Search

Abstract The progression of Parkinson’s disease (PD) is associated with microstructural alterations in neural pathways, contributing to both motor and cognitive decline. However, conflicting findings have emerged due to the use of heterogeneous methods in small studies. Here we performed a large diffusion MRI study in PD, integrating data from 17 cohorts worldwide, to identify stage-specific profiles of white matter differences. Diffusion-weighted MRI data from 1654 participants diagnosed with PD (age: 20–89 years; 33% female) and 885 controls (age: 19–84 years; 47% female) were analyzed using the ENIGMA-DTI protocol to evaluate white matter microstructure. Skeletonized maps of fractional anisotropy (FA) and mean diffusivity (MD) were compared across Hoehn and Yahr (HY) disease groups and controls to reveal the profile of white matter alterations at different stages. We found an enhanced, more widespread pattern of microstructural alterations with each stage of PD, with eventually lower FA and higher MD in almost all regions of interest: Cohen’s d effect sizes reached d = −1.01 for FA differences in the fornix at PD HY Stage 4/5. The early PD signature in HY stage 1 included higher FA and lower MD across the entire white matter skeleton, in a direction opposite to that typical of other neurodegenerative diseases. FA and MD were associated with motor and non-motor clinical dysfunction. While overridden by degenerative changes in the later stages of PD, early PD is associated with paradoxically higher FA and lower MD in PD, consistent with early compensatory changes associated with the disorder.

Abstract Machine learning can be used to define subtypes of psychiatric conditions based on shared biological foundations of mental disorders. Here we analyzed cross-sectional brain images from 4,222 individuals with schizophrenia and 7038 healthy subjects pooled across 41 international cohorts from the ENIGMA, non-ENIGMA cohorts and public datasets. Using the Subtype and Stage Inference (SuStaIn) algorithm, we identify two distinct neurostructural subgroups by mapping the spatial and temporal ‘trajectory’ of gray matter change in schizophrenia. Subgroup 1 was characterized by an early cortical-predominant loss with enlarged striatum, whereas subgroup 2 displayed an early subcortical-predominant loss in the hippocampus, striatum and other subcortical regions. We confirmed the reproducibility of the two neurostructural subtypes across various sample sites, including Europe, North America and East Asia. This imaging-based taxonomy holds the potential to identify individuals with shared neurobiological attributes, thereby suggesting the viability of redefining existing disorder constructs based on biological factors.

Abnormal β-amyloid (Aβ) accumulation in the brain is an early indicator of Alzheimer’s disease (AD) and is typically assessed through invasive procedures such as PET (positron emission tomography) or CSF (cerebrospinal fluid) assays. As new anti-Alzheimer’s treatments can now successfully target amyloid pathology, there is a growing interest in predicting Aβ positivity (Aβ+) from less invasive, more widely available types of brain scans, such as T1-weighted (T1w) MRI. Here we compare multiple approaches to infer Aβ + from standard anatomical MRI: (1) classical machine learning algorithms, including logistic regression, XGBoost, and shallow artificial neural networks, (2) deep learning models based on 2D and 3D convolutional neural networks (CNNs), (3) a hybrid ANN-CNN, combining the strengths of shallow and deep neural networks, (4) transfer learning models based on CNNs, and (5) 3D Vision Transformers. All models were trained on paired MRI/PET data from 1,847 elderly participants (mean age: 75.1 yrs. ± 7.6SD; 863 females/984 males; 661 healthy controls, 889 with mild cognitive impairment (MCI), and 297 with Dementia), scanned as part of the Alzheimer’s Disease Neuroimaging Initiative. We evaluated each model’s balanced accuracy and F1 scores. While further tests on more diverse data are warranted, deep learning models trained on standard MRI showed promise for estimating Aβ + status, at least in people with MCI. This may offer a potential screening option before resorting to more invasive procedures.

