The amygdala volume moderates the relationship between childhood maltreatment and callous-unemotional traits in adolescents with conduct disorder.

CU traits, characterized by shallow affect, lack of fear, and absence of remorse, have been moderately associated with childhood maltreatment in a recent meta-analysis. However, the potential impact of brain structures remains undetermined. This paper examines the relationship between callous-unemotional (CU) traits, childhood maltreatment, and amygdala volumes. In this study, we used a region-of-interest (ROI) analysis to explore the interaction between the volumes of the amygdala, childhood maltreatment, and the manifestation of CU traits in adolescents diagnosed with conduct disorder (CD, N = 67), along with a comparison group of healthy-control youths (HCs, N = 89). The ROI analysis revealed no significant group differences in the bilateral amygdalar volumes. Significant positive correlation was discovered between all forms of child maltreatment (except for physical neglect) and CU traits across subjects. But the interaction of physical abuse and amygdala volumes was only significant within CD patients. Notably, a sensitivity analysis suggested that gender significantly influences these findings. These results contribute critical insights into the etiology of CU traits, emphasizing the need for customized clinical assessment tools and intervention strategies.

Does the Relationship between Age and Brain Structure Differ in Youth with Conduct Disorder?

Conduct disorder (CD) is characterised by persistent antisocial and aggressive behaviour and typically emerges in childhood or adolescence. Although several authors have proposed that CD is a neurodevelopmental disorder, very little evidence is available about brain development in this condition. Structural brain alterations have been observed in CD, and some indirect evidence for delayed brain maturation has been reported. However, no detailed analysis of age-related changes in brain structure in youth with CD has been conducted. Using cross-sectional MRI data, this study aimed to explore differences in brain maturation in youth with CD versus healthy controls to provide further understanding of the neurodevelopmental processes underlying CD. 291 CD cases (153 males) and 379 healthy controls (160 males) aged 9-18 years (Mage = 14.4) were selected from the European multisite FemNAT-CD study. Structural MRI scans were analysed using surface-based morphometry followed by application of the ENIGMA quality control protocols. An atlas-based approach was used to investigate group differences and test for group-by-age and group-by-age-by-sex interactions in cortical thickness, surface area and subcortical volumes. Relative to healthy controls, the CD group showed lower surface area across frontal, temporal and parietal regions as well as lower total surface area. No significant group-by-age or group-by-age-by-sex interactions were observed on any brain structure measure. These findings suggest that CD is associated with lower surface area across multiple cortical regions, but do not support the idea that CD is associated with delayed brain maturation, at least within the age bracket considered here.

Structural abnormalities in adolescents with conduct disorder and high versus low callous unemotional traits.

There may be distinct conduct disorder (CD) etiologies and neural morphologies in adolescents with high callous unemotional (CU) traits versus low CU traits. Here, we employed surface-based morphometry methods to investigate morphological differences in adolescents diagnosed with CD [42 with high CU traits (CD-HCU) and 40 with low CU traits (CD-LCU)] and healthy controls (HCs, N = 115) in China. Whole-brain analyses revealed significantly increased cortical surface area (SA) in the left inferior temporal cortex and the right precuneus, but decreased SA in the left superior temporal cortex in the CD-LCU group, compared with the HC group. There were no significant cortical SA differences between the CD-HCU and the HC groups. Compared to the CD-HCU group, the CD-LCU group had a greater cortical thickness (CT) in the left rostral middle frontal cortex. Region-of-interest analyses revealed significant group differences in the right hippocampus, with CD-HCU group having lower right hippocampal volumes than HCs. We did not detect significant group differences in the amygdalar volume, however, the right amygdalar volume was found to be a significant moderator of the correlation between CU traits and the proactive aggression in CD patients. The present results suggested that the manifestations of CD differ between those with high CU traits versus low CU traits, and underscore the importance of sample characteristics in understanding the neural substrates of CD.

Brain Anatomy in Boys with Conduct Disorder: Differences Among Aggression Subtypes.

Aggression is a core feature of conduct disorder (CD), but the motivation, execution of aggression may vary. A deeper understanding of the neural substrates of aggressive behaviours is critical for effective clinical intervention. Seventy-six Boys with CD (50 with impulsive aggression (I-CD) and 26 with premeditated aggression (P-CD)) and 69 healthy controls (HCs) underwent a structural MRI scan and behavioural assessments. Whole-brain analyses revealed that, compared to HCs, the I-CD group showed significant cortical thinning in the right frontal cortex, while the P-CD group demonstrated significant folding deficits in the bilateral superior parietal cortex. Both types of aggression negatively correlated with the left amygdala volume, albeit in different ways. The present results demonstrated that the complex nature of aggression relies on differentiated anatomical substrates, highlighting the importance of exploring differential circuit-targeted interventions for CD patients.

