Structural Magnetic Resonance Imaging Features Research Articles

Correlations between Immunoinflammatory Factor Levels and Cognitive Functions and Brain Structural Magnetic Resonance Imaging Features among Patients with Primary Schizophrenia.

Schizophrenia is associated with significant cognitive impairment. However, the pathophysiological mechanisms underlying cognitive dysfunction in schizophrenia remain unclear. Based on the latest concept of cognition, immunoinflammatory factors and structural magnetic resonance imaging (sMRI) features of the brain are considered markers of schizophrenia. This study explored the correlations between cognitive function and immunoinflammatory factors and sMRI in primary schizophrenia patients. Non-interventional cross-sectional study was conducted, including 21 patients with primary schizophrenia, who were identified based on the Diagnostic and Statistical Manual, Fifth Edition (DSM-V) and grouped under the observation group. Thirty healthy volunteers with age, gender, hand dominance, and education duration matched with those of the primary schizophrenia patients were recruited to the control group. All subjects underwent sMRI examination. MATRICS consensus cognitive battery (MCCB) was employed to assess the cognitive functions among patients with primary schizophrenia. The levels of serum amyloid A (SAA), monocyte chemoattractant protein 1 (MCP-1), and chitinase-3-like protein 1 (YKL-40) were measured by means of enzyme-linked immunosorbent assay (ELISA). Pearson's correlation analysis was carried out to analyze the correlation between immunoinflammatory factor levels and cognitive functions as well as brain sMRI features. The scores for all MCCB items and the total score for the observation group were apparently lower than those for the control group (p < 0.001), while the YKL-40 and SAA levels were notably higher in the observation group (t = 3.406, p < 0.05; t = 5.656, p < 0.001). Compared to the control group, the observation group exhibited reduced volumes of left and right insular lobes, left and right anterior cingulate cortexes, left and right hippocampi, right parahippocampal gyrus, right amygdala, left inferior occipital lobe, left superior temporal lobe, left temporal pole, and left middle and inferior temporal lobes (p < 0.001). The levels of YKL-40 and SAA were both negatively correlated with MCCB score (r = -0.3668, p = 0.004; r = -0.8495, p < 0.001). The volumes of right insular lobe, left and right anterior cingulate cortexes, right parahippocampal gyrus, right amygdala, and gray matter in left middle temporal lobe were all negatively correlated with the levels of YKL-40 and SAA (p < 0.05). Cognitive impairment in patients with primary schizophrenia is associated with increased serum SAA and YKL-40 levels and decreased gray matter volume.

Machine Learning Models for Diagnosis of Parkinson's Disease Using Multiple Structural Magnetic Resonance Imaging Features.

PurposeThis study aimed to develop machine learning models for the diagnosis of Parkinson’s disease (PD) using multiple structural magnetic resonance imaging (MRI) features and validate their performance.MethodsBrain structural MRI scans of 60 patients with PD and 56 normal controls (NCs) were enrolled as development dataset and 69 patients with PD and 71 NCs from Parkinson’s Progression Markers Initiative (PPMI) dataset as independent test dataset. First, multiple structural MRI features were extracted from cerebellar, subcortical, and cortical regions of the brain. Then, the Pearson’s correlation test and least absolute shrinkage and selection operator (LASSO) regression were used to select the most discriminating features. Finally, using logistic regression (LR) classifier with the 5-fold cross-validation scheme in the development dataset, the cerebellar, subcortical, cortical, and a combined model based on all features were constructed separately. The diagnostic performance and clinical net benefit of each model were evaluated with the receiver operating characteristic (ROC) analysis and the decision curve analysis (DCA) in both datasets.ResultsAfter feature selection, 5 cerebellar (absolute value of left lobule crus II cortical thickness (CT) and right lobule IV volume, relative value of right lobule VIIIA CT and lobule VI/VIIIA gray matter volume), 3 subcortical (asymmetry index of caudate volume, relative value of left caudate volume, and absolute value of right lateral ventricle), and 4 cortical features (local gyrification index of right anterior circular insular sulcus and anterior agranular insula complex, local fractal dimension of right middle insular area, and CT of left supplementary and cingulate eye field) were selected as the most distinguishing features. The area under the curve (AUC) values of the cerebellar, subcortical, cortical, and combined models were 0.679, 0.555, 0.767, and 0.781, respectively, for the development dataset and 0.646, 0.632, 0.690, and 0.756, respectively, for the independent test dataset, respectively. The combined model showed higher performance than the other models (Delong’s test, all p-values < 0.05). All models showed good calibration, and the DCA demonstrated that the combined model has a higher net benefit than other models.ConclusionThe combined model showed favorable diagnostic performance and clinical net benefit and had the potential to be used as a non-invasive method for the diagnosis of PD.

