Structural Magnetic Resonance Imaging Datasets Research Articles

Integration of graph network with kernel SVM and logistic regression for identification of biomarkers in SCA12 and its diagnosis.

Spinocerebellar ataxia type 12 is a hereditary and neurodegenerative illness commonly found in India. However, there is no established noninvasive automatic diagnostic system for its diagnosis and identification of imaging biomarkers. This work proposes a novel four-phase machine learning-based diagnostic framework to find spinocerebellar ataxia type 12 disease-specific atrophic-brain regions and distinguish spinocerebellar ataxia type 12 from healthy using a real structural magnetic resonance imaging dataset. Firstly, each brain region is represented in terms of statistics of coefficients obtained using 3D-discrete wavelet transform. Secondly, a set of relevant regions are selected using a graph network-based method. Thirdly, a kernel support vector machine is used to capture nonlinear relationships among the voxels of a brain region. Finally, the linear relationship among the brain regions is captured to build a decision model to distinguish spinocerebellar ataxia type 12 from healthy by using the regularized logistic regression method. A classification accuracy of 95% and a harmonic mean of precision and recall, i.e. F1-score of 94.92%, is achieved. The proposed framework provides relevant regions responsible for the atrophy. The importance of each region is captured using Shapley Additive exPlanations values. We also performed a statistical analysis to find volumetric changes in spinocerebellar ataxia type 12 group compared to healthy. The promising result of the proposed framework shows that clinicians can use it for early and timely diagnosis of spinocerebellar ataxia type 12.

Controlling the false discovery rate in transformational sparsity: Split Knockoffs

Abstract Controlling the False Discovery Rate (FDR) in a variable selection procedure is critical for reproducible discoveries, and it has been extensively studied in sparse linear models. However, it remains largely open in scenarios where the sparsity constraint is not directly imposed on the parameters but on a linear transformation of the parameters to be estimated. Examples of such scenarios include total variations, wavelet transforms, fused LASSO, and trend filtering. In this paper, we propose a data-adaptive FDR control method, called the Split Knockoff method, for this transformational sparsity setting. The proposed method exploits both variable and data splitting. The linear transformation constraint is relaxed to its Euclidean proximity in a lifted parameter space, which yields an orthogonal design that enables the orthogonal Split Knockoff construction. To overcome the challenge that exchangeability fails due to the heterogeneous noise brought by the transformation, new inverse supermartingale structures are developed via data splitting for provable FDR control without sacrificing power. Simulation experiments demonstrate that the proposed methodology achieves the desired FDR and power. We also provide an application to Alzheimer’s Disease study, where atrophy brain regions and their abnormal connections can be discovered based on a structural Magnetic Resonance Imaging dataset.

Removal of site effects and enhancement of signal using dual projection independent component analysis for pooling multi-site MRI data.

Combining magnetic resonance imaging (MRI) data from multi-site studies is a popular approach for constructing larger datasets to greatly enhance the reliability and reproducibility of neuroscience research. However, the scanner/site variability is a significant confound that complicates the interpretation of the results, so effective and complete removal of the scanner/site variability is necessary to realise the full advantages of pooling multi-site datasets. Independent component analysis (ICA) and general linear model (GLM) based harmonisation methods are the two primary methods used to eliminate scanner/site effects. Unfortunately, there are challenges with both ICA-based and GLM-based harmonisation methods to remove site effects completely when the signals of interest and scanner/site effects-related variables are correlated, which may occur in neuroscience studies. In this study, we propose an effective and powerful harmonisation strategy that implements dual projection (DP) theory based on ICA to remove the scanner/site effects more completely. This method can separate the signal effects correlated with site variables from the identified site effects for removal without losing signals of interest. Both simulations and vivo structural MRI datasets, including a dataset from Autism Brain Imaging Data Exchange II and a travelling subject dataset from the Strategic Research Program for Brain Sciences, were used to test the performance of a DP-based ICA harmonisation method. Results show that DP-based ICA harmonisation has superior performance for removing site effects and enhancing the sensitivity to detect signals of interest as compared with GLM-based and conventional ICA harmonisation methods.