Neuroanatomical changes associated with conduct disorder in boys: influence of childhood maltreatment.

Childhood maltreatment (CM) poses a serious risk to the physical, emotional and psychological well-being of children, and can advance the development of maladaptive behaviors, including conduct disorder (CD). CD involves repetitive, persistent violations of others' basic rights and societal norms. Little is known about whether and how CM influences the neural mechanisms underlying CD, and CD-characteristic neuroanatomical changes have not yet been defined in a structural magnetic resonance imaging (sMRI) study. Here, we used voxel-based morphometry (VBM) and surface-based morphometry (SBM) to investigate the influence of the CD diagnosis and CM on the brain in 96 boys diagnosed with CD (62 with CM) and 86 typically developing (TD) boys (46 with CM). The participants were 12-17 years of age. Compared to the CM- CD group, the CM+ CD group had structural gray matter (GM) alterations in the fronto-limbic regions, including the left amygdala, right posterior cingulate cortex (PCC), right putamen, right dorsolateral prefrontal cortex (dlPFC) and right anterior cingulate cortex (ACC). We also found boys with CD exhibited increased GM volume in bilateral dorsomedial prefrontal cortex (dmPFC), as well as decreased GM volume and decreased gyrification in the left superior temporal gyrus (STG) relative to TD boys. Regional GM volume correlated with aggression and conduct problem severity in the CD group, suggesting that the GM changes may contribute to increased aggression and conduct problems in boys with CD who have suffered CM. In conclusion, these results demonstrate previously unreported CM-associated distinct brain structural changes among CD-diagnosed boys.

Potential structural trait markers of depression in the form of alterations in the structures of subcortical nuclei and structural covariance network properties.

It has been proposed recently that major depressive disorder (MDD) could represent an adaptation to conserve energy after the perceived loss of an investment in a vital source, such as group identity, personal assets, or relationships. Energy conserving behaviors associated with MDD may form a persistent marker in brain regions and networks involved in cognition and emotion regulation. In this study, we examined whether subcortical regions and volume-based structural covariance networks (SCNs) have state-independent alterations (trait markers). First-episode drug-naïve currently depressed (cMDD) patients (N = 131), remitted MDD (RD) patients (N = 67), and healthy controls (HCs, N = 235) underwent structural magnetic resonance imaging (MRI). Subcortical gray matter volumes (GMVs) were calculated in FreeSurfer software, and group differences in GMVs and SCN were analyzed. Compared to HCs, major findings were decreased GMVs of left pallidum and pulvinar anterior of thalamus in the cMDD and RD groups, indicative of a trait marker. Relative to HCs, subcortical SCNs of both cMDD and RD patients were found to have reduced small-world-ness and path length, which together may represent a trait-like topological feature of depression. In sum, the left pallidum, left pulvinar anterior of thalamus volumetric alterations may represent trait marker and reduced small-world-ness, path length may represent trait-like topological feature of MDD.

Impaired global efficiency in boys with conduct disorder and high callous unemotional traits.

Callous unemotional (CU) traits differentiate subtypes of conduct disorder (CD). It has been suggested that CU traits may be related to topographical irregularities that hinder information integration. To date, there is limited evidence of whether CU traits may be associated with abnormal brain topology. In this study, 43 CD boys with high and low CU trait (CD-HCU, CD-LCU), and 46 healthy controls (HCs) were subjected to resting-state functional magnetic resonance imaging to investigate how CU trait level and conduct problems may be reflected in topological organization. Brain functional networks were constructed and network/nodal properties, including small-world properties and network/nodal efficiency, were calculated. Topological analysis revealed that, compared with HCs, CD-HCU group were characterized by decreased small-worldness (σ), decreased global efficiency, and increased path length (λ). These variables were similar between the CD-LCU and HC groups. Self-reported CU traits in CD patients correlated negatively with global efficiency and positively with λ. Regional analysis revealed diminished nodal efficiency in the right amygdala in the CD-HCU group compared with HCs. The present results suggest that disrupted global efficiency, together with a regional abnormality affecting the amygdala, may contribute to abnormal information processing and integration in adolescents with CD and high CU traits.