Abstract Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (N = 5365) to provide a generalizable ML classification benchmark of major depressive disorder (MDD) using shallow linear and non-linear models. Leveraging brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD versus healthy controls (HC) with a balanced accuracy of around 62%. But after harmonizing the data, e.g., using ComBat, the balanced accuracy dropped to approximately 52%. Accuracy results close to random chance levels were also observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may yield more encouraging prospects.

Deficits in memory performance have been linked to a wide range of neurological and neuropsychiatric conditions. While many studies have assessed the memory impacts of individual conditions, this study considers a broader perspective by evaluating how memory recall is differentially associated with nine common neuropsychiatric conditions using data drawn from 55 international studies, aggregating 15,883 unique participants aged 15–90. The effects of dementia, mild cognitive impairment, Parkinson’s disease, traumatic brain injury, stroke, depression, attention-deficit/hyperactivity disorder (ADHD), schizophrenia, and bipolar disorder on immediate, short-, and long-delay verbal learning and memory (VLM) scores were estimated relative to matched healthy individuals. Random forest models identified age, years of education, and site as important VLM covariates. A Bayesian harmonization approach was used to isolate and remove site effects. Regression estimated the adjusted association of each clinical group with VLM scores. Memory deficits were strongly associated with dementia and schizophrenia (p < 0.001), while neither depression nor ADHD showed consistent associations with VLM scores (p > 0.05). Differences associated with clinical conditions were larger for longer delayed recall duration items. By comparing VLM across clinical conditions, this study provides a foundation for enhanced diagnostic precision and offers new insights into disease management of comorbid disorders.

Background: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group. Methods: We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality. Results: We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance. Conclusion: These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

Individuals across six major psychiatric conditions from the ENIGMA consortium reveals a shared morphological effect, following a sensory-fugal axis, which is related to microstructural gradient and neurotransmitter axes.

Changes to structural and functional connectivity can give rise to neurodegeneration and neurodevelopmental diseases. Here the authors investigate molecular and connectomic patterns in 13 different neurological, psychiatric and neurodevelopmental diseases from the ENIGMA consortium.

Abstract Individuals at Clinical High Risk for Psychosis (CHR-P) demonstrate heterogeneity in clinical profiles and outcome features. However, the extent of neuroanatomical heterogeneity in the CHR-P state is largely undetermined. We aimed to quantify the neuroanatomical heterogeneity in structural magnetic resonance imaging measures of cortical surface area (SA), cortical thickness (CT), subcortical volume (SV), and intracranial volume (ICV) in CHR-P individuals compared with healthy controls (HC), and in relation to subsequent transition to a first episode of psychosis. The ENIGMA CHR-P consortium applied a harmonised analysis to neuroimaging data across 29 international sites, including 1579 CHR-P individuals and 1243 HC, offering the largest pooled CHR-P neuroimaging dataset to date. Regional heterogeneity was indexed with the Variability Ratio (VR) and Coefficient of Variation (CV) ratio applied at the group level. Personalised estimates of heterogeneity of SA, CT and SV brain profiles were indexed with the novel Person-Based Similarity Index (PBSI), with two complementary applications. First, to assess the extent of within-diagnosis similarity or divergence of neuroanatomical profiles between individuals. Second, using a normative modelling approach, to assess the ‘normativeness’ of neuroanatomical profiles in individuals at CHR-P. CHR-P individuals demonstrated no greater regional heterogeneity after applying FDR corrections. However, PBSI scores indicated significantly greater neuroanatomical divergence in global SA, CT and SV profiles in CHR-P individuals compared with HC. Normative PBSI analysis identified 11 CHR-P individuals (0.70%) with marked deviation (>1.5 SD) in SA, 118 (7.47%) in CT and 161 (10.20%) in SV. Psychosis transition was not significantly associated with any measure of heterogeneity. Overall, our examination of neuroanatomical heterogeneity within the CHR-P state indicated greater divergence in neuroanatomical profiles at an individual level, irrespective of psychosis conversion. Further large-scale investigations are required of those who demonstrate marked deviation.

