Brain Networks Connectivity in Mild to Moderate Depression: Resting State fMRI Study with Implications to Nonpharmacological Treatment

Depression diagnosis: EEG-based cognitive biomarkers and machine learning

Depression is a complex mental illness that has significant effects on people as well as society. The traditional techniques for the diagnosis of depression, along with the potential of nascent biomarkers especially EEG-based biomarkers, are studied. This review explores the significance of cognitive biomarkers, offering a comprehensive understanding of their role in the overall assessment of depression. It also investigates the effects of depression on various brain regions, outlines promising areas for future research, and emphasizes the importance of understanding the neurophysiological roots of depression. Furthermore, it elucidates how machine learning and deep learning models are integrated into EEG-based depression diagnosis, emphasizing their importance in optimizing personalized therapeutic protocols and improving diagnostic accuracy with EEG data analysis.

Neural Modulation Alteration to Positive and Negative Emotions in Depressed Patients: Insights from fMRI Using Positive/Negative Emotion Atlas

BACKGROUND

Although it has been noticed that depressed patients show differences in processing emotions, the precise neural modulation mechanisms of positive and negative emotions remain elusive. FMRI is a cutting-edge medical imaging technology renowned for its high spatial resolution and dynamic temporal information, making it particularly suitable for the neural dynamics of depression research.

METHODS

To address this gap, our study firstly leveraged fMRI to delineate activated regions associated with positive and negative emotions in healthy individuals, resulting in the creation of the positive emotion atlas (PEA) and the negative emotion atlas (NEA). Subsequently, we examined neuroimaging changes in depression patients using these atlases and evaluated their diagnostic performance based on machine learning.

RESULTS

Our findings demonstrate that the classification accuracy of depressed patients based on PEA and NEA exceeded 0.70, a notable improvement compared to the whole-brain atlases. Furthermore, ALFF analysis unveiled significant differences between depressed patients and healthy controls in eight functional clusters during the NEA, focusing on the left cuneus, cingulate gyrus, and superior parietal lobule. In contrast, the PEA revealed more pronounced differences across fifteen clusters, involving the right fusiform gyrus, parahippocampal gyrus, and inferior parietal lobule.

CONCLUSIONS

These findings emphasize the complex interplay between emotion modulation and depression, showcasing significant alterations in both PEA and NEA among depression patients. This research enhances our understanding of emotion modulation in depression, with implications for diagnosis and treatment evaluation.

STANet: A Novel Spatio-Temporal Aggregation Network for Depression Classification with Small and Unbalanced FMRI Data

Background: Early diagnosis of depression is crucial for effective treatment and suicide prevention. Traditional methods rely on self-report questionnaires and clinical assessments, lacking objective biomarkers. Combining functional magnetic resonance imaging (fMRI) with artificial intelligence can enhance depression diagnosis using neuroimaging indicators, but depression-specific fMRI datasets are often small and imbalanced, posing challenges for classification models. New Method: We propose the Spatio-Temporal Aggregation Network (STANet) for diagnosing depression by integrating convolutional neural networks (CNN) and recurrent neural networks (RNN) to capture both temporal and spatial features of brain activity. STANet comprises the following steps: (1) Aggregate spatio-temporal information via independent component analysis (ICA). (2) Utilize multi-scale deep convolution to capture detailed features. (3) Balance data using the synthetic minority over-sampling technique (SMOTE) to generate new samples for minority classes. (4) Employ the attention-Fourier gate recurrent unit (AFGRU) classifier to capture long-term dependencies, with an adaptive weight assignment mechanism to enhance model generalization. Results: STANet achieves superior depression diagnostic performance, with 82.38% accuracy and a 90.72% AUC. The Spatio-Temporal Feature Aggregation module enhances classification by capturing deeper features at multiple scales. The AFGRU classifier, with adaptive weights and a stacked Gated Recurrent Unit (GRU), attains higher accuracy and AUC. SMOTE outperforms other oversampling methods. Additionally, spatio-temporal aggregated features achieve better performance compared to using only temporal or spatial features. Comparison with existing methods: STANet significantly outperforms traditional classifiers, deep learning classifiers, and functional connectivity-based classifiers. Conclusions: The successful performance of STANet contributes to enhancing the diagnosis and treatment assessment of depression in clinical settings on imbalanced and small fMRI.

Enhanced rich club connectivity in mild or moderate depression after nonpharmacological treatment: A preliminary study

INTRODUCTION

It has been suggested that the rich club organization in major depressive disorder (MDD) was altered. However, it remained unclear whether the rich club organization could be served as a biomarker that predicted the improvement of clinical symptoms in MDD.

