A support vector machine-based method to identify mild cognitive impairment with multi-level characteristics of magnetic resonance imaging

Cortical and Subcortical Gray Matter Abnormalities in Mild Cognitive Impairment

Gray matter changes are thought to be closely related to cognitive decline in mild cognitive impairment (MCI) patients. The study aimed to explore cortical and subcortical structural alterations in MCI and their association with cognitive assessment. 24 MCI patients and 22 normal controls (NCs) were included. Voxel-based morphometry (VBM), vertex-based shape analysis and surface-based morphometry (SBM) analysis were applied to explore subcortical nuclei volume, shape and cortical morphology. Correlations between structural changes and cognition were explored using spearman correlation analysis. Support vector machine (SVM) classification evaluated MCI identification accuracy. MCI patients showed significant atrophy in the left thalamus, left hippocampus, left amygdala, right pallidum, right hippocampus, along with inward deformation in the left amygdala. SBM analysis revealed that MCI group exhibited shallower sulci depth in the left hemisphere and increased cortical gyrification index (GI) in the right frontal gyrus. Correlation analysis showed the positive correlation between right hippocampus volume and episodic memory, while negative correlation between the altered GI and memory performance in MCI group. SVM analysis demonstrated superior performance of sulci depth and GI derived from SBM in MCI identification. When combined with cortical and subcortical metrics, SVM achieved a peak accuracy of 89% in distinguishing MCI from NC. The study reveals significant gray matter structural changes in MCI, suggesting their potential role in underlying functional differences and neural mechanisms behind memory impairment in MCI.

Classification of Alzheimer's disease: application of a transfer learning deep Q-network method

Early diagnosis is crucial to slowing the progression of Alzheimer's disease (AD), so it is urgent to find an effective diagnostic method for AD. This study intended to investigate whether the transfer learning approach of deep Q-network (DQN) could effectively distinguish AD patients using local metrics of resting-state functional magnetic resonance imaging (rs-fMRI) as features. This study included 1310 subjects from the Consortium for Reliability and Reproducibility (CoRR) and 50 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) GO/2. The amplitude of low-frequency fluctuation (ALFF), fractional ALFF (fALFF) and percent amplitude of fluctuation (PerAF) were extracted as features using the Power 264 atlas. Based on gender bias in AD, we searched for transferable similar parts between the CoRR feature matrix and the ADNI feature matrix, resulting in the CoRR similar feature matrix served as the source domain and the ADNI similar feature matrix served as the target domain. A DQN classifier was pre-trained in the source domain and transferred to the target domain. Finally, the transferred DQN classifier was used to classify AD and healthy controls (HC). A permutation test was performed. The DQN transfer learning achieved a classification accuracy of 86.66% (p < 0.01), recall of 83.33% and precision of 83.33%. The findings suggested that the transfer learning approach using DQN could be an effective way to distinguish AD from HC. It also revealed the potential value of local brain activity in AD clinical diagnosis.

Structural degeneration of the nucleus basalis of Meynert in mild cognitive impairment and Alzheimer's disease - Evidence from an MRI-based meta-analysis

Recent models of Alzheimer's disease (AD) suggest that neuropathological changes of the medial temporal lobe, especially entorhinal cortex, are preceded by degenerations of the cholinergic Nucleus basalis of Meynert (NbM). Evidence from imaging studies in humans, however, is limited. Therefore, we performed an activation-likelihood estimation meta-analysis on whole brain voxel-based morphometry (VBM) MRI data from 54 experiments and 2581 subjects in total. It revealed, compared to healthy older controls, reduced gray matter in the bilateral NbM in AD, but only limited evidence for such an effect in patients with mild cognitive impairment (MCI), which typically precedes AD. Both patient groups showed less gray matter in the amygdala and hippocampus, with hints towards more pronounced amygdala effects in AD. We discuss our findings in the context of studies that highlight the importance of the cholinergic basal forebrain in learning and memory throughout the lifespan, and conclude that they are partly compatible with pathological staging models suggesting initial and pronounced structural degenerations within the NbM in the progression of AD.

Functional brain activity in patients with amnestic mild cognitive impairment: an rs-fMRI study

Background

Amnestic mild cognitive impairment (aMCI) is an early stage of Alzheimer's disease (AD). Regional homogeneity (ReHo) and amplitude of low-frequency fluctuation (ALFF) are employed to explore spontaneous brain function in patients with aMCI. This study applied ALFF and ReHo indicators to analyze the neural mechanism of aMCI by resting-state functional magnetic resonance imaging (rs-fMRI).

Methods

Twenty-six patients with aMCI were included and assigned to the aMCI group. The other 26 healthy subjects were included as a healthy control (HC) group. Rs-fMRI was performed for all participants in both groups. Between-group comparisons of demographic data and neuropsychological scores were analyzed using SPSS 25.0. Functional imaging data were analyzed using DPARSF and SPM12 software based on MATLAB 2017a. Gender, age, and years of education were used as covariates to obtain ALFF and ReHo indices.

Results

Compared with HC group, ALFF decreased in the left fusiform gyrus, left superior temporal gyrus, and increased in the left cerebellum 8, left inferior temporal gyrus, left superior frontal gyrus (BA11), and right inferior temporal gyrus (BA20) in the aMCI group (p < 0.05, FWE correction). In addition, ReHo decreased in the right middle temporal gyrus and right anterior cuneiform lobe, while it increased in the left middle temporal gyrus, left inferior temporal gyrus, cerebellar vermis, right parahippocampal gyrus, left caudate nucleus, right thalamus, and left superior frontal gyrus (BA6) (p < 0.05, FWE correction). In the aMCI group, the ALFF of the left superior frontal gyrus was negatively correlated with Montreal Cognitive Assessment (MoCA) score (r = -0.437, p = 0.026), and the ALFF of the left superior temporal gyrus was positively correlated with the MoCA score (r = 0.550, p = 0.004). The ReHo of the right hippocampus was negatively correlated with the Mini-Mental State Examination (MMSE) score (r = -0.434, p = 0.027), and the ReHo of the right middle temporal gyrus was positively correlated with MMSE score (r = 0.392, p = 0.048).

Conclusion

Functional changes in multiple brain regions rather than in a single brain region have been observed in patients with aMCI. The abnormal activity of multiple specific brain regions may be a manifestation of impaired central function in patients with aMCI.