Machine Learning Prediction of Treatment Outcome in Late-Life Depression.

Background: Recent evidence suggests that integration of multi-modal data improves performance in machine learning prediction of depression treatment outcomes. Here, we compared the predictive performance of three machine learning classifiers using differing combinations of sociodemographic characteristics, baseline clinical self-reports, cognitive tests, and structural magnetic resonance imaging (MRI) features to predict treatment outcomes in late-life depression (LLD).Methods: Data were combined from two clinical trials conducted with depressed adults aged 60 and older, including response to escitalopram (N = 32, NCT01902004) and Tai Chi (N = 35, NCT02460666). Remission was defined as a score of 6 or less on the 24-item Hamilton Rating Scale for Depression (HAMD) at the end of 24 weeks of treatment. Features subsets were constructed from baseline sociodemographic and clinical features, gray matter volumes (GMVs), or both. Three classification algorithms were compared: (1) Support Vector Machine-Radial Bias Function (SVMRBF), (2) Random Forest (RF), and (3) Logistic Regression (LR). A repeated 5-fold cross-validation approach with a wrapper-based feature selection method was used for model fitting. Model performance metrics included Area under the ROC Curve (AUC) and Matthews correlation coefficient (MCC). Cross-validated performance significance was tested by permutation analysis. Classifiers were compared by Cochran's Q and post-hoc pairwise comparisons using McNemar's Chi-Square test with Bonferroni correction.Results: For the RF and SVMRBF algorithms, the combined feature set outperformed the clinical and GMV feature sets with a final cross-validated AUC of 0.83 ± 0.11 and 0.80 ± 0.11, respectively. Both classifiers passed permutation analysis. The LR algorithm performed best using GMV features alone (AUC 0.79 ± 0.14) but failed to pass permutation analysis using any feature set. Performance of the three classifiers differed significantly for all three features sets. Important predictive features of treatment response included anterior and posterior cingulate volumes, depression characteristics, and self-reported health-related quality scores.Conclusion: This preliminary exploration into the use of ML and multi-modal data to identify predictors of general treatment response in LLD indicates that integration of clinical and structural MRI features significantly increases predictive capability. Identified features are among those previously implicated in geriatric depression, encouraging future work in this arena.

Two-Year Changes in Magnetic Resonance Imaging Features and Pain in Thumb Base Osteoarthritis.

ObjectiveTo investigate the two‐year course of pain and osteoarthritic features on magnetic resonance imaging (MRI) in the thumb base.MethodsPatients in the Hand Osteoarthritis in Secondary Care (HOSTAS) cohort who had received radiographic examination, MRI, and clinical examination of the right thumb base at baseline and who had a 2‐year follow‐up period were studied. Pain on palpation of the thumb base was assessed on a 0–3 scale. MRIs were analyzed with the Outcome Measures in Rheumatology (OMERACT) thumb base osteoarthritis MRI scoring system for synovitis, bone marrow lesions (BMLs), subchondral bone defects, cartilage space loss, osteophytes, and subluxation. Radiographs were assessed for osteophytes and joint space narrowing. We studied the associations of changes in synovitis and BMLs with changes in pain using a logistic regression model adjusted for radiographic damage, with values expressed as odds ratios (ORs) and 95% confidence intervals (95% CIs).ResultsOf 165 patients, 83% were women and the mean age was 60.7 years. At baseline, 65 patients had thumb base pain. At 2‐year follow‐up, pain had decreased in 32 patients and increased in 33 patients. MRI features remained stable in most patients. Structural MRI features generally deteriorated, while synovitis and BMLs improved in some individuals and deteriorated in others. Change in radiographic osteophytes rarely occurred (n = 10). Increased synovitis (odds ratio [OR] 3.4 [95% CI 1.3–9.3]) and increased BMLs (OR 5.1 [95% CI 2.1–12.6]) were associated with increased pain. Decreased BMLs appeared to be associated with decreased pain (OR 2.7 [95% CI 0.8–8.9]), and reductions in synovitis occurred too infrequently to calculate associations.ConclusionOver 2 years, thumb base pain fluctuated, while MRI features changed in a minority of patients with hand osteoarthritis. Changes in synovitis and BMLs were associated with changes in pain on palpation, even after adjustment for radiographic damage.

Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features.

Autism spectrum disorder (ASD) is characterized by a spectrum of social and communication impairments and rigid and stereotyped behaviors that have a neurodevelopmental origin. Although many imaging studies have reported structural and functional alterations in multiple brain regions, clinically useful diagnostic imaging biomarkers for ASD remain unavailable. In this study, we applied machine learning (ML) models to regional volumetric and cortical thickness data from the largest structural magnetic resonance imaging (sMRI) dataset available from the Enhancing Neuro Imaging Genetics Through Meta-Analysis (ENIGMA) consortium (1833 subjects with ASD and 1838 without ASD; age range: 1.5-64; average age: 15.6; male/female ratio: 4.2:1). The highest classification accuracy on a hold-out test set was achieved using a stacked Extra Tree Classifier. The area under the receiver operating characteristic (ROC) curve (AUC) was 0.62 (95% confidence interval [CI]: 0.57, 0.68) and the area under the precision-recall curve was 0.58. Learning curve analysis showed the good fit of the model and suggests that more training examples will not likely benefit model performance. Our results suggest that sMRI volumetric and cortical thickness data alone may not provide clinically sufficient useful diagnostic biomarkers for ASD. Developing clinically useful imaging classifiers for ASD will benefit from combining other data modalities or feature types, such as functional MRI data and raw images that can leverage other machine learning (ML) techniques such as convolutional neural networks.

Biomarker Extraction Based on Subspace Learning for the Prediction of Mild Cognitive Impairment Conversion.

Accurate recognition of progressive mild cognitive impairment (MCI) is helpful to reduce the risk of developing Alzheimer's disease (AD). However, it is still challenging to extract effective biomarkers from multivariate brain structural magnetic resonance imaging (MRI) features to accurately differentiate the progressive MCI from stable MCI. We develop novel biomarkers by combining subspace learning methods with the information of AD as well as normal control (NC) subjects for the prediction of MCI conversion using multivariate structural MRI data. Specifically, we first learn two projection matrices to map multivariate structural MRI data into a common label subspace for AD and NC subjects, where the original data structure and the one-to-one correspondence between multiple variables are kept as much as possible. Afterwards, the multivariate structural MRI features of MCI subjects are mapped into a common subspace according to the projection matrices. We then perform the self-weighted operation and weighted fusion on the features in common subspace to extract the novel biomarkers for MCI subjects. The proposed biomarkers are tested on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Experimental results indicate that our proposed biomarkers outperform the competing biomarkers on the discrimination between progressive MCI and stable MCI. And the improvement from the proposed biomarkers is not limited to a particular classifier. Moreover, the results also confirm that the information of AD and NC subjects is conducive to predicting conversion from MCI to AD. In conclusion, we find a good representation of brain features from high-dimensional MRI data, which exhibits promising performance for predicting conversion from MCI to AD.

Node Centrality Measures Identify Relevant Structural MRI Features of Subjects with Autism.