Alzheimer’s disease (AD) is a progressive neurodegenerative disease characterized by cognitive decline and atrophy in the medial temporal lobe (MTL) and subsequent brain regions. Structural magnetic resonance imaging (sMRI) has been widely used in research and clinical care for diagnosis and monitoring AD progression. However, atrophy patterns are complex and vary by patient. To address this issue, researchers have made efforts to develop more concise metrics that can summarize AD-specific atrophy. Many of these methods can be difficult to interpret clinically, hampering adoption.In this study, we introduce a novel index which we call an “AD-NeuroScore,” that uses a modified Euclidean-inspired distance function to calculate differences between regional brain volumes associated with cognitive decline. The index is adjusted for intracranial volume (ICV), age, sex, and scanner model. We validated AD-NeuroScore using 929 older adults from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, with a mean age of 72.7 years (SD = 6.3; 55.1–91.5) and cognitively normal (CN), mild cognitive impairment (MCI), or AD diagnoses.Our validation results showed that AD-NeuroScore was significantly associated with diagnosis and disease severity scores (measured by MMSE, CDR-SB, and ADAS-11) at baseline. Furthermore, baseline AD-NeuroScore was associated with both changes in diagnosis and disease severity scores at all time points with available data. The performance of AD-NeuroScore was equivalent or superior to adjusted hippocampal volume (AHV), a widely used metric in AD research. Further, AD-NeuroScore typically performed as well as or sometimes better when compared to other existing sMRI-based metrics.In conclusion, we have introduced a new metric, AD-NeuroScore, which shows promising results in detecting AD, benchmarking disease severity, and predicting disease progression. AD-NeuroScore differentiates itself from other metrics by being clinically practical and interpretable.

Abstract The goal of this study was to compare brain structure between individuals with generalized anxiety disorder (GAD) and healthy controls. Previous studies have generated inconsistent findings, possibly due to small sample sizes, or clinical/analytic heterogeneity. To address these concerns, we combined data from 28 research sites worldwide through the ENIGMA-Anxiety Working Group, using a single, pre-registered mega-analysis. Structural magnetic resonance imaging data from children and adults (5–90 years) were processed using FreeSurfer. The main analysis included the regional and vertex-wise cortical thickness, cortical surface area, and subcortical volume as dependent variables, and GAD, age, age-squared, sex, and their interactions as independent variables. Nuisance variables included IQ, years of education, medication use, comorbidities, and global brain measures. The main analysis (1020 individuals with GAD and 2999 healthy controls) included random slopes per site and random intercepts per scanner. A secondary analysis (1112 individuals with GAD and 3282 healthy controls) included fixed slopes and random intercepts per scanner with the same variables. The main analysis showed no effect of GAD on brain structure, nor interactions involving GAD, age, or sex. The secondary analysis showed increased volume in the right ventral diencephalon in male individuals with GAD compared to male healthy controls, whereas female individuals with GAD did not differ from female healthy controls. This mega-analysis combining worldwide data showed that differences in brain structure related to GAD are small, possibly reflecting heterogeneity or those structural alterations are not a major component of its pathophysiology.