Elevated serum platelet count inhibits the effects of brain functional changes on cognitive function in patients with mild cognitive impairment: A resting-state functional magnetic resonance imaging study

Objective

Brain function remodeling has been observed in patients with mild cognitive impairment (MCI) and is closely associated with cognitive performance. However, it is not clear if this relationship is influenced by complete blood counts. This study investigated the role of complete blood counts in the relationship between brain function and cognitive performance.

Methods

Twenty-two MCI patients and eighteen controls were enrolled. All subjects underwent resting-state functional magnetic resonance imaging. A neuropsychological battery [Mini-Mental Status Examination, Auditory Verbal Learning Test (AVLT), Symbol Digit Modalities Test, Boston Naming Test (BNT), Shape Trails Test B (STT-B), Rey Complex Figure Test (RCFT), Hamilton Anxiety Rating Scale (HAMA), and Hamilton Depression Scale] was used to assess cognitive function, and MCI patients received complete blood counts tests for red blood cells (RBC), white blood cells, hemoglobin (HGB), monocytes, and platelet counts (PLT).

Results

Compared with controls, MCI patients demonstrated significantly decreased amplitude of low-frequency fluctuation (ALFF) values in the left dorsolateral superior frontal gyrus, left post orbitofrontal cortex, right medial superior frontal gyrus, right insula, and left triangular inferior frontal gyrus. In the MCI group, there were associations between ALFF values of the left hippocampus (HIP.L) and AVLT (p = 0.003) and AVLT-N5 scores (p = 0.001); ALFF values of the right supramarginal gyrus (SMG.R) and BNT scores (p = 0.044); ALFF values of the right superior temporal gyrus (STG.R) and BNT scores (p = 0.022); ALFF values of the left precuneus (PCUN.L) and STT-B time (p = 0.012); and ALFF values of the left caudate nucleus (CAU.L) and RCFT-time (p = 0.036). Moreover, the HAMA scores were negatively correlated with RBC and HGB levels, and positively correlated with monocyte count. The PLT count was positively correlated with STT-B time. Additionally, high PLT count inhibited the effect of ALFF values of the PCUN. L on STT-B performance in MCI patients (p = 0.0207).

Conclusion

ALFF values of the HIP. L, SMG.R, STG. R, PCUN.L, and CAU. L were associated with decreased memory, language, executive function, and visuospatial ability in MCI patients. Notably, elevated PLT count could inhibit the effect of brain functional changes in the PCUN.L on executive function in MCI patients.

Episodic Memory-Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer's Disease: A Multicenter Study Based on Machine Learning

BACKGROUND

Individualized and reliable biomarkers are crucial for diagnosing Alzheimer's disease (AD). However, lack of accessibility and neurobiological correlation are the main obstacles to their clinical application. Machine learning algorithms can effectively identify personalized biomarkers based on the prominent symptoms of AD.

METHODS

Episodic memory-related magnetic resonance imaging (MRI) features of 143 patients with amnesic mild cognitive impairment (MCI) were identified using a multivariate relevance vector regression algorithm. The support vector machine classification model was constructed using these MRI features and verified in 2 independent datasets (N = 994). The neurobiological basis was also investigated based on cognitive assessments, neuropathologic biomarkers of cerebrospinal fluid, and positron emission tomography images of amyloid-β plaques.

RESULTS

The combination of gray matter volume and amplitude of low-frequency fluctuation MRI features accurately predicted episodic memory impairment in individual patients with amnesic MCI (r = 0.638) when measured using an episodic memory assessment panel. The MRI features that contributed to episodic memory prediction were primarily distributed across the default mode network and limbic network. The classification model based on these features distinguished patients with AD from normal control subjects with more than 86% accuracy. Furthermore, most identified episodic memory-related regions showed significantly different amyloid-β positron emission tomography measurements among the AD, MCI, and normal control groups. Moreover, the classification outputs significantly correlated with cognitive assessment scores and cerebrospinal fluid pathological biomarkers' levels in the MCI and AD groups.

CONCLUSIONS

Neuroimaging features can reflect individual episodic memory function and serve as potential diagnostic biomarkers of AD.

Inherent regional brain activity changes in male obstructive sleep apnea with mild cognitive impairment: A resting-state magnetic resonance study

Obstructive sleep apnea (OSA) is the most common sleep disorder worldwide. Previous studies have shown that OSA patients are often accompanied by cognitive function loss, and the underlying neurophysiological mechanism is still unclear. This study aimed to determine whether there are differences in regional homogeneity (Reho) and functional connectivity (FC) across the brain between OSA patients with MCI (OSA-MCI) and those without MCI (OSA-nMCI) and whether such differences can be used to distinguish the two groups. Resting state magnetic resonance data were collected from 48 OSA-MCI patients and 47 OSA-nMCI patients. The brain regions with significant differences in Reho and FC between the two groups were identified, and the Reho and FC features were combined with machine learning methods for classification. Compared with OSA-nMCI patients, OSA-MCI patients showed significantly lower Reho in bilateral lingual gyrus and left superior temporal gyrus. OSA-MCI patients also showed significantly lower FC between the bilateral lingual gyrus and bilateral cuneus, left superior temporal gyrus and left middle temporal gyrus, middle frontal gyrus, and bilateral posterior cingulate/calcarine/cerebellar anterior lobe. Based on Reho and FC features, logistic regression classification accuracy was 0.87; sensitivity, 0.70; specificity, 0.89; and area under the curve, 0.85. Correlation analysis showed that MoCA scale score in OSA patients was significant positive correlation sleep efficiency and negatively correlation with neck circumference. In conclusion, our results showed that the OSA-MCI group showed decreased Reho and FC in specific brain regions compared with the OSA-nMCI group, which may help to understand the underlying neuroimaging mechanism of OSA leading to cognitive dysfunction and may serve as a potential biomarker to distinguish whether OSA is accompanied by cognitive impairment.

Altered dynamic intrinsic brain activity of the default mode network in Alzheimer’s disease: A resting-state fMRI study

Objective

Static regional homogeneity (ReHo) based on the resting-state functional magnetic resonance imaging (rs-fMRI) has been used to study intrinsic brain activity (IBA) in Alzheimer’s disease (AD). However, few studies have examined dynamic ReHo (dReHo) in AD. In this study, we used rs-fMRI and dReHo to investigate the alterations in dynamic IBA in patients with AD to uncover dynamic imaging markers of AD.