Gray Matter Changes in the Orbitofrontal-Paralimbic Cortex in Male Youths With Non-comorbid Conduct Disorder.

Conduct disorder is one of the most common developmental psychiatric disorders which is characterized by persistent aggressive and antisocial behaviors during childhood or adolescence. Previous neuroimaging studies have investigated the neural correlates underlying CD and demonstrated several constructive findings. However, Individuals with CD are at high risk for comorbidities, which might give rise to the inconsistencies of existed findings. It remains unclear which neuroanatomical abnormalities are specifically related to CD without comorbidities. Using structural magnetic resonance imaging (sMRI) data of 69 CD and 69 typically developing (TD) male youths (aged 14-17 years), the present study aims at investigating gray matter volume alterations of non-comorbid CD (i.e., not comorbid with attention deficit hyperactivity disorder, substance abuse disorder, anxiety or depression). We also examined how regional gray matter volumes were related to callous-unemotional (CU) traits and conduct problems in the CD group. The whole-brain analysis revealed decreased gray matter volumes in the right pre-postcentral cortex, supramarginal gyrus and right putamen in CD youths compared with TD youths. The region-of-interest analyses showed increased gray matter volumes in the superior temporal gyrus (STG) and right orbitofrontal cortex (OFC) in CD youths. Correlation analysis found that gray matter volume in the left amygdala was negatively correlated with CU traits in CD participants. These results demonstrated that gray matter volume in the orbitofrontal-paralimbic cortex, including OFC, STG and amygdala, might characterize the male youths with non-comorbid CD and might contribute to different severe forms and trajectories of CD.

Influence of psychosocial stress on activation in human brain regions: moderation by the 5-HTTLPR genetic locus.

Variants of the serotonin transporter linked polymorphic region (5-HTTLPR) of the serotonin transporter gene SLC6A4 have been related with the onset of depression, anxiety, and other mental disorders. Homozygotes for the short 5-HTTLPR variant, referred to as the SS genotype, have greater cortisol responses to experimentally induced psychosocial stress. In the current study, we used functional magnetic resonance imaging (fMRI) to compare regional brain activations across 5-HTTLPR genotypes in subjects performing the Montreal Imaging Stress Task (MIST). Subjects with an SS genotype had significant greater increases in cortisol concentrations after the task than subjects with at least one long 5-HTTLPR allele. Additionally, relative to L carriers, the SS group had greater activation in the dorsomedial prefrontal cortex(dmPFC), dorsal anterior cingulate cortex, anterior insula.

Effects of BDNF Val66Met polymorphisms on brain structures and behaviors in adolescents with conduct disorder.

Accumulating evidence suggests that neural abnormalities in conduct disorder (CD) may be subject to genetic influences, but few imaging studies have taken genetic variants into consideration. The Val66Met polymorphism of brain-derived neurotrophic factor (BDNF) has emerged as a high-interest genetic variant due to its importance in cortical maturation, and several studies have implicated its involvement in neurodevelopmental disorders. Thus, it is unclear how this polymorphism may influence brain anatomy and aberrant behaviors in CD. A total of 65 male adolescents with CD and 69 gender-, IQ- and socioeconomic status-matched healthy controls (HCs) (age range 13-17 years) were enrolled in this study. Analyses of variance (ANOVAs) were used to assess the main effects of CD diagnosis, BDNF genotype, and diagnosis-genotype interactions on brain anatomy and behaviors. We detected a significant main effect of BDNF genotype on temporal gyrification and antisocial behaviors, but not on CD symptoms. Diagnosis-genotype interactive effects were found for cortical thickness of the superior temporal and adjacent areas. These results suggest that the BDNF Val66Met polymorphism may exert its influence both on neural alterations and delinquent behaviors in CD patients. This initial evidence highlights the importance of elucidating potentially different pathways between BDNF genotype and cortical alterations or delinquent behaviors in CD patients.

Neuroticism modulates neural activities of posterior cingulate cortex and thalamus during psychosocial stress processing.