Magnetic resonance imaging datasets with anatomical fiducials for quality control and registration

Tools available for reproducible, quantitative assessment of brain correspondence have been limited. We previously validated the anatomical fiducial (AFID) placement protocol for point-based assessment of image registration with millimetric (mm) accuracy. In this data descriptor, we release curated AFID placements for some of the most commonly used structural magnetic resonance imaging datasets and templates. The release of our accurate placements allows for rapid quality control of image registration, teaching neuroanatomy, and clinical applications such as disease diagnosis and surgical targeting. We release placements on individual subjects from four datasets (N = 132 subjects for a total of 15,232 fiducials) and 14 brain templates (4,288 fiducials), totalling more than 300 human rater hours of annotation. We also validate human rater accuracy of released placements to be within 1 – 2 mm (using more than 45,000 Euclidean distances), consistent with prior studies. Our data is compliant with the Brain Imaging Data Structure allowing for facile incorporation into neuroimaging analysis pipelines.

Measures of Brain Connectivity and Cognition by Sex in US Children

The neurobiological underpinnings underlying sex differences in cognition during adolescence are largely unknown. To examine sex differences in brain circuitry and their association with cognitive performance in US children. This cross-sectional study analyzed behavioral and imaging data from 9- to 11-year-old children from the Adolescent Brain Cognitive Development (ABCD) study between August 2017 and November 2018. The ABCD study is an open-science, multisite study following up more than 11 800 youths into early adulthood for 10 years with annual laboratory-based assessments and biennial magnetic resonance imaging (MRI). The selection of ABCD study children for the current analysis was based on the availability of functional and structural MRI data sets in ABCD Brain Imaging Data Structure Community Collection format. Five hundred and sixty participants who had excessive level of head motion (>50% of time points with framewise displacement >0.5 mm) during resting-state functional MRI were excluded from the analyses. Data were analyzed between January and August 2022. The main outcomes were the sex differences in (A) global functional connectivity density at rest and (B) mean water diffusivity (MD) and (C) the correlation of these metrics with total cognitive scores. A total of 8961 children (4604 boys and 4357 girls; mean [SD] age, 9.92 [0.62] years) were included in this analysis. Girls had higher functional connectivity density in default mode network hubs than boys, predominantly in the posterior cingulate cortex (Cohen d = -0.36), and lower MD and transverse diffusivity, predominantly in the superior corticostriatal white matter bundle (Cohen d = 0.3). Age-corrected fluid and total composite scores were higher for girls than for boys (Cohen d = -0.08 [fluid] and -0.04 [total]; P = 2.7 × 10-5). Although total mean (SD) brain volume (1260 [104] mL in boys and 1160 [95] mL in girls; t = 50; Cohen d = 1.0; df = 8738) and the proportion of white matter (d = 0.4) were larger for boys than for girls, the proportion of gray matter was larger for girls than for boys (d = -0.3; P = 2.2 × 10-16). The findings of this cross-sectional study on sex differences in brain connectivity and cognition are relevant to the future creation of brain developmental trajectory charts to monitor for deviations associated with impairments in cognition or behavior, including those due to psychiatric or neurological disorders. They could also serve as a framework for studies investigating the differential contribution of biological vs social or cultural factors in the neurodevelopmental trajectories of girls and boys.

Atypical hemispheric lateralization of brain function and structure in autism: a comprehensive meta-analysis study.

Characteristic changes in the asymmetric nature of the human brain are associated with neurodevelopmental differences related to autism. In people with autism, these differences are thought to affect brain structure and function, although the structural and functional bases of these defects are yet to be fully characterized. We applied a comprehensive meta-analysis to resting-state functional and structural magnetic resonance imaging datasets from 370 people with autism and 498 non-autistic controls using seven datasets of the Autism Brain Imaging Data Exchange Project. We studied the meta-effect sizes based on standardized mean differences and standard deviations (s.d.) for lateralization of gray matter volume (GMV), fractional amplitude of low-frequency fluctuation (fALFF), and regional homogeneity (ReHo). We examined the functional correlates of atypical laterality through an indirect annotation approach followed by a direct correlation analysis with symptom scores. In people with autism, 85, 51, and 51% of brain regions showed a significant diagnostic effect for lateralization in GMV, fALFF, and ReHo, respectively. Among these regions, 35.7% showed overlapping differences in lateralization in GMV, fALFF, and ReHo, particularly in regions with functional annotations for language, motor, and perceptual functions. These differences were associated with clinical measures of reciprocal social interaction, communication, and repetitive behaviors. A meta-analysis based on s.d. showed that people with autism had lower variability in structural lateralization but higher variability in functional lateralization. These findings highlight that atypical hemispheric lateralization is a consistent feature in autism across different sites and may be used as a neurobiological marker for autism.