Autism spectrum disorders (ASDs) are a heterogeneous group of neurodevelopmental conditions characterized by impairments in social interaction and communication and restricted patterns of behavior, interests, and activities. Although the etiopathogenesis of idiopathic ASD has not been fully elucidated, compelling evidence suggests an interaction between genetic liability and environmental factors in producing early alterations of structural and functional brain development that are detectable by magnetic resonance imaging (MRI) at the group level. This work shows the results of a network-based approach to characterize not only variations in the values of the extracted features but also in their mutual relationships that might reflect underlying brain structural differences between autistic subjects and healthy controls. We applied a network-based analysis on sMRI data from the Autism Brain Imaging Data Exchange I (ABIDE-I) database, containing 419 features extracted with FreeSurfer software. Two networks were generated: one from subjects with autistic disorder (AUT) (DSM-IV-TR), and one from typically developing controls (TD), adopting a subsampling strategy to overcome class imbalance (235 AUT, 418 TD). We compared the distribution of several node centrality measures and observed significant inter-class differences in averaged centralities. Moreover, a single-node analysis allowed us to identify the most relevant features that distinguished the groups.

Patellofemoral alignment, morphology and structural features are not related to sitting pain in individuals with patellofemoral pain

BackgroundSitting-related pain is a common feature of patellofemoral pain (PFP). However, little is known regarding features associated with sitting-related PFP. The aim of this study was to determine whether sitting-related PFP is associated with patellofemoral alignment, morphology and structural magnetic resonance imaging (MRI) features of the patellofemoral joint (cartilage lesions, bone marrow lesions, fat pad synovitis). Methods133 individuals with PFP were included from two unique but similar cohorts. Participants were classified into one of three groups based on their response to item 8 of the Anterior Knee Pain Scale: (i) problems with sitting; (ii) sitting pain after exercise; and (iii) no difficulty with sitting. All participants underwent 3T Magnetic Resonance Imaging (MRI) to enable: (i) scoring of structural features of the patellofemoral joint with MRI Osteoarthritis Knee Score (MOAKS); and (ii) patellofemoral alignment and morphology measurements using standardised methods. The association of sitting pain to bony alignment, morphology and MOAKS features were evaluated using multinomial logistic regression (adjusted for age, sex, BMI; reference group = no difficulty with sitting). Results82 (61.7%) participants reported problems with sitting, and 24 (18%) participants reported sitting pain after exercise. There were no significant associations between the presence of sitting pain and any morphology, alignment or structural characteristics. ConclusionsFindings indicate that PFP related to sitting is not associated with patellofemoral alignment, morphology, or structural MRI features of the patellofemoral joint. Further research to determine mechanisms of sitting-related PFP, and inform targeted treatments, are required.

Cognitive and structural magnetic resonance imaging features of Lewy body dementia and Alzheimer's disease

To assess medial temporal atrophy (MTA) and atrophy adjacent to the third ventricle (Peri-IIIVent) on brain magnetic resonance images as biomarkers for the diagnosis of Alzheimer's disease (AD) and Lewy body dementia (LBD), and to assess the relationship between biomarkers and clinical and functional measures. Subjects diagnosed with no cognitive impairment (n = 30), AD (n = 30), or LBD (n = 31) were evaluated with the Mini-Mental State Examination, Multiple Delayed Recall Test, Category Fluency Test, Clinical Dementia Rating Sum of Boxes score, Functional Assessment Questionnaire, and the Unified Parkinson's Disease Rating Scale. A validated visual rating system was used to rate MTA, and volumetric studies were performed to measure total intracranial and hippocampal volumes. Additionally, linear measurements of third ventricle width, Peri-IIIVent height, and Peri-IIIVent width were performed. Subjects with AD and those with LBD were equivalent with respect to age and levels of cognitive impairment. Atrophy in medial temporal and Peri-IIIVent regions was greater among both patients with AD and those with LBD compared with subjects with no cognitive impairment. The best discriminators of AD from LBD were the severity of MTA, using visual rating, and the severity of memory impairment. Only subjects with LBD showed significant correlations between Unified Parkinson's Disease Rating Scale scores and Peri-IIIVent atrophy measures. Mild AD could be distinguished from mild LBD by the severity of MTA and memory impairment. The severity of parkinsonism was associated with the severity of atrophy in the third ventricular region, but was not a good discriminator between AD and LBD.