scholarly journals Evaluating the diagnostic utility of applying a machine learning algorithm to diffusion tensor MRI measures in individuals with major depressive disorder

2016 ◽  
Author(s):  
David M Schnyer ◽  
Peter C. Clasen ◽  
Christopher Gonzalez ◽  
Christopher G Beevers
Keyword(s):  
Major Depressive Disorder ◽  
White Matter ◽  
Depressive Disorder ◽  
Right Hemisphere ◽  
Diffusion Tensor ◽  
Support Vector ◽  
Healthy Controls ◽  
Major Depressive ◽  
Predictive Information ◽  
Brain White Matter

AbstractUsing MRI to diagnose mental disorders has been a long-term goal. Despite this, the vast majority of prior neuroimaging work has been descriptive rather than predictive. The current study applies support vector machine (SVM) learning to MRI measures of brain white matter to classify adults with Major Depressive Disorder (MDD) and healthy controls. In a precisely matched group of individuals with MDD (n = 25) and healthy controls (n = 25), SVM learning accurately (70%) classified patients and controls across a brain map of white matter fractional anisotropy values (FA). The study revealed three main findings: 1) SVM applied to DTI derived FA maps can accurately classify MDD vs. healthy controls; 2) prediction is strongest when only right hemisphere white matter is examined; and 3) removing FA values from a region identified by univariate contrast as significantly different between MDD and healthy controls does not change the SVM accuracy. These results indicate that SVM learning applied to neuroimaging data can classify the presence versus absence of MDD and that predictive information is distributed across brain networks rather than being highly localized. Finally, MDD group differences revealed through typical univariate contrasts do not necessarily reveal patterns that provide accurate predictive information.

scholarly journals Brain white-matter hyperintensities and treatment outcome in major depressive disorder

2006 ◽  
Vol 188 (2) ◽  
pp. 180-185 ◽  
Author(s):  
Dan V. Iosifescu ◽  
Perry F. Renshaw ◽  
In Kyoon Lyoo ◽  
Ho Kyu Lee ◽  
Roy H. Perlis ◽  
...  
Keyword(s):  
Risk Factors ◽  
Major Depressive Disorder ◽  
Treatment Outcome ◽  
Cardiovascular Risk ◽  
White Matter ◽  
Depressive Disorder ◽  
Cardiovascular Risk Factors ◽  
White Matter Hyperintensities ◽  
Major Depressive ◽  
Brain White Matter

BackgroundAn increased incidence of brain white-matter hyperintensities has been described in major depressive disorder, but the impact of such hyperintensities on treatment outcome is still controversial.AimsTo investigate the relationship of brain white-matter hyperintensities with cardiovascular risk factors and with treatment outcome in younger people with major depressive disorder.MethodWe assessed brain white-matter hyperintensities and cardiovascular risk factors in 84 people with major depressive disorder prior to initiating antidepressanttreatment. We also assessed hyperintensities in 35 matched controls.ResultsWe found no significant difference in the prevalence of white-matter hyperintensities between the depression and the control groups. Left-hemisphere subcortical hyperintensities correlated with lower rates of treatment response. We found no correlation between global hyperintensity measures and clinical outcome. Brain white-matter hyperintensities correlated with hypertension and age and with total cardiovascular risk score.ConclusionsSubcortical white-matter hyperintensities in the left hemisphere (but not in other brain areas) may be associated with poor response to antidepressant treatment in major depression.

scholarly journals Abnormal Default-Mode Network Homogeneity in Melancholic and Nonmelancholic Major Depressive Disorder at Rest

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Meiqi Yan ◽  
Xilong Cui ◽  
Feng Liu ◽  
Huabing Li ◽  
Renzhi Huang ◽  
...  
Keyword(s):  
Major Depressive Disorder ◽  
Depressive Disorder ◽  
Middle Temporal Gyrus ◽  
Support Vector ◽  
Healthy Controls ◽  
Major Depressive ◽  
Middle Temporal ◽  
Inferior Temporal Gyrus ◽  
Medial Frontal Gyrus ◽  
The Right