QMRI-BIDS: An extension to the brain imaging data structure for quantitative magnetic resonance imaging data

The Brain Imaging Data Structure (BIDS) established community consensus on the organization of data and metadata for several neuroimaging modalities. Traditionally, BIDS had a strong focus on functional magnetic resonance imaging (MRI) datasets and lacked guidance on how to store multimodal structural MRI datasets. Here, we present and describe the BIDS Extension Proposal 001 (BEP001), which adds a range of quantitative MRI (qMRI) applications to the BIDS. In general, the aim of qMRI is to characterize brain microstructure by quantifying the physical MR parameters of the tissue via computational, biophysical models. By proposing this new standard, we envision standardization of qMRI through multicenter dissemination of interoperable datasets. This way, BIDS can act as a catalyst of convergence between qMRI methods development and application-driven neuroimaging studies that can help develop quantitative biomarkers for neural tissue characterization. In conclusion, this BIDS extension offers a common ground for developers to exchange novel imaging data and tools, reducing the entrance barrier for qMRI in the field of neuroimaging.

SPAMRI: A MATLAB Toolbox for Surface-Based Processing and Analysis of Magnetic Resonance Imaging.

Structural magnetic resonance imaging (MRI) has elicited increasing attention in morphological surface studies due to its stability and sensitivity to neurodegenerative processes, particularly in exploring brain aging and psychiatric disease. However, a user-friendly toolbox for the surface-based analysis of structural MRI is still lacking. On the basis of certain software functions in FreeSurfer, CAT and ANTs, a MATLAB toolbox called “surface-based processing and analysis of MRI” (SPAMRI) has been developed, which can be performed in Windows, Linux and Mac-OS. SPAMRI contains several features as follows: (1) open-source MATLAB-based package with a graphical user interface (GUI); (2) a set of images that can be generated for quality checking, such as Talairach transform, skull strip, and surface reconstruction; (3) user-friendly GUI with capabilities on statistical analysis, multiple comparison corrections, reporting of results, and surface measurement extraction; and (4) provision of a conversion tool between surface files (e.g., mesh files) and volume files (e.g., NIFTI files). SPAMRI is applied to a publicly released structural MRI dataset of 44 healthy young adults and 39 old adults. Findings showed that old people have decreased cortical thickness, especially in prefrontal cortex, relative to those of young adults, thereby suggesting a cognitive decline in the former. SPAMRI is anticipated to substantially simplify surface-based image processing and MRI dataset analyses and subsequently open new opportunities to investigate structural morphologies.

Consecutive Independence and Correlation Transform for Multimodal Data Fusion: Discovery of One-to-Many Associations in Structural and Functional Imaging Data

Brain signals can be measured using multiple imaging modalities, such as magnetic resonance imaging (MRI)-based techniques. Different modalities convey distinct yet complementary information; thus, their joint analyses can provide valuable insight into how the brain functions in both healthy and diseased conditions. Data-driven approaches have proven most useful for multimodal fusion as they minimize assumptions imposed on the data, and there are a number of methods that have been developed to uncover relationships across modalities. However, none of these methods, to the best of our knowledge, can discover “one-to-many associations”, meaning one component from one modality is linked with more than one component from another modality. However, such “one-to-many associations” are likely to exist, since the same brain region can be involved in multiple neurological processes. Additionally, most existing data fusion methods require the signal subspace order to be identical for all modalities—a severe restriction for real-world data of different modalities. Here, we propose a new fusion technique—the consecutive independence and correlation transform (C-ICT) model—which successively performs independent component analysis and independent vector analysis and is uniquely flexible in terms of the number of datasets, signal subspace order, and the opportunity to find “one-to-many associations”. We apply C-ICT to fuse diffusion MRI, structural MRI, and functional MRI datasets collected from healthy controls (HCs) and patients with schizophrenia (SZs). We identify six interpretable triplets of components, each of which consists of three associated components from the three modalities. Besides, components from these triplets that show significant group differences between the HCs and SZs are identified, which could be seen as putative biomarkers in schizophrenia.