OBJECTIVE: Individuals with higher neuroticism are vulnerable to stress and are prone to develop depression, however, the neural mechanisms underlying it have not been clarified clearly. METHOD: The Montreal Imaging Stress Task (MIST) was administered to 148 healthy adults during functional magnetic resonance imaging (fMRI). Whole-brain voxel-wise regression analyses were used to detect associations of neuroticism with neural activity involved in perceiving and processing psychosocial stress. In addition, two-sample t-tests were conducted between the high-neurotic and low-neurotic group in order to supplement the results found in regression analyses. RESULTS: Higher neuroticism scores were associated with higher activities in the posterior cingulate cortex (PCC)/precuneus and thalamus (p < 0.05, false discovery rate correction). Moreover, two sample t-tests also revealed that the high-neurotic group had higher neural stress responses in precuneus and bilateral thalamus in comparison to the low-neurotic group (p < 0.05, false discovery rate correction). LIMITATIONS: Our study mainly recruited young adults, which may limit the generalizability of our findings. CONCLUSIONS: Our findings highlight the crucial role of PCC/precuneus and thalamus in the association between neuroticism and stress and may provide insight into the cognitive model of depression.

Neural correlates of theory of mind in typically-developing youth: Influence of sex, age and callous-unemotional traits.

Theory of mind (ToM), or the ability to infer and predict the intentions, thoughts and beliefs of others, involves cognitive perspective taking (cognitive ToM/cToM) and understanding emotions (affective ToM/aToM). While behavioral evidence indicates that ToM is influenced by sex and age, no study has examined the influence of these variables on the neural correlates of cToM and aToM in late childhood/adolescence. Using fMRI with 35 typically-developing youths (aged 9-18 years, 12 males), we investigated the influence of sex and age on the neural correlates of cToM and aToM. We also examined how callous-unemotional traits, indexing a lack of empathy, were related to brain responses during aToM. Across both conditions, we found convergent activity in ToM network regions, such as superior temporal sulcus/temporoparietal junction (TPJ) and precuneus across males and females, but males recruited the left TPJ significantly more than females during cToM. During aToM, age was negatively correlated with brain responses in frontal, temporal and posterior midline regions, while callous-unemotional traits were positively correlated with right anterior insula responses. These results provide the first evidence in youth that sex influences the neural correlates of cToM, while age and callous-unemotional traits are specifically related to brain responses during aToM.

State-independent and -dependent structural alterations in limbic-cortical regions in patients with current and remitted depression.

BACKGROUND: The high recurrence of major depressive disorder (MDD) may derive from underlying state-independent structural alterations. METHODS: First-episode drug-naïve currently depressed (cMDD) patients (N = 97), remitted depressed (RD) patients (N = 72), and healthy controls (HCs, N = 100) underwent structural magnetic resonance imaging (MRI). Group differences in cortical thickness (CT), surface area (SA), and local gyrification index (lGI) were analyzed in FreeSurfer. RESULTS: Both groups of depressed patients had significantly decreased CT, relative to HCs, in the left precentral gyrus and significantly increased lGI values in the left superior frontal gyrus (SFG) indicative of state-independent alterations. Relative to HCs, the cMDD group had decreased CT of the SFG, caudal middle frontal gyrus (MFG), posterior cingulate cortex (PCC), and lateral occipital regions as well as increased SA or lGI of the superior temporal gyrus, precuneus, and pericalcarine, whereas the RD group had increased SA or lGI of the SFG, caudal MFG, and supramarginal gyrus; these alterations appeared to be state-dependent. SA or lGI values of the fusiform gyrus, inferior temporal gyrus, and superior parietal lobule differed between the cMDD and RD groups, consistent with state-dependent alterations. Beck depression inventory scores correlated with CT or lGI values of the caudal MFG, lateral occipital cortex in depressed patients. LIMITATIONS: The structural features of several subcortical limbic regions were not analyzed. CONCLUSIONS: Left precentral gyrus CT and left SFG gyrification alterations may represent state-independent alterations in MDD.

Topologically state-independent and dependent functional connectivity patterns in current and remitted depression.