Method

In total, 111 patients with AD, 29 patients with mild cognitive impairment (MCI), and 73 healthy controls (HCs) were recruited for this study ultimately. After the rs-fMRI scan, we calculated the dReHo values using the sliding window method. ANOVA and post hoc two-sample t-tests were used to detect the differences among the three groups. We used the mini-mental state examination (MMSE) and Montreal Cognitive Assessment (MoCA) to evaluate the cognitive function of the subjects. The associations between the MMSE score, MoCA score, and dReHo were assessed by the Pearson correlation analysis.

Results

Significant dReHo variability in the right middle frontal gyrus (MFG) and right posterior cingulate gyrus (PCG) was detected in the three groups through ANOVA. In post hoc analysis, the AD group exhibited significantly greater dReHo variability in the right MFG than the MCI group. Compared with the HC group, the AD group exhibited significantly increased dReHo variability in the right PCG. Furthermore, dReHo variability in the right PCG was significantly negatively correlated with the MMSE and MoCA scores of patients with AD.

Conclusion

Disrupted dynamic IBA in the DMN might be an important characteristic of AD and could be a potential biomarker for the diagnosis or prognosis of AD.

Predictive models for small-for-gestational-age births in women exposed to pesticides before pregnancy based on multiple machine learning algorithms

Background

The association between prenatal pesticide exposures and a higher incidence of small-for-gestational-age (SGA) births has been reported. No prediction model has been developed for SGA neonates in pregnant women exposed to pesticides prior to pregnancy.

Methods

A retrospective cohort study was conducted using information from the National Free Preconception Health Examination Project between 2010 and 2012. A development set (n = 606) and a validation set (n = 151) of the dataset were split at random. Traditional logistic regression (LR) method and six machine learning classifiers were used to develop prediction models for SGA neonates. The Shapley Additive Explanation (SHAP) model was applied to determine the most influential variables that contributed to the outcome of the prediction.

Results

757 neonates in total were analyzed. SGA occurred in 12.9% (n = 98) of cases overall. With an area under the receiver-operating-characteristic curve (AUC) of 0.855 [95% confidence interval (CI): 0.752–0.959], the model based on category boosting (CatBoost) algorithm obtained the best performance in the validation set. With the exception of the LR model (AUC: 0.691, 95% CI: 0.554–0.828), all models had good AUCs. Using recursive feature elimination (RFE) approach to perform the feature selection, we included 15 variables in the final model based on CatBoost classifier, achieving the AUC of 0.811 (95% CI: 0.675–0.947).

Conclusions

Machine learning algorithms can develop satisfactory tools for SGA prediction in mothers exposed to pesticides prior to pregnancy, which might become a tool to predict SGA neonates in the high-risk population.

Impact of a multidomain lifestyle intervention on regional spontaneous brain activity

In the SoUth Korean study to PrEvent cognitive impaiRment and protect BRAIN health through lifestyle intervention in at-risk elderly people (SUPERBRAIN), we evaluated the impact of multidomain lifestyle intervention on regional homogeneity (ReHo) in resting-state functional brain magnetic resonance imaging (MRI) data. Of 152 participants aged 60–79 years without dementia assigned to either facility-based multidomain intervention (FMI), home-based MI, or controls, we analyzed 56 scanned MRIs at baseline and 24 weeks. ReHo values from regions with significant longitudinal changes were compared between the intervention and control groups and their correlations with the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS) or serum brain-derived neurotrophic factor (BDNF) were evaluated. ReHo values in the left medial orbitofrontal gyrus and right superior parietal lobule were increased [p = 0.021, correlated positively with serum BDNF changes (r = 0.504, p = 0.047)] and decreased [p = 0.021, correlated negatively with changes in the total (r = −0.509, p = 0.044) and attention (r = −0.562, p = 0.023). RBANS], respectively, in the participants assigned to the FMI group than those of the controls. Our results suggest that facility-based group preventive strategies may have cognitive benefits through neuroplastic changes in functional processing circuits in the brain areas which play a crucial role in the adaptive learning and internally directed cognition.

An Activation Likelihood Estimation Meta-Analysis of Specific Functional Alterations in Dorsal Attention Network in Mild Cognitive Impairment

Background

Mild cognitive impairment (MCI) is known as the prodromal stage of the Alzheimer’s disease (AD) spectrum. The recent studies have advised that functional alterations in the dorsal attention network (DAN) could be used as a sensitive marker to forecast the progression from MCI to AD. Therefore, our aim was to investigate specific functional alterations in the DAN in MCI.

Methods

We systematically searched PubMed, EMBASE, and Web of Science and chose relevant articles based on the three functional indicators, the amplitude of low-frequency fluctuation (ALFF), regional homogeneity (ReHo), and functional connectivity (FC) in the DAN in MCI. Based on the activation likelihood estimation, we accomplished the aggregation of specific coordinates and the analysis of functional alterations.

Results

A total of 38 studies were involved in our meta-analysis. By summing up included articles, we acquired specific brain region alterations in the DAN mainly in the superior temporal gyrus (STG), middle temporal gyrus (MTG), superior frontal gyrus (SFG), middle frontal gyrus (MFG), inferior frontal gyrus (IFG), precentral gyrus (preCG), inferior parietal lobule (IPL), superior parietal lobule (SPL). At the same time, the key area that shows anti-interaction with default mode network included the IPL in the DAN. The one showing interactions with executive control network was mainly in the MFG. Finally, the frontoparietal network showed a close connection with DAN especially in the IPL and IFG.

Conclusion

This study demonstrated abnormal functional markers in the DAN and its interactions with other networks in MCI group, respectively. It provided the foundation for future targeted interventions in preventing the progression of AD.

Systematic Review Registration

[https://www.crd.york.ac.uk/PROSPERO/], identifier [CRD42021287958].

Artificial intelligence in brain MRI analysis of Alzheimer's disease over the past 12 years: A systematic review

INTRODUCTION

Multiple structural brain changes in Alzheimer's disease (AD) and mild cognitive impairment (MCI) have been revealed on magnetic resonance imaging (MRI). There is a fast-growing effort in applying artificial intelligence (AI) to analyze these data. Here, we review and evaluate the AI studies in brain MRI analysis with synthesis.

METHODS

A systematic review of the literature, spanning the years from 2009 to 2020, was completed using the PubMed database. AI studies using MRI imaging to investigate normal aging, mild cognitive impairment, and AD-dementia were retrieved for review. Bias assessment was completed using the PROBAST criteria.

