the edges most consistently selected as features was associated with memory and executive function performance in the patient group. Our results demonstrate that connection-wise patterns of functional connectivity may be useful for discriminating Parkinson’s disease patients according to the presence of cognitive deficits.