Voxel-Wise Feature Selection Method for CNN Binary Classification of Neuroimaging Data

Voxel-wise group analysis is presented as a novel feature selection (FS) technique for a deep learning (DL) approach to brain imaging data classification. The method, based on a voxel-wise two-sample t-test and denoted as t-masking, is integrated into the learning procedure as a data-driven FS strategy. t-Masking has been introduced in a convolutional neural network (CNN) for the test bench of binary classification of very-mild Alzheimer’s disease vs. normal control, using a structural magnetic resonance imaging dataset of 180 subjects. To better characterize the t-masking impact on CNN classification performance, six different experimental configurations were designed. Moreover, the performances of the presented FS method were compared to those of similar machine learning (ML) models that relied on different FS approaches. Overall, our results show an enhancement of about 6% in performance when t-masking was applied. Moreover, the reported performance enhancement was higher with respect to similar FS-based ML models. In addition, evaluation of the impact of t-masking on various selection rates has been provided, serving as a useful characterization for future insights. The proposed approach is also highly generalizable to other DL architectures, neuroimaging modalities, and brain pathologies.

Normative Analysis of Individual Brain Differences Based on a Population MRI-Based Atlas of Cynomolgus Macaques.

The developmental trajectory of the primate brain varies substantially with aging across subjects. However, this ubiquitous variability between individuals in brain structure is difficult to quantify and has thus essentially been ignored. Based on a large-scale structural magnetic resonance imaging dataset acquired from 162 cynomolgus macaques, we create a species-specific 3D template atlas of the macaque brain, and deploy normative modeling to characterize individual variations of cortical thickness (CT) and regional gray matter volume (GMV). We observed an overall decrease in total GMV and mean CT, and an increase in white matter volume from juvenile to early adult. Specifically, CT and regional GMV were greater in prefrontal and temporal cortices relative to early unimodal areas. Age-dependent trajectories of thickness and volume for each cortical region revealed an increase in the medial temporal lobe, and decreases in all other regions. A low percentage of highly individualized deviations of CT and GMV were identified (0.0021%, 0.0043%, respectively, P < 0.05, false discovery rate [FDR]-corrected). Our approach provides a natural framework to parse individual neuroanatomical differences for use as a reference standard in macaque brain research, potentially enabling inferences regarding the degree to which behavioral or symptomatic variables map onto brain structure in future disease studies.

Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm.

ObjectiveAlthough distinctive structural abnormalities occur in patients with schizophrenia, detecting schizophrenia with magnetic resonance imaging (MRI) remains challenging. This study aimed to detect schizophrenia in structural MRI data sets using a trained deep learning algorithm.MethodFive public MRI data sets (BrainGluSchi, COBRE, MCICShare, NMorphCH, and NUSDAST) from schizophrenia patients and normal subjects, for a total of 873 structural MRI data sets, were used to train a deep convolutional neural network.ResultsThe deep learning algorithm trained with structural MR images detected schizophrenia in randomly selected images with reliable performance (area under the receiver operating characteristic curve [AUC] of 0.96). The algorithm could also identify MR images from schizophrenia patients in a previously unencountered data set with an AUC of 0.71 to 0.90. The deep learning algorithm’s classification performance degraded to an AUC of 0.71 when a new data set with younger patients and a shorter duration of illness than the training data sets was presented. The brain region contributing the most to the performance of the algorithm was the right temporal area, followed by the right parietal area. Semitrained clinical specialists hardly discriminated schizophrenia patients from healthy controls (AUC: 0.61) in the set of 100 randomly selected brain images.ConclusionsThe deep learning algorithm showed good performance in detecting schizophrenia and identified relevant structural features from structural brain MRI data; it had an acceptable classification performance in a separate group of patients at an earlier stage of the disease. Deep learning can be used to delineate the structural characteristics of schizophrenia and to provide supplementary diagnostic information in clinical settings.

The impact of hippocampal segmentation methods on correlations with clinical data.

In vivo measurement of hippocampal volume with magnetic resonance imaging (MRI) has become an important element in neuroimaging research. However, hippocampal volumetric findings and their relationship with cardiovascular risk factors and memory performance are still controversial and inconsistent for non-demented adults. To compare total and regional hippocampal volumes from manual tracing and automated Freesurfer segmentation methods and their relationship with mid-life clinical data and late-life verbal episodic memory performance in older women. This study used structural MRI datasets from 161 women who were scanned in 2012 and underwent neuropsychological assessments. Of these participants, 135 women had completed baseline measures of cardiovascular risk factors in 1992. Our results showed a significant correlation between manual tracing and automated Freesurfer output segmentations of total (r = 0.71), anterior (r = 0.65), and posterior (r = 0.38) hippocampal volumes. Mid-life Framingham Cardiovascular Risk Profile score is not associated with late-life hippocampal volumes, adjusted for intracranial volume, age, education, and apolipoprotein E gene ε4 status. Anterior hippocampal volume segmented either with manual tracing or automated Freesurfer software is sensitive to changes in mid-life high-density lipoprotein (HDL) cholesterol level, while posterior hippocampal volume is linked with verbal episodic memory performance in elderly women. These findings support the use of Freesurfer automated segmentation measures for large datasets as being highly correlated with the manual tracing method. In addition, our results suggest intervention strategies that target mid-life HDL cholesterol level in women.