OBJECTIVE: Identification of state-independent and -dependent neural biomarkers may provide insight into the pathophysiology and effective treatment of major depressive disorder (MDD), therefore we aimed to investigate the state-independent and -dependent topological alterations of MDD. METHOD: Brain resting-state functional magnetic resonance imaging (fMRI) data were acquired from 59 patients with unmedicated first episode current MDD (cMDD), 48 patients with remitted MDD (rMDD) and 60 demographically matched healthy controls (HCs). Using graph theory, we systematically studied the topological organization of their whole-brain functional networks at the global and nodal level. RESULTS: At a global level, both patient groups showed decreased normalized clustering coefficient in relative to HCs. On a nodal level, both patient groups showed decreased nodal centrality, predominantly in cortex-mood-regulation brain regions including the dorsolateral prefrontal cortex, posterior parietal cortex and posterior cingulate cortex. By comparison to cMDD patients, rMDD group had a higher nodal centrality in right parahippocampal gyrus. LIMITATIONS: The present study, an exploratory analysis, may require further confirmation with task-based and experimental studies. CONCLUSIONS: Deficits in the topological organization of the whole brain and cortex-mood-regulation brain regions in both rMDD and cMDD represent state-independent biomarkers.

Psychometric properties of the Chinese version of the Childhood Trauma Questionnaire-Short Form (CTQ-SF) among undergraduates and depressive patients.

OBJECTIVE: The Childhood Trauma Questionnaire-Short Form (CTQ-SF) is a self-report questionnaire that retrospectively provides screening for a history of childhood abuse and neglect, and which is widely used throughout the world. The current study aimed to examine the psychometric properties of the Chinese version of the CTQ-SF. METHODS: Participants included 3431 undergraduates from Hunan provinces and 234 depressive patients from psychological clinics. Confirmatory factor analysis was performed to examine how well the original five-factor model fit the data and the measurement equivalence of CTQ-SF across gender. Internal consistency was also evaluated. RESULTS: The five-factor model achieved satisfactory fit (Undergraduate sample TLI = 0.925, CFI = 0.936, RMSEA = 0.034, SRMR = 0.046; depressive sample TLI = 0.912, CFI = 0.923, RMSEA = 0.044, SRMR = 0.062). Measurement invariance of the five-factor model across gender was supported fully assuming different degrees of invariance. The CTQ-SF also showed acceptable internal consistency and good stability. CONCLUSION: The current study provides that the Chinese version of the Childhood Trauma questionnaire-short form has good reliability and validity among Chinese undergraduates and depressive samples, which also indicates that the CTQ-SF is a good tool for child trauma assessment.

State-Related Alterations of Spontaneous Neural Activity in Current and Remitted Depression Revealed by Resting-State fMRI.

Purpose: Although efforts have been made to identify neurobiological characteristic of major depressive disorder (MDD) in recent years, trait- and state-related biological characteristics of MDD still remains unclear. Using functional magnetic resonance imaging (fMRI), the aim of this study was to explore whether altered spontaneous neural activities in MDD are trait- or state- related. Materials and Methods: Resting-state fMRI data were analyzed for 72 current MDD (cMDD) patients (first-episode, medication-naïve), 49 remitted MDD (rMDD) patients, and 78 age- and sex- matched healthy control (HC) subjects. The values of amplitude of low-frequency fluctuation (ALFF) were compared between groups. Results: Compared with the cMDD group, the rMDD group had increased ALFF values in the left middle occipital gyrus, left middle temporal gyrus and right cerebellum anterior lobe. Besides, compared with the HC group, the cMDD group had decreased ALFF values in the left middle occipital gyrus. Further analysis explored that the mean ALFF values in the left middle occipital gyrus, left middle temporal gyrus and right cerebellum anterior lobe were correlated positively with BDI scores in rMDD patients. Conclusion: Abnormal activity in the left middle occipital gyrus, left middle temporal gyrus and right cerebellum anterior lobe may be state-specific in current (first-episode, medication-naïve) and remitted (medication-naïve) depression patients. Furthermore, the state-related compensatory effect was found in these brain areas.

State-independent alterations of intrinsic brain network in current and remitted depression.

BACKGROUND: It has been proposed that state-independent, or trait, neurobiological alterations across illness phases may contribute to the high recurrence of major depressive disorder (MDD). Although intrinsic brain network abnormalities have been implicated consistently in MDD neuropathology, MDD state-independent and -dependent resting-state network alterations have not been clearly studied. METHODS: Resting-state functional magnetic resonance imaging (fMRI) data were collected from 57 medication-naive first-episode current MDD patients, 35 remitted MDD patients, and 66 healthy controls (HCs). Independent component analysis (ICA) was used to extract subnetworks of the default mode network (DMN), central executive network (CEN), and salience network (SN). RESULTS: Relative to HCs, the current MDD and remitted MDD groups had decreased intra-intrinsic functional connectivity (iFC) in the dorsal lateral prefrontal cortex (dlPFC) of the left CEN, increased inter-FC between the SN and right CEN (rCEN), and decreased inter-FC between the anterior DMN (aDMN) and rCEN. The altered intra-iFC in the left CEN were correlated negatively with the depressive level in the remitted MDD. CONCLUSIONS: Hypoactivity of the dlPFC in the left CEN, increased inter-FC between the SN and rCEN, and decreased inter-FC between the aDMN and rCEN may reflect state-independent biomarkers of MDD.