METHODS

The current study included 29 mild or moderate patients with MDD, who were grouped into a treatment group (receiving cognitive behavioral therapy or real-time fMRI feedback treatment) and a no-treatment group. Resting-state MRI scans were obtained for all participants. Graph theory was employed to investigate the treatment-related changes in network properties and rich club organization.

RESULTS

We found that patients in the treatment group had decreased depressive symptom scores and enhanced rich club connectivity following the nonpharmacological treatment. Moreover, the changes in rich club connectivity were significantly correlated with the changes in depressive symptom scores. In addition, the nonpharmacological treatment on patients with MDD increased functional connectivity mainly among the salience network, default mode network, frontoparietal network, and subcortical network. Patients in the no-treatment group did not show significant changes in depressive symptom scores and rich club organization.

CONCLUSIONS

Those results suggested that the remission of depressive symptoms after nonpharmacological treatment in MDD patients was associated with the increased efficiency of global information processing.

The Ripple Effect: Unveiling the Bidirectional Relationship Between Negative Life Events and Depressive Symptoms in Medical Cadets

Background

Previous studies have explored the relationship between negative life events and depression, but little is known about the bidirectional relationship between negative life events and depression, particularly in specific groups of medical cadets.

Purpose

This study aimed to explore the relationship between negative life events and depressive symptoms among medical cadets during their four years of college.

Methods

An analysis of 4-wave longitudinal data collected from 2015-2018 was conducted using a cross-lagged panel network (CLPN) model to explore the complex causal relationship between negative life events and depressive symptoms in medical cadets (N=433).

Results

We found differences in negative life events and depressive symptoms among medical cadets across four network models over four years of university. Nodes A-21, A-20, A-23 and A-24, and depressive symptoms D-6 showed greater lagged effect values.

Conclusion

Our findings suggest that there is a lagged and mutually causal interaction between negative life events and depressive symptoms in medical cadets over 4 years of college, but that the predictability of negative life events is more important. However, more attention needs to be paid to the predictive role of depressive symptoms, especially those in early life which are often overlooked. Our study provides new insights into the relationship between negative life events and depressive symptoms in university students and helps to refine strategies for prevention and intervention of depression.

Random matrix theory tools for the predictive analysis of functional magnetic resonance imaging examinations

Purpose

Random matrix theory (RMT) is an increasingly useful tool for understanding large, complex systems. Prior studies have examined functional magnetic resonance imaging (fMRI) scans using tools from RMT, with some success. However, RMT computations are highly sensitive to a number of analytic choices, and the robustness of findings involving RMT remains in question. We systematically investigate the usefulness of RMT on a wide variety of fMRI datasets using a rigorous predictive framework.

Approach

We develop open-source software to efficiently compute RMT features from fMRI images and examine the cross-validated predictive potential of eigenvalue and RMT-based features ("eigenfeatures") with classic machine-learning classifiers. We systematically vary pre-processing extent, normalization procedures, RMT unfolding procedures, and feature selection and compare the impact of these analytic choices on the distributions of cross-validated prediction performance for each combination of dataset binary classification task, classifier, and feature. To deal with class imbalance, we use the area under the receiver operating characteristic curve (AUROC) as the main performance metric.

Results

Across all classification tasks and analytic choices, we find RMT- and eigenvalue-based "eigenfeatures" to have predictive utility more often than not (82.4% of median AUROCs > 0.5 ; median AUROC range across classification tasks 0.47 to 0.64). Simple baseline reductions on source timeseries, by contrast, were less useful (58.8% of median AUROCs > 0.5 , median AUROC range across classification tasks 0.42 to 0.62). Additionally, eigenfeature AUROC distributions were overall more right-tailed than baseline features, suggesting greater predictive potential. However, performance distributions were wide and often significantly affected by analytic choices.

Conclusions

Eigenfeatures clearly have potential for understanding fMRI functional connectivity in a wide variety of scenarios. The utility of these features is strongly dependent on analytic decisions, suggesting caution when interpreting past and future studies applying RMT to fMRI. However, our study demonstrates that the inclusion of RMT statistics in fMRI investigations could improve prediction performances across a wide variety of phenomena.

Objective biomarkers of depression: A study of Granger causality and wavelet coherence in resting-state fMRI

BACKGROUND AND PURPOSE

The lack of a robust diagnostic biomarker makes understanding depression from a neurobiological standpoint an important goal, especially in the context of brain imaging.

METHODS

In this study, we aim to create novel image-based features for objective diagnosis of depression. Resting-state network time series are used to investigate neurodynamics with the help of wavelet coherence and Granger causality (G-causality). Three new features are introduced: total wavelet coherence, wavelet lead coherence, and wavelet coherence blob analysis. The fourth feature, pair-wise conditional G-causality, is used to establish the causality between resting-state networks. We use the proposed features to classify depression in adult subjects.