RESULTS

97 relevant studies were included in the review. The studies were typically focused on the classification of AD, MCI, and normal aging (71% of the reported studies) and the prediction of MCI conversion to AD (25%). The best performance was achieved by using the deep learning-based convolution neural network algorithms (weighted average accuracy 89%), in contrast to 76-86% using Logistic Regression, Support Vector Machines, and other AI methods.

DISCUSSION

The synthesized evidence is paramount to developing sophisticated AI approaches to reliably capture and quantify multiple subtle MRI changes in the whole brain that exemplify the complexity and heterogeneity of AD and brain aging.

Development and Evaluation of a Machine Learning Prediction Model for Small-for-Gestational-Age Births in Women Exposed to Radiation before Pregnancy

Exposure to radiation has been associated with increased risk of delivering small-for-gestational-age (SGA) newborns. There are no tools to predict SGA newborns in pregnant women exposed to radiation before pregnancy. Here, we aimed to develop an array of machine learning (ML) models to predict SGA newborns in women exposed to radiation before pregnancy. Patients’ data was obtained from the National Free Preconception Health Examination Project from 2010 to 2012. The data were randomly divided into a training dataset (n = 364) and a testing dataset (n = 91). Eight various ML models were compared for solving the binary classification of SGA prediction, followed by a post hoc explainability based on the SHAP model to identify and interpret the most important features that contribute to the prediction outcome. A total of 455 newborns were included, with the occurrence of 60 SGA births (13.2%). Overall, the model obtained by extreme gradient boosting (XGBoost) achieved the highest area under the receiver-operating-characteristic curve (AUC) in the testing set (0.844, 95% confidence interval (CI): 0.713–0.974). All models showed satisfied AUCs, except for the logistic regression model (AUC: 0.561, 95% CI: 0.355–0.768). After feature selection by recursive feature elimination (RFE), 15 features were included in the final prediction model using the XGBoost algorithm, with an AUC of 0.821 (95% CI: 0.650–0.993). ML algorithms can generate robust models to predict SGA newborns in pregnant women exposed to radiation before pregnancy, which may thus be used as a prediction tool for SGA newborns in high-risk pregnant women.

Altered Patterns of Amplitude of Low-Frequency Fluctuations and Fractional Amplitude of Low-Frequency Fluctuations Between Amnestic and Vascular Mild Cognitive Impairment: An ALE-Based Comparative Meta-Analysis

Background: Changes in the amplitude of low-frequency fluctuations (ALFF) and the fractional amplitude of low-frequency fluctuations (fALFF) have provided stronger evidence for the pathophysiology of cognitive impairment. Whether the altered patterns of ALFF and fALFF differ in amnestic cognitive impairment (aMCI) and vascular mild cognitive impairment (vMCI) is largely unknown. The purpose of this study was to explore the ALFF/fALFF changes in the two diseases and to further explore whether they contribute to the diagnosis and differentiation of these diseases.

Methods: We searched PubMed, Ovid, and Web of Science databases for articles on studies using the ALFF/fALFF method in patients with aMCI and vMCI. Based on the activation likelihood estimation (ALE) method, connectivity modeling based on coordinate meta-analysis and functional meta-analysis was carried out.

Results: Compared with healthy controls (HCs), patients with aMCI showed increased ALFF/fALFF in the bilateral parahippocampal gyrus/hippocampus (PHG/HG), right amygdala, right cerebellum anterior lobe (CAL), left middle temporal gyrus (MTG), left cerebrum temporal lobe sub-gyral, left inferior temporal gyrus (ITG), and left cerebrum limbic lobe uncus. Meanwhile, decreased ALFF/fALFF values were also revealed in the bilateral precuneus (PCUN), bilateral cuneus (CUN), and bilateral posterior cingulate (PC) in patients with aMCI. Compared with HCs, patients with vMCI predominantly showed decreased ALFF/fALFF in the bilateral CUN, left PCUN, left PC, and right cingulate gyrus (CG).

Conclusions: The present findings suggest that ALFF and fALFF displayed remarkable altered patterns between aMCI and vMCI when compared with HCs. Thus, the findings of this study may serve as a reliable tool for distinguishing aMCI from vMCI, which may help understand the pathophysiological mechanisms of these diseases.

Machine Learning Models to Predict Cognitive Impairment of Rodents Subjected to Space Radiation

This research uses machine-learned computational analyses to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is from a rodent model exposed to ≤15 cGy of individual galactic cosmic radiation (GCR) ions: 4He, 16O, 28Si, 48Ti, or 56Fe, expected for a Lunar or Mars mission. This work investigates rats at a subject-based level and uses performance scores taken before irradiation to predict impairment in attentional set-shifting (ATSET) data post-irradiation. Here, the worst performing rats of the control group define the impairment thresholds based on population analyses via cumulative distribution functions, leading to the labeling of impairment for each subject. A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the simple discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the compound discrimination (CD) stage. On a subject-based level, implementing machine learning (ML) classifiers such as the Gaussian naïve Bayes, support vector machine, and artificial neural networks identifies rats that have a higher tendency for impairment after GCR exposure. The algorithms employ the experimental prescreen performance scores as multidimensional input features to predict each rodent's susceptibility to cognitive impairment due to space radiation exposure. The receiver operating characteristic and the precision-recall curves of the ML models show a better prediction of impairment when 56Fe is the ion in question in both SD and CD stages. They, however, do not depict impairment due to 4He in SD and 28Si in CD, suggesting no dose-dependent impairment response in these cases. One key finding of our study is that prescreen performance scores can be used to predict the ATSET performance impairments. This result is significant to crewed space missions as it supports the potential of predicting an astronaut's impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. Future research can focus on constructing ML ensemble methods to integrate the findings from the methodologies implemented in this study for more robust predictions of cognitive decrements due to space radiation exposure.

Recognition of Dementia Biomarkers With Deep Finer-DBN

The treatment of neurodegenerative diseases is expensive, and long-term treatment makes families bear a heavy burden. Accumulating evidence suggests that the high conversion rate can possibly be reduced if clinical interventions are applied at the early stage of brain diseases. Thus, a variety of deep learning methods are utilized to recognize the early stages of neurodegenerative diseases for clinical intervention and treatment. However, most existing methods have ignored the issue of sample imbalance, which often makes it difficult to train an effective model due to lack of a large number of negative samples. To address this problem, we propose a two-stage method, which is used to learn the compression and recover rules of normal subjects so that potential negative samples can be detected. The experimental results show that the proposed method can not only obtain a superb recognition result, but also give an explanation that conforms to the physiological mechanism. Most importantly, the deep learning model does not need to be retrained for each type of disease, which can be widely applied to the diagnosis of various brain diseases. Furthermore, this research could have great potential in understanding regional dysfunction of various brain diseases.