Ventricular volumetry and free-water corrected diffusion tensor imaging of the anterior thalamic radiation in idiopathic normal pressure hydrocephalus

Background and purposeThe pathophysiology of idiopathic normal pressure hydrocephalus (iNPH) has not been completely clarified. We investigated the brain structure in iNPH using automatic ventricular volumetry, single-tensor diffusion tensor imaging (DTI) and bi-tensor free-water (FW) imaging analyses while focusing on cognitive impairments before and after lumboperitoneal shunt surgery. Materials and methodsThis retrospective study included 12 iNPH patients with structural magnetic resonance imaging (MRI) and diffusion MRI (dMRI) on a 3T-MRI scanner who underwent neuropsychological assessments before and after shunting and 8 healthy controls. Ventricular volumetry was conducted on structural MRI datasets using FreeSurfer. Ventricular volume was compared pre- and postoperatively. Correlation analyses were performed between ventricular volume or volume change and neuropsychological scores or score change. Tract-based spatial statistics were performed using dMRI datasets for group analyses between iNPH and controls and between pre- and post-surgery iNPH patients and for correlation analyses using neuropsychological scores. Tract-specific analyses were performed in the anterior thalamic radiation (ATR), followed by comparison and correlation analyses. ResultsThe third ventricular volume was significantly decreased after shunting; its volume reduction negatively correlated with a neuropsychological improvement. Compared with controls, iNPH patients had lower fractional anisotropy and higher axial, radial, and mean diffusivities, and FW in the periventricular white matter including ATR, resulting in no difference in FW-corrected indices. Single-tensor DTI indices partially correlated with neuropsychological improvements, while FW-corrected indices had no correlations. ConclusionThird ventricle enlargement is possibly linked to cognitive impairment and FW imaging possibly provides better white matter characterization in iNPH.

Revisiting subcortical brain volume correlates of autism in the ABIDE dataset: effects of age and sex.

Autism spectrum disorders (ASD) are characterized by substantial clinical, etiological and neurobiological heterogeneity. Despite this heterogeneity, previous imaging studies have highlighted the role of specific cortical and subcortical structures in ASD and have forwarded the notion of an ASD specific neuroanatomy in which abnormalities in brain structures are present that can be used for diagnostic classification approaches. A large (N = 859, 6-27 years, IQ 70-130) multi-center structural magnetic resonance imaging dataset was examined to specifically test ASD diagnostic effects regarding (sub)cortical volumes. Despite the large sample size, we found virtually no main effects of ASD diagnosis. Yet, several significant two- and three-way interaction effects of diagnosis by age by gender were found. The neuroanatomy of ASD does not exist, but is highly age and gender dependent. Implications for approaches of stratification of ASD into more homogeneous subtypes are discussed.

No Association between Cortical Gyrification or Intrinsic Curvature and Attention-deficit/Hyperactivity Disorder in Adolescents and Young Adults.

Magnetic resonance imaging (MRI) studies have highlighted subcortical, cortical, and structural connectivity abnormalities associated with attention-deficit/hyperactivity disorder (ADHD). Gyrification investigations of the cortex have been inconsistent and largely negative, potentially due to a lack of sensitivity of the previously used morphological parameters. The innovative approach of applying intrinsic curvature analysis, which is predictive of gyrification pattern, to the cortical surface applied herein allowed us greater sensitivity to determine whether the structural connectivity abnormalities thus far identified at a centimeter scale also occur at a millimeter scale within the cortical surface. This could help identify neurodevelopmental processes that contribute to ADHD. Structural MRI datasets from the NeuroIMAGE project were used [n = 306 ADHD, n = 164 controls, and n = 148 healthy siblings of individuals with ADHD (age in years, mean(sd); 17.2 (3.4), 16.8 (3.2), and 17.7 (3.8), respectively)]. Reconstructions of the cortical surfaces were computed with FreeSurfer. Intrinsic curvature (taken as a marker of millimeter-scale surface connectivity) and local gyrification index were calculated for each point on the surface (vertex) with Caret and FreeSurfer, respectively. Intrinsic curvature skew and mean local gyrification index were extracted per region; frontal, parietal, temporal, occipital, cingulate, and insula. A generalized additive model was used to compare the trajectory of these measures between groups over age, with sex, scanner site, total surface area of hemisphere, and familiality accounted for. After correcting for sex, scanner site, and total surface area no group differences were found in the developmental trajectory of intrinsic curvature or local gyrification index. Despite the increased sensitivity of intrinsic curvature, compared to gyrification measures, to subtle morphological abnormalities of the cortical surface we found no milimeter-scale connectivity abnormalities associated with ADHD.