RESULTS

We obtained an accuracy of 86% in the wavelet lead coherence, 80% in Granger causality, and 86% in wavelet coherence blob analysis. Subjects with depression showed hyperconnectivity between the dorsal attention network and the auditory network as well as between the posterior default mode network and the dorsal attention network. Hypoconnectivity was found between the anterior default mode network and the auditory network as well as the right frontoparietal network and the lateral visual network. An abnormal co-activation pattern was found between cerebellum and the lateral motor network according to the wavelet coherence blob analysis.

CONCLUSION

Based on abnormal functional dynamics between brain networks, we were able to identify subjects with depression with high accuracy. The findings of this study contribute to the understanding of the impaired emotional and attention processing associated with depression, as well as decreased motor activity.

The alterations of brain functional connectivity networks in major depressive disorder detected by machine learning through multisite rs-fMRI data

BACKGROUND

The current diagnosis of major depressive disorder (MDD) is mainly based on the patient's self-report and clinical symptoms. Machine learning methods are used to identify MDD using resting-state functional magnetic resonance imaging (rs-fMRI) data. However, due to large site differences in multisite rs-fMRI data and the difficulty of sample collection, most of the current machine learning studies use small sample sizes of rs-fMRI datasets to detect the alterations of functional connectivity (FC) or network attribute (NA), which may affect the reliability of the experimental results.

METHODS

Multisite rs-fMRI data were used to increase the size of the sample, and then we extracted the functional connectivity (FC) and network attribute (NA) features from 1611 rs-fMRI data (832 patients with MDD (MDDs) and 779 healthy controls (HCs)). ComBat algorithm was used to harmonize the data variances caused by the multisite effect, and multivariate linear regression was used to remove age and sex covariates. Two-sample t-test and wrapper-based feature selection methods (support vector machine recursive feature elimination with cross-validation (SVM-RFECV) and LightGBM's "feature_importances_" function) were used to select important features. The Shapley additive explanations (SHAP) method was used to assign the contribution of features to the best classification effect model.

RESULTS

The best result was obtained from the LinearSVM model trained with the 136 important features selected by SVMRFE-CV. In the nested five-fold cross-validation (consisting of an outer and an inner loop of five-fold cross-validation) of 1611 data, the model achieved the accuracy, sensitivity, and specificity of 68.90 %, 71.75 %, and 65.84 %, respectively. The 136 important features were tested in a small dataset and obtained excellent classification results after balancing the ratio between patients with depression and HCs.

CONCLUSIONS

The combined use of FC and NA features is effective for classifying MDDs and HCs. The important FC and NA features extracted from the large sample dataset have some generalization performance and may be used as a reference for the altered brain functional connectivity networks in MDD.

Sustained attention alterations in major depressive disorder: A review of fMRI studies employing Go/No-Go and CPT tasks

BACKGROUND

Major depressive disorder (MDD) is a severe psychiatric condition characterized by selective cognitive dysfunctions. In this regard, functional Magnetic Resonance Imaging (fMRI) studies showed, both at resting state and during tasks, alterations in the brain functional networks involved in cognitive processes in MDD patients compared to controls. Among those, it seems that the attention network may have a role in the disease pathophysiology. Therefore, in this review we aim at summarizing the current fMRI evidence investigating sustained attention in MDD patients.

METHODS

We conducted a search on PubMed on case-control studies on MDD employing fMRI acquisitions during Go/No-Go and continuous performance tasks. A total of 12 studies have been included in the review.

RESULTS

Overall, the majority of fMRI studies reported quantitative alterations in the response to attentive tasks in selective brain regions, including the prefrontal cortex, the cingulate cortex, the temporal and parietal lobes, the insula and the precuneus, which are key nodes of the attention, the executive, and the default mode networks.

LIMITATIONS

The heterogeneity in the study designs, fMRI acquisition techniques and processing methods have limited the generalizability of the results.

CONCLUSIONS

The results from the included studies showed the presence of alterations in the activation patterns of regions involved in sustained attention in MDD, which are in line with current evidence and seemed to explain some of the key symptoms of depression. However, given the paucity and heterogeneity of studies available, it may be worthwhile to continue investigating the attentional domain in MDD with ad-hoc study designs to retrieve more robust evidence.

Alteration of whole-brain amplitude of low-frequency fluctuation and degree centrality in patients with mild to moderate depression: A resting-state functional magnetic resonance imaging study

BACKGROUND

Mild to moderate depressive disorder has a high risk of progressing to major depressive disorder.