Identifying Mild Cognitive Impairment with Random Forest by Integrating Multiple MRI Morphological Metrics

Mild cognitive impairment (MCI) exhibits a high risk of progression to Alzheimer's disease (AD), and it is commonly deemed as the precursor of AD. It is important to find effective and robust ways for the early diagnosis of MCI. In this paper, a random forest-based method combining multiple morphological metrics was proposed to identify MCI from normal controls (NC). Voxel-based morphometry, deformation-based morphometry, and surface-based morphometry were utilized to extract morphological metrics such as gray matter volume, Jacobian determinant value, cortical thickness, gyrification index, sulcus depth, and fractal dimension. An initial discovery dataset (56 MCI/55 NC) from the ADNI were used to construct classification models and the performances were testified with 10-fold cross validation. To test the generalization of the proposed method, two extra validation datasets including longitudinal ADNI data (30 MCI/16 NC) and collected data from Xuanwu Hospital (27 MCI/32 NC) were employed respectively to evaluate the performance. No matter whether testing was done on the discovery dataset or the extra validation datasets, the accuracies were about 80% with the combined morphological metrics, which were significantly superior to single metric (accuracy: 45% ∼76%) and also displayed good generalization across datasets. Additionally, gyrification index and cortical thickness derived from surface-based morphometry outperformed other features in MCI identification, suggesting they were some key morphological biomarkers for early MCI diagnosis. Combining the multiple morphological metrics together resulted in a significantly better and reliable identification model, which may be helpful to assist in the clinical diagnosis of MCI.

An Effective Brain Imaging Biomarker for AD and aMCI: ALFF in Slow-5 Frequency Band

BACKGROUND

As a potential brain imaging biomarker, amplitude of low frequency fluctuation (ALFF) has been used as a feature to distinguish patients with Alzheimer's disease (AD) and amnestic mild cognitive impairment (aMCI) from normal controls (NC). However, it remains unclear whether the frequency-dependent pattern of ALFF alterations can effectively distinguish the different phases of the disease.

METHODS

In the present study, 52 AD and 50 aMCI patients were enrolled together with 43 NC in total. The ALFF values were calculated in the following three frequency bands: classical (0.01-0.08 Hz), slow-4 (0.027-0.073 Hz) and slow-5 (0.01-0.027 Hz) for the three different groups. Subsequently, the local functional abnormalities were employed as features to examine the effect of classification among AD, aMCI and NC using a support vector machine (SVM).

RESULTS

We found that the among-group differences of ALFF in the different frequency bands were mainly located in the left hippocampus (HP), right HP, bilateral posterior cingulate cortex (PCC) and bilateral precuneus (PCu), left angular gyrus (AG) and left medial prefrontal cortex (mPFC). When the local functional abnormalities were employed as features, we identified that the ALFF in the slow-5 frequency band showed the highest accuracy to distinguish among the three groups.

CONCLUSION

These findings may deepen our understanding of the pathogenesis of AD and suggest that slow-5 frequency band may be helpful to explore the pathogenesis and distinguish the phases of this disease.

Voxelwise Meta-Analysis of Gray Matter Abnormalities in Mild Cognitive Impairment and Subjective Cognitive Decline Using Activation Likelihood Estimation

Background: Voxel-based morphometry studies have not yielded consistent results among patients with mild cognitive impairment (MCI) and subjective cognitive decline (SCD). Objective: Therefore, we aimed to conduct a meta-analysis of gray matter (GM) abnormalities acquired from these studies to determine their respective neuroanatomical changes. Methods: We systematically searched for voxel-based whole-brain morphometry studies that compared MCI or SCD subjects with healthy controls in PubMed, Web of Science, and EMBASE databases. We used the coordinate-based method of activation likelihood estimation to determine GM changes in SCD, MCI, and MCI sub-groups (amnestic MCI and non-amnestic MCI). Results: A total of 45 studies were included in our meta-analysis. In the MCI group, we found structural atrophy of the bilateral hippocampus, parahippocampal gyrus (PHG), amygdala, right lateral globus pallidus, right insula, and left middle temporal gyrus. The aMCI group exhibited GM atrophy in the bilateral hippocampus, PHG, and amygdala. The naMCI group presented with structural atrophy in the right putamen, right insula, right precentral gyrus, left medial/superior frontal gyrus, and left anterior cingulate. The right lingual gyrus, right cuneus, and left medial frontal gyrus were atrophic GM regions in the SCD group. Conclusion: Our meta-analysis identified unique patterns of neuroanatomical alternations in both the MCI and SCD group. Structural changes in SCD patients provide new evidence for the notion that subtle impairment of visual function, perception, and cognition may be related to early signs of cognitive impairment. In addition, our findings provide a foundation for future targeted interventions at different stages of preclinical Alzheimer’s disease.

Machine Learning in Neuroimaging: A New Approach to Understand Acupuncture for Neuroplasticity

The effects of acupuncture facilitating neural plasticity for treating diseases have been identified by clinical and experimental studies. In the last two decades, the application of neuroimaging techniques in acupuncture research provided visualized evidence for acupuncture promoting neuroplasticity. Recently, the integration of machine learning (ML) and neuroimaging techniques becomes a focus in neuroscience and brings a new and promising approach to understand the facilitation of acupuncture on neuroplasticity at the individual level. This review is aimed at providing an overview of this rapidly growing field by introducing the commonly used ML algorithms in neuroimaging studies briefly and analyzing the characteristics of the acupuncture studies based on ML and neuroimaging, so as to provide references for future research.