MAOA genotype modulates default mode network deactivation during inhibitory control.

It has been demonstrated, in a long line of research, that the low-activity genotype of the monoamine oxidase A (MAOA) gene is associated with aggression. Previous work has linked impaired response inhibition to aggression, but little is known about how this relates to the purported MAOA-aggression relationship in adolescents. Here, we examined how MAOA genotype influences neural correlates of inhibitory control in 74 healthy male adolescents using a GoStop and a Go/Nogo task while differentiating between action cancelation and action restraint. Carriers of the low-expressing MAOA alleles (MAOA-L) did not show altered brain activation in the prefrontal-subcortical inhibition network relative to carriers of the high-expressing alleles across inhibition conditions. However, they exhibited a more pronounced deactivation during response inhibition in the posterior cingulate cortex (PCC) and precuneus, areas belonging to the default mode network (DMN). Larger DMN suppression in MAOA-L carriers might represent a compensation mechanism for impaired cognitive control.

MAOA genotype influences neural response during an inhibitory task in adolescents with conduct disorder.

Conduct disorder (CD), a common psychiatric disorder in children and adolescents, is characterized by encroaching upon other rights and violations of age-appropriate social expectations repeatedly and persistently. Individuals with CD often have high aggressiveness and low inhibitory capacity. The monoamine oxidase A (MAOA) gene has long been associated with aggression. Effects of MAOA genotype on inhibitory control have been examined in general population. Several studies had revealed reduced activation in prefrontal areas, especially the anterior cingulate cortex (ACC), in low-expression MAOA (MAOA-L) allele carriers compared to high-expression MAOA (MAOA-H) allele carriers. However, little is known about its genetic risk influences on inhibitory processes in clinical samples. In this study, functional magnetic resonance imaging (fMRI) was administered to a sample of adolescent boys with CD during the performance of a GoStop task, 29 of whom carrying MAOA-L allele and 24 carrying MAOA-H allele. Relative to MAOA-H carriers, MAOA-L carriers in CD showed more pronounced deactivation in the precuneus, supplementary motor area (SMA) and dorsal anterior cingulate cortex (dACC). Deactivation within the default mode network (DMN) and inhibitory-related areas in MAOA-L carriers may be related to compensation for low sensitivity to inhibition and/or an atypical allocation of cognitive resources. The results suggested a possible neural mechanism through which MAOA affects inhibitory processes in a clinical sample.

Distinguishing Adolescents With Conduct Disorder From Typically Developing Youngsters Based on Pattern Classification of Brain Structural MRI.

Background: Conduct disorder (CD) is a mental disorder diagnosed in childhood or adolescence that presents antisocial behaviors, and is associated with structural alterations in brain. However, whether these structural alterations can distinguish CD from healthy controls (HCs) remains unknown. Here, we quantified these structural differences and explored the classification ability of these quantitative features based on machine learning (ML). Materials and Methods: High-resolution 3D structural magnetic resonance imaging (sMRI) was acquired from 60 CD subjects and 60 age-matched HCs. Voxel-based morphometry (VBM) was used to assess the regional gray matter (GM) volume difference. The significantly different regional GM volumes were then extracted as features, and input into three ML classifiers: logistic regression, random forest and support vector machine (SVM). We trained and tested these ML models for classifying CD from HCs by using fivefold cross-validation (CV). Results: Eight brain regions with abnormal GM volumes were detected, which mainly distributed in the frontal lobe, parietal lobe, anterior cingulate, cerebellum posterior lobe, lingual gyrus, and insula areas. We found that these ML models achieved comparable classification performance, with accuracy of 77.9 ∼ 80.4%, specificity of 73.3 ∼ 80.4%, sensitivity of 75.4 ∼ 87.5%, and area under the receiver operating characteristic curve (AUC) of 0.76 ∼ 0.80. Conclusion: Based on sMRI and ML, the regional GM volumes may be used as potential imaging biomarkers for stable and accurate classification of CD.