Regional amplitude abnormities in the major depressive disorder: A resting-state fMRI study and support vector machine analysis

Chen, Qing; Bi, Yanmeng; Zhao, Xiaohua; Lai, Yuqi; Yan, Weixin; Xie, Lingpeng; Gao, Tingting; Xie, Shuwen; Zeng, Ting; Li, Jun; Kuang, Shanshan; Gao, Lei; Lv, Zhi-Ping

doi:10.1016/j.jad.2022.03.079

Cited by 20 publications

(15 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM combined with neuroimaging technology has been widely used in the study of various diseases. For example, Chen et al found that combining the average ALFF and fall values of the right caudate nucleus and corpus callosum can diagnose MDD [accuracy (79.79%), sensitivity (65.12%), and specificity (92.16%)] ( 52 ). Gao et al found that the combination of increased fALFF in the right precuneus and left superior frontal gyrus (SFG) with a diagnostic accuracy of 76.39% ( 18 ).…”

Section: Discussionmentioning

confidence: 99%

Abnormal degree centrality values as a potential imaging biomarker for major depressive disorder: A resting-state functional magnetic resonance imaging study and support vector machine analysis

et al. 2022

View full text Add to dashboard Cite

ObjectivePrevious studies have revealed abnormal degree centrality (DC) in the structural and functional networks in the brains of patients with major depressive disorder (MDD). There are no existing reports on the DC analysis method combined with the support vector machine (SVM) to distinguish patients with MDD from healthy controls (HCs). Here, the researchers elucidated the variations in DC values in brain regions of MDD patients and provided imaging bases for clinical diagnosis.MethodsPatients with MDD (N = 198) and HCs (n = 234) were scanned using resting-state functional magnetic resonance imaging (rs-fMRI). DC and SVM were applied to analyze imaging data.ResultsCompared with HCs, MDD patients displayed elevated DC values in the vermis, left anterior cerebellar lobe, hippocampus, and caudate, and depreciated DC values in the left posterior cerebellar lobe, left insula, and right caudate. As per the results of the SVM analysis, DC values in the left anterior cerebellar lobe and right caudate could distinguish MDD from HCs with accuracy, sensitivity, and specificity of 87.71% (353/432), 84.85% (168/198), and 79.06% (185/234), respectively. Our analysis did not reveal any significant correlation among the DC value and the disease duration or symptom severity in patients with MDD.ConclusionOur study demonstrated abnormal DC patterns in patients with MDD. Aberrant DC values in the left anterior cerebellar lobe and right caudate could be presented as potential imaging biomarkers for the diagnosis of MDD.

show abstract

Section: Discussionmentioning

confidence: 99%

Abnormal degree centrality values as a potential imaging biomarker for major depressive disorder: A resting-state functional magnetic resonance imaging study and support vector machine analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“… 46 During loss vs. reward stimuli, higher coupling was also found between the striatum and posterior default mode network (DMN), which could also predict the severity of depressive symptoms in MDD patients. 47 As in our study, MDD patients have shown striatum hyperactivity in many rs-fMRI studies, 18 , 48 , 49 and a combination of mean ALFF and fractional ALFF in the right striatum was selected as a feature of SVM to discriminate MDD patients and HC. Above all, the hypofunctions in the frontal-parietal cortex and hyperactivities in limbic structures found by our study are indicative of cortical-striatal dysregulation in MDD patients.…”

Section: Discussionmentioning

confidence: 97%

Mapping the modulating effect of transcutaneous auricular vagus nerve stimulation on voxel-based analyses in patients with first-episode major depressive disorder: a resting-state functional magnetic resonance imaging study