Results of neuroimaging datasets aggregated from multiple sites may be biased by site-specific profiles in participants’ demographic and clinical characteristics, as well as MRI acquisition protocols and scanning platforms. We compared the impact of four different harmonization methods on results obtained from analyses of cortical thickness data: (1) linear mixed-effects model (LME) that models site-specific random intercepts (LMEINT), (2) LME that models both site-specific random intercepts and age-related random slopes (LMEINT+SLP), (3) ComBat, and (4) ComBat with a generalized additive model (ComBat-GAM). Our test case for comparing harmonization methods was cortical thickness data aggregated from 29 sites, which included 1,340 cases with posttraumatic stress disorder (PTSD) (6.2–81.8 years old) and 2,057 trauma-exposed controls without PTSD (6.3–85.2 years old). We found that, compared to the other data harmonization methods, data processed with ComBat-GAM was more sensitive to the detection of significant case-control differences (Χ2(3) = 63.704, p < 0.001) as well as case-control differences in age-related cortical thinning (Χ2(3) = 12.082, p = 0.007). Both ComBat and ComBat-GAM outperformed LME methods in detecting sex differences (Χ2(3) = 9.114, p = 0.028) in regional cortical thickness. ComBat-GAM also led to stronger estimates of age-related declines in cortical thickness (corrected p-values < 0.001), stronger estimates of case-related cortical thickness reduction (corrected p-values < 0.001), weaker estimates of age-related declines in cortical thickness in cases than controls (corrected p-values < 0.001), stronger estimates of cortical thickness reduction in females than males (corrected p-values < 0.001), and stronger estimates of cortical thickness reduction in females relative to males in cases than controls (corrected p-values < 0.001). Our results support the use of ComBat-GAM to minimize confounds and increase statistical power when harmonizing data with non-linear effects, and the use of either ComBat or ComBat-GAM for harmonizing data with linear effects.

Tourette syndrome (TS) is characterized by multiple motor and vocal tics, and high-comorbidity rates with other neuropsychiatric disorders. Obsessive compulsive disorder (OCD), attention deficit hyperactivity disorder (ADHD), autism spectrum disorders (ASDs), major depressive disorder (MDD), and anxiety disorders (AXDs) are among the most prevalent TS comorbidities. To date, studies on TS brain structure and function have been limited in size with efforts mostly fragmented. This leads to low-statistical power, discordant results due to differences in approaches, and hinders the ability to stratify patients according to clinical parameters and investigate comorbidity patterns. Here, we present the scientific premise, perspectives, and key goals that have motivated the establishment of the Enhancing Neuroimaging Genetics through Meta-Analysis for TS (ENIGMA-TS) working group. The ENIGMA-TS working group is an international collaborative effort bringing together a large network of investigators who aim to understand brain structure and function in TS and dissect the underlying neurobiology that leads to observed comorbidity patterns and clinical heterogeneity. Previously collected TS neuroimaging data will be analyzed jointly and integrated with TS genomic data, as well as equivalently large and already existing studies of highly comorbid OCD, ADHD, ASD, MDD, and AXD. Our work highlights the power of collaborative efforts and transdiagnostic approaches, and points to the existence of different TS subtypes. ENIGMA-TS will offer large-scale, high-powered studies that will lead to important insights toward understanding brain structure and function and genetic effects in TS and related disorders, and the identification of biomarkers that could help inform improved clinical practice.

Neurological and psychiatric illnesses are associated with regional brain deficit patterns that bear unique signatures and capture illness-specific characteristics. The Regional Vulnerability Index (RVI) was developed to quantify brain similarity by comparing individual white matter microstructure, cortical gray matter thickness and subcortical gray matter structural volume measures with neuroanatomical deficit patterns derived from large-scale meta-analytic studies. We tested the specificity of the RVI approach for major depressive disorder (MDD) and Alzheimer’s disease (AD) in a large epidemiological sample of UK Biobank (UKBB) participants (N = 19,393; 9138 M/10,255F; age = 64.8 ± 7.4 years). Compared to controls free of neuropsychiatric disorders, participants with MDD (N = 2,248; 805 M/1443F; age = 63.4 ± 7.4) had significantly higher RVI-MDD values (t = 5.6, p = 1·10−8), but showed no detectable difference in RVI-AD (t = 2.0, p = 0.10). Subjects with dementia (N = 7; 4 M/3F; age = 68.6 ± 8.6 years) showed significant elevation in RVI-AD (t = 4.2, p = 3·10−5) but not RVI-MDD (t = 2.1, p = 0.10) compared to controls. Even within affective illnesses, participants with bipolar disorder (N = 54) and anxiety disorder (N = 773) showed no significant elevation in whole-brain RVI-MDD. Participants with Parkinson’s disease (N = 37) showed elevation in RVI-AD (t = 2.4, p = 0.01) while subjects with stroke (N = 247) showed no such elevation (t = 1.1, p = 0.3). In summary, we demonstrated elevation in RVI-MDD and RVI-AD measures in the respective illnesses with strong replicability that is relatively specific to the respective diagnoses. These neuroanatomic deviation patterns offer a useful biomarker for population-wide assessments of similarity to neuropsychiatric illnesses.