Enhancing studies of the connectome in autism using the autism brain imaging data exchange II

The second iteration of the Autism Brain Imaging Data Exchange (ABIDE II) aims to enhance the scope of brain connectomics research in Autism Spectrum Disorder (ASD). Consistent with the initial ABIDE effort (ABIDE I), that released 1112 datasets in 2012, this new multisite open-data resource is an aggregate of resting state functional magnetic resonance imaging (MRI) and corresponding structural MRI and phenotypic datasets. ABIDE II includes datasets from an additional 487 individuals with ASD and 557 controls previously collected across 16 international institutions. The combination of ABIDE I and ABIDE II provides investigators with 2156 unique cross-sectional datasets allowing selection of samples for discovery and/or replication. This sample size can also facilitate the identification of neurobiological subgroups, as well as preliminary examinations of sex differences in ASD. Additionally, ABIDE II includes a range of psychiatric variables to inform our understanding of the neural correlates of co-occurring psychopathology; 284 diffusion imaging datasets are also included. It is anticipated that these enhancements will contribute to unraveling key sources of ASD heterogeneity.

In vivo quantification of amygdala subnuclei using 4.7 T fast spin echo imaging

The amygdala (AG) is an almond-shaped heterogeneous structure located in the medial temporal lobe. The majority of previous structural Magnetic Resonance Imaging (MRI) volumetric methods for AG measurement have so far only been able to examine this region as a whole. In order to understand the role of the AG in different neuropsychiatric disorders, it is necessary to understand the functional role of its subnuclei. The main goal of the present study was to develop a reliable volumetric method to delineate major AG subnuclei groups using ultra-high resolution high field MRI.38 healthy volunteers (15 males and 23 females, 21–60 years of age) without any history of medical or neuropsychiatric disorders were recruited for this study. Structural MRI datasets were acquired at 4.7 T Varian Inova MRI system using a fast spin echo (FSE) sequence.The AG was manually segmented into its five major anatomical subdivisions: lateral (La), basal (B), accessory basal (AB) nuclei, and cortical (Co) and centromedial (CeM) groups. Inter-(intra-) rater reliability of our novel volumetric method was assessed using intra-class correlation coefficient (ICC) and Dice's Kappa.Our results suggest that reliable measurements of the AG subnuclei can be obtained by image analysts with experience in AG anatomy. We provided a step-by-step segmentation protocol and reported absolute and relative volumes for the AG subnuclei. Our results showed that the basolateral (BLA) complex occupies seventy-eight percent of the total AG volume, while CeM and Co groups occupy twenty-two percent of the total AG volume. Finally, we observed no hemispheric effects and no gender differences in the total AG volume and the volumes of its subnuclei.Future applications of this method will help to understand the selective vulnerability of the AG subnuclei in neurological and psychiatric disorders.

Predicting obsessive–compulsive disorder severity combining neuroimaging and machine learning methods

BackgroundRecently, machine learning methods have been used to discriminate, on an individual basis, patients from healthy controls through brain structural magnetic resonance imaging (MRI). However, the application of these methods to predict the severity of psychiatric symptoms is less common. MethodsHerein, support vector regression (SVR) was employed to evaluate whether gray matter volumes encompassing cortical–subcortical loops contain discriminative information to predict obsessive–compulsive disorder (OCD) symptom severity in 37 treatment-naïve adult OCD patients. ResultsThe Pearson correlation coefficient between predicted and observed symptom severity scores was 0.49 (p=0.002) for total Dimensional Yale-Brown Obsessive–Compulsive Scale (DY-BOCS) and 0.44 (p=0.006) for total Yale-Brown Obsessive–Compulsive Scale (Y-BOCS). The regions that contained the most discriminative information were the left medial orbitofrontal cortex and the left putamen for both scales. LimitationsOur sample is relatively small and our results must be replicated with independent and larger samples. ConclusionsThese results indicate that machine learning methods such as SVR analysis may identify neurobiological markers to predict OCD symptom severity based on individual structural MRI datasets.