Regional Hurst Exponent Reflects Impulsivity-Related Alterations in Fronto-Hippocampal Pathways Within the Waiting Impulsivity Network

In general, the Hurst exponent. is used as a measure of long-term memory of time series. In previous neuroimaging studies, H has been introduced as one important parameter to define resting-state networks, reflecting upon global scale-free properties emerging from a network. H has been examined in the waiting impulsivity (WI) network in an earlier study. We found that alterations of H in the anterior cingulate cortex (H^ACC) and the nucleus accumbens (H^NAcc) were lower in high impulsive (highIMP) compared to low impulsive (lowIMP) participants. Following up on those findings, we addressed the relation between altered fractality in H^ACC and H^NAcc and brain activation and neural network connectivity. To do so, brain activation maps were calculated, and network connectivity was determined using the Dynamic Causal Modeling (DCM) approach. Finally, 1–H scores were determined to quantify the alterations of H. This way, the focus of the analyses was placed on the potential effects of alterations of H on neural network activation and connectivity. Correlation analyses between the alterations of H^ACC/H^NAcc and activation maps and DCM estimates were performed. We found that the alterations of H predominantly correlated with fronto-hippocampal pathways and correlations were significant only in highIMP subjects. For example, alterations of H^ACC was associated with a decrease in neural activation in the right HC in combination with increased ACC-hippocampal connectivity. Alteration inH^NAcc, in return, was related to an increase in bilateral prefrontal activation in combination with increased fronto-hippocampal connectivity. The findings, that the WI network was related to H alteration in highIMP subjects indicated that impulse control was not reduced per se but lacked consistency. Additionally, H has been used to describe long-term memory processes before, e.g., in capital markets, energy future prices, and human memory. Thus, current findings supported the relation of H toward memory processing even when further prominent cognitive functions were involved.

Structural magnetic resonance imaging for the early diagnosis of dementia due to Alzheimer's disease in people with mild cognitive impairment

BACKGROUND

Mild cognitive impairment (MCI) due to Alzheimer's disease is the symptomatic predementia phase of Alzheimer's disease dementia, characterised by cognitive and functional impairment not severe enough to fulfil the criteria for dementia. In clinical samples, people with amnestic MCI are at high risk of developing Alzheimer's disease dementia, with annual rates of progression from MCI to Alzheimer's disease estimated at approximately 10% to 15% compared with the base incidence rates of Alzheimer's disease dementia of 1% to 2% per year.

OBJECTIVES

To assess the diagnostic accuracy of structural magnetic resonance imaging (MRI) for the early diagnosis of dementia due to Alzheimer's disease in people with MCI versus the clinical follow-up diagnosis of Alzheimer's disease dementia as a reference standard (delayed verification). To investigate sources of heterogeneity in accuracy, such as the use of qualitative visual assessment or quantitative volumetric measurements, including manual or automatic (MRI) techniques, or the length of follow-up, and age of participants. MRI was evaluated as an add-on test in addition to clinical diagnosis of MCI to improve early diagnosis of dementia due to Alzheimer's disease in people with MCI.

SEARCH METHODS

On 29 January 2019 we searched Cochrane Dementia and Cognitive Improvement's Specialised Register and the databases, MEDLINE, Embase, BIOSIS Previews, Science Citation Index, PsycINFO, and LILACS. We also searched the reference lists of all eligible studies identified by the electronic searches.

SELECTION CRITERIA

We considered cohort studies of any size that included prospectively recruited people of any age with a diagnosis of MCI. We included studies that compared the diagnostic test accuracy of baseline structural MRI versus the clinical follow-up diagnosis of Alzheimer's disease dementia (delayed verification). We did not exclude studies on the basis of length of follow-up. We included studies that used either qualitative visual assessment or quantitative volumetric measurements of MRI to detect atrophy in the whole brain or in specific brain regions, such as the hippocampus, medial temporal lobe, lateral ventricles, entorhinal cortex, medial temporal gyrus, lateral temporal lobe, amygdala, and cortical grey matter.

DATA COLLECTION AND ANALYSIS

Four teams of two review authors each independently reviewed titles and abstracts of articles identified by the search strategy. Two teams of two review authors each independently assessed the selected full-text articles for eligibility, extracted data and solved disagreements by consensus. Two review authors independently assessed the quality of studies using the QUADAS-2 tool. We used the hierarchical summary receiver operating characteristic (HSROC) model to fit summary ROC curves and to obtain overall measures of relative accuracy in subgroup analyses. We also used these models to obtain pooled estimates of sensitivity and specificity when sufficient data sets were available.

MAIN RESULTS

We included 33 studies, published from 1999 to 2019, with 3935 participants of whom 1341 (34%) progressed to Alzheimer's disease dementia and 2594 (66%) did not. Of the participants who did not progress to Alzheimer's disease dementia, 2561 (99%) remained stable MCI and 33 (1%) progressed to other types of dementia. The median proportion of women was 53% and the mean age of participants ranged from 63 to 87 years (median 73 years). The mean length of clinical follow-up ranged from 1 to 7.6 years (median 2 years). Most studies were of poor methodological quality due to risk of bias for participant selection or the index test, or both. Most of the included studies reported data on the volume of the total hippocampus (pooled mean sensitivity 0.73 (95% confidence interval (CI) 0.64 to 0.80); pooled mean specificity 0.71 (95% CI 0.65 to 0.77); 22 studies, 2209 participants). This evidence was of low certainty due to risk of bias and inconsistency. Seven studies reported data on the atrophy of the medial temporal lobe (mean sensitivity 0.64 (95% CI 0.53 to 0.73); mean specificity 0.65 (95% CI 0.51 to 0.76); 1077 participants) and five studies on the volume of the lateral ventricles (mean sensitivity 0.57 (95% CI 0.49 to 0.65); mean specificity 0.64 (95% CI 0.59 to 0.70); 1077 participants). This evidence was of moderate certainty due to risk of bias. Four studies with 529 participants analysed the volume of the total entorhinal cortex and four studies with 424 participants analysed the volume of the whole brain. We did not estimate pooled sensitivity and specificity for the volume of these two regions because available data were sparse and heterogeneous. We could not statistically evaluate the volumes of the lateral temporal lobe, amygdala, medial temporal gyrus, or cortical grey matter assessed in small individual studies. We found no evidence of a difference between studies in the accuracy of the total hippocampal volume with regards to duration of follow-up or age of participants, but the manual MRI technique was superior to automatic techniques in mixed (mostly indirect) comparisons. We did not assess the relative accuracy of the volumes of different brain regions measured by MRI because only indirect comparisons were available, studies were heterogeneous, and the overall accuracy of all regions was moderate.

AUTHORS' CONCLUSIONS

The volume of hippocampus or medial temporal lobe, the most studied brain regions, showed low sensitivity and specificity and did not qualify structural MRI as a stand-alone add-on test for an early diagnosis of dementia due to Alzheimer's disease in people with MCI. This is consistent with international guidelines, which recommend imaging to exclude non-degenerative or surgical causes of cognitive impairment and not to diagnose dementia due to Alzheimer's disease. In view of the low quality of most of the included studies, the findings of this review should be interpreted with caution. Future research should not focus on a single biomarker, but rather on combinations of biomarkers to improve an early diagnosis of Alzheimer's disease dementia.