Background. Melancholic depression has been assumed as a severe type of major depressive disorder (MDD). We aimed to explore if there were some distinctive alterations in melancholic MDD and whether the alterations could be used to discriminate the melancholic MDD and nonmelancholic MDD. Methods. Thirty-one outpatients with melancholic MDD, thirty-three outpatients with nonmelancholic MDD, and thirty-two age- and gender-matched healthy controls were recruited. All participants were scanned by resting-state functional magnetic resonance imaging (fMRI). Imaging data were analyzed with the network homogeneity (NH) and support vector machine (SVM) methods. Results. Both patient groups exhibited increased NH in the right PCC/precuneus and right angular gyrus and decreased NH in the right middle temporal gyrus compared with healthy controls. Compared with nonmelancholic patients and healthy controls, melancholic patients exhibited significantly increased NH in the bilateral superior medial frontal gyrus and decreased NH in the left inferior temporal gyrus. But merely for melancholic patients, the NH of the right middle temporal gyrus was negatively correlated with TEPS total and contextual anticipatory scores. SVM analysis showed that a combination of NH values in the left superior medial frontal gyrus and left inferior temporal gyrus could distinguish melancholic patients from nonmelancholic patients with accuracy, sensitivity, and specificity of 79.66% (47/59), 70.97% (22/31), and 89.29%(25/28), respectively. Conclusion. Our findings showed distinctive network homogeneity alterations in melancholic MDD which may be potential imaging markers to distinguish melancholic MDD and nonmelancholic MDD.

scholarly journals Replicable association between human cytomegalovirus infection and reduced white matter fractional anisotropy in major depressive disorder

2021 ◽  
Author(s):  
Haixia Zheng ◽  
◽  
Maurizio Bergamino ◽  
Bart N. Ford ◽  
Rayus Kuplicki ◽  
...  
Keyword(s):  
Major Depressive Disorder ◽  
White Matter ◽  
Depressive Disorder ◽  
Fractional Anisotropy ◽  
Human Cytomegalovirus ◽  
Hcmv Infection ◽  
Diffusion Tensor ◽  
Major Depressive ◽  
Replication Sample ◽  
Discovery Sample

AbstractMajor depressive disorder (MDD) is associated with reductions in white matter microstructural integrity as measured by fractional anisotropy (FA), an index derived from diffusion tensor imaging (DTI). The neurotropic herpesvirus, human cytomegalovirus (HCMV), is a major cause of white matter pathology in immunosuppressed populations but its relationship with FA has never been tested in MDD despite the presence of inflammation and weakened antiviral immunity in a subset of depressed patients. We tested the relationship between FA and HCMV infection in two independent samples consisting of 176 individuals with MDD and 44 healthy controls (HC) (Discovery sample) and 88 participants with MDD and 48 HCs (Replication sample). Equal numbers of HCMV positive (HCMV+) and HCMV negative (HCMV−) groups within each sample were balanced on ten different clinical/demographic variables using propensity score matching. Anti-HCMV IgG antibodies were measured using a solid-phase ELISA. In the Discovery sample, significantly lower FA was observed in the right inferior fronto-occipital fasciculus (IFOF) in HCMV+ participants with MDD compared to HCMV− participants with MDD (cluster size 1316 mm3; pFWE < 0.05, d = −0.58). This association was confirmed in the replication sample by extracting the mean FA from this exact cluster and applying the identical statistical model (p < 0.05, d = −0.45). There was no significant effect of diagnosis or interaction between diagnosis and HCMV in either sample. The effect of chronic HCMV infection on white matter integrity may—in at-risk individuals—contribute to the psychopathology of depression. These findings may provide a novel target of intervention for a subgroup of patients with MDD.

scholarly journals Injuries in Left Corticospinal Tracts, Forceps Major, and Left Superior Longitudinal Fasciculus (Temporal) as the Quality Indicators for Major Depressive Disorder