He¹,

Li²,

Wang³

et al. 2023

Brazilian Journal of Psychiatry

View full text Add to dashboard Cite

Introduction: Seed-based analysis has shown that transcutaneous auricular vagus nerve stimulation (taVNS) can modulate the dysfunctional brain network in patients with major depressive disorder (MDD). However, the voxel-based neuropsychological mechanism of taVNS on patients with first-episode MDD is poorly understood. The objective of this study was to assess the effects of an 8-week course of taVNS on patients with first-episode MDD. Methods: Twenty-two patients with first-episode MDD accepted an 8-week course of taVNS treatment. Resting-state functional magnetic resonance imaging (rs-fMRI) scans were performed before and after treatment. Voxel-based analyses were performed to characterize spontaneous brain activity. Healthy controls (n=23) were recruited to minimize test-retest effects. Analysis of covariance (ANCOVA) was performed to ascertain treatment-related changes. Then, correlations between changes in brain activity and the Hamilton Depression Rating Scale (HAM-D)/Hamilton Anxiety Scale (HAM-A) remission rate were estimated. Results: Significant group-by-time interactions on voxel-based analyses were observed in the inferior ventral striatum (VSi) and precuneus. Post-hoc analyses showed that taVNS inhibited higher brain activity in the VSi, while upregulating it in the precuneus. Functional connectivity (FC) between the VSi and precuneus decreased. Positive correlations were found between the HAM-D remission rate and changes in brain activity in the VSi. Conclusion: taVNS reduced the FC between VSi and precuneus by normalizing the abnormal spontaneous brain activity of VSi in first-episode MDD patients.

show abstract

“…The current study greatly improved the performance to classify MDD and HCs compared with previous studies. 16,17,[28][29][30][31] A recent study based on traditional static brain networks identified MDD from HCs using whole brain function connectivity as features and obtained an accuracy of 0.59. 30 The improvement in classification performance of our study indicated that incorporating the dynamics of brain network implied rich information.…”

Section: Discussionmentioning

confidence: 99%

Classification of Major Depressive Disorder Based on Integrated Temporal and Spatial Functional MRI Variability Features of Dynamic Brain Network

Gai

Chu

Che

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Characterization of the dynamics of functional brain network has gained increased attention in the study of depression. However, most studies have focused on single temporal dimension, while ignoring spatial dimensional information, hampering the discovery of validated biomarkers for depression. Purpose To integrate temporal and spatial functional MRI variability features of dynamic brain network in machine‐learning techniques to distinguish patients with major depressive disorder (MDD) from healthy controls (HCs). Study Type Prospective. Population A discovery cohort including 119 patients and 106 HCs and an external validation cohort including 126 patients and 124 HCs from Rest‐meta‐MDD consortium. Field Strength/Sequence A 3.0 T/resting‐state functional MRI using the gradient echo sequence. Assessment A random forest (RF) model integrating temporal and spatial variability features of dynamic brain networks with separate feature selection method (MSFS) was implemented for MDD classification. Its performance was compared with three RF models that used: temporal variability features (MTVF), spatial variability features (MSVF), and integrated temporal and spatial variability features with hybrid feature selection method (MHFS). A linear regression model based on MSFS was further established to assess MDD symptom severity, with prediction performance evaluated by the correlations between true and predicted scores. Statistical Tests Receiver operating characteristic analyses with the area under the curve (AUC) were used to evaluate models' performance. Pearson's correlation was used to assess relationship of predicted scores and true scores. P < 0.05 was considered statistically significant. Results The model with MSFS achieved the best performance, with AUCs of 0.946 and 0.834 in the discovery and validation cohort, respectively. Additionally, altered temporal and spatial variability could significantly predict the severity of depression (r = 0.640) and anxiety (r = 0.616) in MDD. Data Conclusion Integration of temporal and spatial variability features provides potential assistance for clinical diagnosis and symptom prediction of MDD. Evidence Level 2. Technical Efficacy Stage 2.

show abstract

Regional amplitude abnormities in the major depressive disorder: A resting-state fMRI study and support vector machine analysis

Cited by 20 publications

References 48 publications

Abnormal degree centrality values as a potential imaging biomarker for major depressive disorder: A resting-state functional magnetic resonance imaging study and support vector machine analysis

Abnormal degree centrality values as a potential imaging biomarker for major depressive disorder: A resting-state functional magnetic resonance imaging study and support vector machine analysis

Mapping the modulating effect of transcutaneous auricular vagus nerve stimulation on voxel-based analyses in patients with first-episode major depressive disorder: a resting-state functional magnetic resonance imaging study

Classification of Major Depressive Disorder Based on Integrated Temporal and Spatial Functional MRI Variability Features of Dynamic Brain Network

Contact Info

Product

Resources

About