Multi-modal latent space inducing ensemble SVM classifier for early dementia diagnosis with neuroimaging data

Fusing multi-modality data is crucial for accurate identification of brain disorder as different modalities can provide complementary perspectives of complex neurodegenerative disease. However, there are at least four common issues associated with the existing fusion methods. First, many existing fusion methods simply concatenate features from each modality without considering the correlations among different modalities. Second, most existing methods often make prediction based on a single classifier, which might not be able to address the heterogeneity of the Alzheimer's disease (AD) progression. Third, many existing methods often employ feature selection (or reduction) and classifier training in two independent steps, without considering the fact that the two pipelined steps are highly related to each other. Forth, there are missing neuroimaging data for some of the participants (e.g., missing PET data), due to the participants' "no-show" or dropout. In this paper, to address the above issues, we propose an early AD diagnosis framework via novel multi-modality latent space inducing ensemble SVM classifier. Specifically, we first project the neuroimaging data from different modalities into a latent space, and then map the learned latent representations into the label space to learn multiple diversified classifiers. Finally, we obtain the more reliable classification results by using an ensemble strategy. More importantly, we present a Complete Multi-modality Latent Space (CMLS) learning model for complete multi-modality data and also an Incomplete Multi-modality Latent Space (IMLS) learning model for incomplete multi-modality data. Extensive experiments using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset have demonstrated that our proposed models outperform other state-of-the-art methods.

Deep Learning of Static and Dynamic Brain Functional Networks for Early MCI Detection

While convolutional neural network (CNN) has been demonstrating powerful ability to learn hierarchical spatial features from medical images, it is still difficult to apply it directly to resting-state functional MRI (rs-fMRI) and the derived brain functional networks (BFNs). We propose a novel CNN framework to simultaneously learn embedded features from BFNs for brain disease diagnosis. Since BFNs can be built by considering both static and dynamic functional connectivity (FC), we first decompose rs-fMRI into multiple static BFNs with modified independent component analysis. Then, the voxel-wise variability in dynamic FC is used to quantify BFN dynamics. A set of paired 3D images representing static/dynamic BFNs can be fed into 3D CNNs, from which we can hierarchically and simultaneously learn static/dynamic BFN features. As a result, the dynamic BFN features can complement static BFN features and, at the meantime, different BFNs can help each other toward a joint and better classification. We validate our method with a publicly accessible, large cohort of rs-fMRI dataset in early-stage mild cognitive impairment (eMCI) diagnosis, which is one of the most challenging problems to the clinicians. By comparing with a conventional method, our method shows significant diagnostic performance improvement by almost 10%. This result demonstrates the effectiveness of deep learning in preclinical Alzheimer's disease diagnosis, based on the complex and high-dimensional voxel-wise spatiotemporal patterns of the resting-state brain functional connectomics. The framework provides a new but intuitive way to fully exploit deeply embedded diagnostic features from rs-fMRI for a better-individualized diagnosis of various neurological diseases.

Radiological images and machine learning: Trends, perspectives, and prospects

The application of machine learning to radiological images is an increasingly active research area that is expected to grow in the next five to ten years. Recent advances in machine learning have the potential to recognize and classify complex patterns from different radiological imaging modalities such as x-rays, computed tomography, magnetic resonance imaging and positron emission tomography imaging. In many applications, machine learning based systems have shown comparable performance to human decision-making. The applications of machine learning are the key ingredients of future clinical decision making and monitoring systems. This review covers the fundamental concepts behind various machine learning techniques and their applications in several radiological imaging areas, such as medical image segmentation, brain function studies and neurological disease diagnosis, as well as computer-aided systems, image registration, and content-based image retrieval systems. Synchronistically, we will briefly discuss current challenges and future directions regarding the application of machine learning in radiological imaging. By giving insight on how take advantage of machine learning powered applications, we expect that clinicians can prevent and diagnose diseases more accurately and efficiently.

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

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

Alterations of brain local functional connectivity in amnestic mild cognitive impairment

Background

Resting-state functional magnetic resonance imaging studies using a regional homogeneity (ReHo) method have reported that amnestic mild cognitive impairment (aMCI) was associated with abnormalities in local functional connectivity. However, their results were not conclusive.

Methods

Seed-based d Mapping was used to conduct a coordinate-based meta-analysis to identify consistent ReHo alterations in aMCI.

Results

We identified 10 studies with 11 datasets suitable for inclusion, including 378 patients with aMCI and 435 healthy controls. This meta-analysis identified significant ReHo alterations in patients with aMCI relative to healthy controls, mainly within the default mode network (DMN) (bilateral posterior cingulate cortex [PCC], right angular gyrus, bilateral middle temporal gyri, and left parahippocampal gyrus/hippocampus), executive control network (right superior parietal lobule and dorsolateral prefrontal cortex), visual network (right lingual gyrus and left middle occipital gyrus), and sensorimotor network (right paracentral lobule/supplementary motor area, right postcentral gyrus and left posterior insula). Significant heterogeneity of ReHo alterations in the bilateral PCC, left parahippocampal gyrus/hippocampus, and right superior parietal lobule/angular gyrus was observed. Exploratory meta-regression analyses indicated that general cognitive function, gender distribution, age, and education level partially contributed to this heterogeneity.

Conclusions

This study provides provisional evidence that aMCI is associated with abnormal ReHo within the DMN, executive control network, visual network, and sensorimotor network. These local functional connectivity alterations suggest coexistence of functional deficits and compensation in these networks. These findings contribute to the modeling of brain functional connectomes and to a better understanding of the neural substrates of aMCI. Confounding factors merit much attention and warrant future investigations.

Electronic supplementary material

The online version of this article (10.1186/s40035-018-0134-8) contains supplementary material, which is available to authorized users.