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Ziwei Liu ◽  
Lijun Kang ◽  
Aixia Zhang ◽  
Chunxia Yang ◽  
Min Liu ◽  
...  
Keyword(s):  
Major Depressive Disorder ◽  
White Matter ◽  
Depressive Disorder ◽  
Quality Indicators ◽  
Diffusion Tensor ◽  
Superior Longitudinal Fasciculus ◽  
Major Depressive ◽  
First Degree Relatives ◽  
Corticospinal Tracts ◽  
Anterior Thalamic Radiation

At present, the etiology and pathogenesis of major depressive disorder (MDD) are still not clear. Studies have found that the risk of first-degree relatives of MDD is 2–3 times that of the general population. Diffusion tensor imaging (DTI) has been previously used to explore the pathogenesis of MDD. The purpose of this study is to explore the etiology of MDD by DTI and further to explore the correlation between its clinical characteristics and the structural changes of white matter in the brain. The study included 27 first-episode, drug-naive patients with MDD, 16 first-degree relatives without MDD, and 28 healthy control subjects with no family history of MDD (HC). Results showed that the fractional anisotropy (FA) differences among the three groups were mainly in the left anterior thalamic radiation (LATR), right anterior thalamic radiation (RATR), left corticospinal tracts (LCST), forceps major (FMa), right inferior longitudinal fasciculus (RILF), and left superior longitudinal fasciculus (temporal) (LSLF(T)). Among the 6 sites, LCST, FMa, and LSLF(T) showed significant differences between MDD and First-degree relatives compared to HC. MDD patients had significant emotional symptoms, somatic symptoms, and cognitive impairment. FMa FA was significantly positively correlated with delayed memory score ( r = 0.43 , P = 0.031 ), and RILF FA was significantly negatively correlated with the FSS score ( r = − 0.42 , P = 0.028 ). These results revealed that the white matter characteristics of MDD-susceptible patients were LCST, FMa, and LSLF(T) lesions, all of which may be quality indicators of MDD.

scholarly journals Alterations of core structural network connectome associated with suicidal ideation in major depressive disorder patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xinyi Liu ◽  
Cancan He ◽  
Dandan Fan ◽  
Feifei Zang ◽  
Yao Zhu ◽  
...  
Keyword(s):  
Major Depressive Disorder ◽  
Depressive Disorder ◽  
Suicide Ideation ◽  
Neural Circuit ◽  
Diffusion Tensor ◽  
Support Vector ◽  
Major Depressive ◽  
Rich Club ◽  
Structural Network ◽  
The Rich

AbstractSuicide ideation (SI) is a most high-risk clinical sign for major depressive disorder (MDD). However, whether the rich-club network organization as a core structural network is associated with SI and how the related neural circuits are distributed in MDD patients remain unknown. Total 177 participants including 69 MDD patients with SI (MDDSI), 58 MDD without SI (MDDNSI) and 50 cognitively normal (CN) subjects were recruited and completed neuropsychological tests and diffusion-tensor imaging scan. The rich-club organization was identified and the global and regional topological properties of structural networks, together with the brain connectivity of specific neural circuit architectures, were analyzed. Further, the support vector machine (SVM) learning was applied in classifying MDDSI or MDDNSI from CN subjects. MDDSI and MDDNSI patients both exhibited disrupted rich-club organizations. However, MDDSI patients showed that the differential network was concentrated on the non-core low-level network and significantly destroyed betweeness centrality was primarily located in the regional non-hub regions relative to MDDNSI patients. The differential structural network connections involved the superior longitudinal fasciculus and the corpus callosum were incorporated in the cognitive control circuit and default mode network. Finally, the feeder serves as a potentially powerful indicator for distinguishing MDDSI patients from MDDNSI or CN subjects. The altered rich-club organization provides new clues to understand the underlying pathogenesis of MDD patients, and the feeder was useful as a diagnostic neuroimaging biomarker for differentiating MDD patients with or without SI.

Sign in / Sign up

Export Citation Format

Share Document