METHODS

Low-frequency amplitude and degree centrality were calculated to compare 49 patients with mild to moderate depression and 21 matched healthy controls. Correlation analysis was conducted to explore the correlation between the amplitude of low-frequency fluctuation (ALFF) and the degree centrality (DC) of altered brain region and the scores of clinical scale. Receiver operating characteristic (ROC) curves were further analyzed to evaluate the predictive value of above altered ALFF and DC areas as image markers for mild to moderate depression.

RESULTS

Compared with healthy controls, patients with mild to moderate depression had lower ALFF values in the left precuneus and posterior cingulate gyrus [voxel p < 0.005, cluster p < 0.05, Gaussian random field correction (GRF) corrected] and lower DC values in the left insula (voxel p < 0.005, cluster p < 0.05, GRF corrected). There was a significant negative correlation between DC in the left insula and scale scores of Zung's Depression Scale (ZungSDS), Beck Self-Rating Depression Scale (BDI), Toronto Alexithymia Scale (TAS26), and Ruminative Thinking Response Scale (RRS_SUM, RRS_REFLECTION, RRS_DEPR). Finally, ROC analysis showed that the ALFF of the left precuneus and posterior cingulate gyrus had a sensitivity of 61.9% and a specificity of 79.6%, and the DC of the left insula had a sensitivity of 81% and a specificity of 85.7% in differentiating mild to moderate depression from healthy controls.

CONCLUSION

Intrinsic abnormality of the brain was mainly located in the precuneus and insular in patients with mild to moderate depression, which provides insight into potential neurological mechanisms.

Altered effective connectivity in sensorimotor cortices is a signature of severity and clinical course in depression

Research into neurobiology of depression primarily focuses on its complex psychological aspects. Here we propose an alternative approach and target sensorimotor alterations—a prominent but often neglected feature of depression. We demonstrated using resting-state functional MRI data and computational modeling that top-down and bottom-up information flow in sensory and motor cortices is altered with increasing depression severity in a way that is consistent with depression symptoms. Depression-associated changes were found to be consistent across sessions, amenable to treatment and of effect size sufficiently large to predict whether somebody has mild or severe depression. These results pave the way for an avenue of research into the neural underpinnings of mental health conditions.

Functional neuroimaging research on depression has traditionally targeted neural networks associated with the psychological aspects of depression. In this study, instead, we focus on alterations of sensorimotor function in depression. We used resting-state functional MRI data and dynamic causal modeling (DCM) to assess the hypothesis that depression is associated with aberrant effective connectivity within and between key regions in the sensorimotor hierarchy. Using hierarchical modeling of between-subject effects in DCM with parametric empirical Bayes we first established the architecture of effective connectivity in sensorimotor cortices. We found that in (interoceptive and exteroceptive) sensory cortices across participants, the backward connections are predominantly inhibitory, whereas the forward connections are mainly excitatory in nature. In motor cortices these parities were reversed. With increasing depression severity, these patterns are depreciated in exteroceptive and motor cortices and augmented in the interoceptive cortex, an observation that speaks to depressive symptomatology. We established the robustness of these results in a leave-one-out cross-validation analysis and by reproducing the main results in a follow-up dataset. Interestingly, with (nonpharmacological) treatment, depression-associated changes in backward and forward effective connectivity partially reverted to group mean levels. Overall, altered effective connectivity in sensorimotor cortices emerges as a promising and quantifiable candidate marker of depression severity and treatment response.

Factors associated with recurrent transient global amnesia: systematic review and pathophysiological insights

The examination of the risk factors that affect the recurrence of transient global amnesia (TGA) may shed light on the pathophysiological substrate of the disease. A systematic review was performed to identify the factors associated with the recurrence of TGA. MEDLINE, EMBASE, CENTRAL and PsycINFO were meticulously searched. Observational controlled studies involving patients with single (s-TGA) and recurrent TGA (r-TGA) according to Hodges and Warlow's criteria were retrieved. Differences in the demographic characteristics, personal and family medical history, previous exposure to precipitating events and laboratory findings were examined. Retrieved evidence was assessed in the context of the individual article validity, based on the numerical power and methodological quality of each study. Nine cohort studies with retrospective, prospective or mixed design were retrieved. In total, 1989 patients with TGA were included, 269 of whom suffered from r-TGA (13.5%). R-TGA presented an earlier age of onset. Evidence was suggestive of a relationship between recurrence and a family or personal history of migraine, as well as a personal history of depression. There was weaker evidence that associated recurrence with a positive family history of dementia, a personal history of head injury and hippocampal lesions in diffusion-weighted MRI. On the other hand, no connection was found between recurrence and electroencephalographic abnormalities, impaired jugular venous drainage, cardiovascular risk factors, atrial fibrillation, previous cerebrovascular events, exposure to precipitating events, a positive family history of TGA and hypothyroidism. Important pathophysiological insights that arised from these findings were discussed.