A Brainnetome Atlas Based Mild Cognitive Impairment Identification Using Hurst Exponent

Mild cognitive impairment (MCI), which generally represents the transition state between normal aging and the early changes related to Alzheimer’s disease (AD), has drawn increasing attention from neuroscientists due that efficient AD treatments need early initiation ahead of irreversible brain tissue damage. Thus effective MCI identification methods are desperately needed, which may be of great importance for the clinical intervention of AD. In this article, the range scaled analysis, which could effectively detect the temporal complexity of a time series, was utilized to calculate the Hurst exponent (HE) of functional magnetic resonance imaging (fMRI) data at a voxel level from 64 MCI patients and 60 healthy controls (HCs). Then the average HE values of each region of interest (ROI) in brainnetome atlas were extracted and compared between MCI and HC. At last, the abnormal average HE values were adopted as the classification features for a proposed support vector machine (SVM) based identification algorithm, and the classification performance was estimated with leave-one-out cross-validation (LOOCV). Our results indicated 83.1% accuracy, 82.8% sensitivity and 83.3% specificity, and an area under curve of 0.88, suggesting that the HE index could serve as an effective feature for the MCI identification. Furthermore, the abnormal HE brain regions in MCI were predominately involved in left middle frontal gyrus, right hippocampus, bilateral parahippocampal gyrus, bilateral amygdala, left cingulate gyrus, left insular gyrus, left fusiform gyrus, left superior parietal gyrus, left orbital gyrus and left basal ganglia.

Resting-state functional connectivity of the dorsal frontal cortex predicts subcortical vascular cognition impairment

Functional magnetic resonance imaging (fMRI) studies have revealed group differences in the frontal area between the subcortical vascular cognition impairment (SVCI) patients and the controls. However, most of the existing research focused on average differences between the two groups, and therefore had limited clinical applicability. The aim of our study was to investigate whether inter-regions functional connectivity of the dorsal frontal cortex (DFC) can be used to discriminate the SVCI from the controls at the level of the individual. Thirty-two SVCI patients and 32 demographically similar healthy individuals underwent resting-state functional magnetic resonance imaging. The DFC, derived from a prior atlas, was divided into 10 clusters. Features based on DFC were obtained through functional connectivity analysis between pairs of DFC. A nonlinear kernel support vector machine was used for classification and validated using 8-fold cross validation. An excellent classification accuracy was obtained from both the left and the right DFC functional connectivity (accuracy=75.07%, sensitivity=81.57% and specificity=61.71%; accuracy=45.38%, sensitivity=60.74% and specificity=39.48%; P<0.001). These findings shed further light on the pathogenesis of SVCI and showed promising classification performance using machine learning analysis based on DFC fMRI data, which may be useful for the differentiation of SVCI.

Cerebral 18F-FDG PET in macrophagic myofasciitis: An individual SVM-based approach

INTRODUCTION

Macrophagic myofasciitis (MMF) is an emerging condition with highly specific myopathological alterations. A peculiar spatial pattern of a cerebral glucose hypometabolism involving occipito-temporal cortex and cerebellum have been reported in patients with MMF; however, the full pattern is not systematically present in routine interpretation of scans, and with varying degrees of severity depending on the cognitive profile of patients. Aim was to generate and evaluate a support vector machine (SVM) procedure to classify patients between healthy or MMF 18F-FDG brain profiles.

METHODS

18F-FDG PET brain images of 119 patients with MMF and 64 healthy subjects were retrospectively analyzed. The whole-population was divided into two groups; a training set (100 MMF, 44 healthy subjects) and a testing set (19 MMF, 20 healthy subjects). Dimensionality reduction was performed using a t-map from statistical parametric mapping (SPM) and a SVM with a linear kernel was trained on the training set. To evaluate the performance of the SVM classifier, values of sensitivity (Se), specificity (Sp), positive predictive value (PPV), negative predictive value (NPV) and accuracy (Acc) were calculated.

RESULTS

The SPM12 analysis on the training set exhibited the already reported hypometabolism pattern involving occipito-temporal and fronto-parietal cortices, limbic system and cerebellum. The SVM procedure, based on the t-test mask generated from the training set, correctly classified MMF patients of the testing set with following Se, Sp, PPV, NPV and Acc: 89%, 85%, 85%, 89%, and 87%.

CONCLUSION

We developed an original and individual approach including a SVM to classify patients between healthy or MMF metabolic brain profiles using 18F-FDG-PET. Machine learning algorithms are promising for computer-aided diagnosis but will need further validation in prospective cohorts.

Aberrant Intrinsic Activity and Connectivity in Cognitively Normal Parkinson's Disease

Disturbances in intrinsic activity during resting-state functional MRI (rsfMRI) are common in Parkinson's disease (PD), but have largely been studied in a priori defined subnetworks. The cognitive significance of abnormal intrinsic activity is also poorly understood, as are abnormalities that precede the onset of mild cognitive impairment. To address these limitations, we leveraged three different analytic approaches to identify disturbances in rsfMRI metrics in 31 cognitively normal PD patients (PD-CN) and 30 healthy adults. Subjects were screened for mild cognitive impairment using the Movement Disorders Society Task Force Level II criteria. Whole-brain data-driven analytic approaches first analyzed the amplitude of low-frequency intrinsic fluctuations (ALFF) and regional homogeneity (ReHo), a measure of local connectivity amongst functionally similar regions. We then examined if regional disturbances in these metrics altered functional connectivity with other brain regions. We also investigated if abnormal rsfMRI metrics in PD-CN were related to brain atrophy and executive, visual organization, and episodic memory functioning. The results revealed abnormally increased and decreased ALFF and ReHo in PD-CN patients within the default mode network (posterior cingulate, inferior parietal cortex, parahippocampus, entorhinal cortex), sensorimotor cortex (primary motor, pre/post-central gyrus), basal ganglia (putamen, caudate), and posterior cerebellar lobule VII, which mediates cognition. For default mode network regions, we also observed a compound profile of altered ALFF and ReHo. Most regional disturbances in ALFF and ReHo were associated with strengthened long-range interactions in PD-CN, notably with regions in different networks. Stronger long-range functional connectivity in PD-CN was also partly expanded to connections that were outside the networks of the control group. Abnormally increased activity and functional connectivity appeared to have a pathological, rather than compensatory influence on cognitive abilities tested in this study. Receiver operating curve analyses demonstrated excellent sensitivity (≥90%) of rsfMRI variables in distinguishing patients from controls, but poor accuracy for brain volume and cognitive variables. Altogether these results provide new insights into the topology, cognitive relevance, and sensitivity of aberrant intrinsic activity and connectivity that precedes clinically significant cognitive impairment. Longitudinal studies are needed to determine if these neurocognitive associations presage the development of future mild cognitive impairment or dementia.