Artificial intelligence has recently gained popularity across different medical fields to aid in the detection of diseases based on pathology samples or medical imaging findings. Brain magnetic resonance imaging (MRI) is a key assessment tool for patients with temporal lobe epilepsy (TLE). The role of machine learning and artificial intelligence to increase detection of brain abnormalities in TLE remains inconclusive. We used support vector machine (SV) and deep learning (DL) models based on region of interest (ROI-based) structural (n = 336) and diffusion (n = 863) brain MRI data from patients with TLE with (“lesional”) and without (“non-lesional”) radiographic features suggestive of underlying hippocampal sclerosis from the multinational (multi-center) ENIGMA-Epilepsy consortium. Our data showed that models to identify TLE performed better or similar (68–75%) compared to models to lateralize the side of TLE (56–73%, except structural-based) based on diffusion data with the opposite pattern seen for structural data (67–75% to diagnose vs. 83% to lateralize). In other aspects, structural and diffusion-based models showed similar classification accuracies. Our classification models for patients with hippocampal sclerosis were more accurate (68–76%) than models that stratified non-lesional patients (53–62%). Overall, SV and DL models performed similarly with several instances in which SV mildly outperformed DL. We discuss the relative performance of these models with ROI-level data and the implications for future applications of machine learning and artificial intelligence in epilepsy care.

Brain imaging with diffusion-weighted MRI (dMRI) is sensitive to microstructural white matter (WM) changes associated with brain aging and neurodegeneration. In its third phase, the Alzheimer’s Disease Neuroimaging Initiative (ADNI3) is collecting data across multiple sites and scanners using different dMRI acquisition protocols, to better understand disease effects. It is vital to understand when data can be pooled across scanners, and how the choice of dMRI protocol affects the sensitivity of extracted measures to differences in clinical impairment. Here, we analyzed ADNI3 data from 317 participants (mean age: 75.4 ± 7.9 years; 143 men/174 women), who were each scanned at one of 47 sites with one of six dMRI protocols using scanners from three different manufacturers. We computed four standard diffusion tensor imaging (DTI) indices including fractional anisotropy (FADTI) and mean, radial, and axial diffusivity, and one FA index based on the tensor distribution function (FATDF), in 24 bilaterally averaged WM regions of interest. We found that protocol differences significantly affected dMRI indices, in particular FADTI. We ranked the diffusion indices for their strength of association with four clinical assessments. In addition to diagnosis, we evaluated cognitive impairment as indexed by three commonly used screening tools for detecting dementia and AD: the AD Assessment Scale (ADAS-cog), the Mini-Mental State Examination (MMSE), and the Clinical Dementia Rating scale sum-of-boxes (CDR-sob). Using a nested random-effects regression model to account for protocol and site, we found that across all dMRI indices and clinical measures, the hippocampal-cingulum and fornix (crus)/stria terminalis regions most consistently showed strong associations with clinical impairment. Overall, the greatest effect sizes were detected in the hippocampal-cingulum (CGH) and uncinate fasciculus (UNC) for associations between axial or mean diffusivity and CDR-sob. FATDF detected robust widespread associations with clinical measures, while FADTI was the weakest of the five indices for detecting associations. Ultimately, we were able to successfully pool dMRI data from multiple acquisition protocols from ADNI3 and detect consistent and robust associations with clinical impairment and age.