Dataset Information

Resting-state magnetoencephalography source magnitude imaging with deep-learning neural network for classification of symptomatic combat-related mild traumatic brain injury.

ABSTRACT: Combat-related mild traumatic brain injury (cmTBI) is a leading cause of sustained physical, cognitive, emotional, and behavioral disabilities in Veterans and active-duty military personnel. Accurate diagnosis of cmTBI is challenging since the symptom spectrum is broad and conventional neuroimaging techniques are insensitive to the underlying neuropathology. The present study developed a novel deep-learning neural network method, 3D-MEGNET, and applied it to resting-state magnetoencephalography (rs-MEG) source-magnitude imaging data from 59 symptomatic cmTBI individuals and 42 combat-deployed healthy controls (HCs). Analytic models of individual frequency bands and all bands together were tested. The All-frequency model, which combined delta-theta (1-7 Hz), alpha (8-12 Hz), beta (15-30 Hz), and gamma (30-80 Hz) frequency bands, outperformed models based on individual bands. The optimized 3D-MEGNET method distinguished cmTBI individuals from HCs with excellent sensitivity (99.9 ± 0.38%) and specificity (98.9 ± 1.54%). Receiver-operator-characteristic curve analysis showed that diagnostic accuracy was 0.99. The gamma and delta-theta band models outperformed alpha and beta band models. Among cmTBI individuals, but not controls, hyper delta-theta and gamma-band activity correlated with lower performance on neuropsychological tests, whereas hypo alpha and beta-band activity also correlated with lower neuropsychological test performance. This study provides an integrated framework for condensing large source-imaging variable sets into optimal combinations of regions and frequencies with high diagnostic accuracy and cognitive relevance in cmTBI. The all-frequency model offered more discriminative power than each frequency-band model alone. This approach offers an effective path for optimal characterization of behaviorally relevant neuroimaging features in neurological and psychiatric disorders.

SUBMITTER: Huang MX

PROVIDER: S-EPMC8046098 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundDementia and mild cognitive impairment are characterised by symptoms of cognitive decline, which are typically assessed using neuropsychological assessments (NPAs), such as the Mini-Mental State Examination (MMSE) and Frontal Assessment Battery (FAB). Magnetoencephalography (MEG) is a novel clinical assessment technique that measures brain activities (summarised as oscillatory parameters), which are associated with symptoms of cognitive impairment. However, the relevance of MEG and regional cerebral blood flow (rCBF) data obtained using single-photon emission computed tomography (SPECT) has not been examined using clinical datasets. Therefore, this study aimed to investigate the relationships among MEG oscillatory parameters, clinically validated biomarkers computed from rCBF, and NPAs using outpatient data retrieved from hospital records.MethodsClinical data from 64 individuals with mixed pathological backgrounds were retrieved and analysed. MEG oscillatory parameters, including relative power (RP) from delta to high gamma bands, mean frequency, individual alpha frequency, and Shannon's spectral entropy, were computed for each cortical region. For SPECT data, three pathological parameters-'severity', 'extent', and 'ratio'-were computed using an easy z-score imaging system (eZIS). As for NPAs, the MMSE and FAB scores were retrieved.ResultsMEG oscillatory parameters were correlated with eZIS parameters. The eZIS parameters associated with Alzheimer's disease pathology were reflected in theta power augmentation and slower shift of the alpha peak. Moreover, MEG oscillatory parameters were found to reflect NPAs. Global slowing and loss of diversity in neural oscillatory components correlated with MMSE and FAB scores, whereas the associations between eZIS parameters and NPAs were sparse.ConclusionMEG oscillatory parameters correlated with both SPECT (i.e. eZIS) parameters and NPAs, supporting the clinical validity of MEG oscillatory parameters as pathological and symptomatic indicators. The findings indicate that various components of MEG oscillatory characteristics can provide valuable pathological and symptomatic information, making MEG data a rich resource for clinical examinations of patients with cognitive impairments. SPECT (i.e. eZIS) parameters showed no correlations with NPAs. The results contributed to a better understanding of the characteristics of electrophysiological and pathological examinations for patients with cognitive impairments, which will help to facilitate their co-use in clinical application, thereby improving patient care.

Project description:ObjectiveTo evaluate whether diffusion tensor imaging (DTI) will noninvasively reveal white matter changes not present on conventional MRI in acute blast-related mild traumatic brain injury (mTBI) and to determine correlations with clinical measures and recovery.MethodsProspective observational study of 95 US military service members with mTBI enrolled within 7 days from injury in Afghanistan and 101 healthy controls. Assessments included Rivermead Post-Concussion Symptoms Questionnaire (RPCSQ), Post-Traumatic Stress Disorder Checklist Military (PCLM), Beck Depression Inventory (BDI), Balance Error Scoring System (BESS), Automated Neuropsychological Assessment Metrics (ANAM), conventional MRI, and DTI.ResultsSignificantly greater impairment was observed in participants with mTBI vs controls: RPCSQ (19.7 ± 12.9 vs 3.6 ± 7.1, p < 0.001), PCLM (32 ± 13.2 vs 20.9 ± 7.1, p < 0.001), BDI (7.4 ± 6.8 vs 2.5 ± 4.9, p < 0.001), and BESS (18.2 ± 8.4 vs 15.1 ± 8.3, p = 0.01). The largest effect size in ANAM performance decline was in simple reaction time (mTBI 74.5 ± 148.4 vs control -11 ± 46.6 milliseconds, p < 0.001). Fractional anisotropy was significantly reduced in mTBI compared with controls in the right superior longitudinal fasciculus (0.393 ± 0.022 vs 0.405 ± 0.023, p < 0.001). No abnormalities were detected with conventional MRI. Time to return to duty correlated with RPCSQ (r = 0.53, p < 0.001), ANAM simple reaction time decline (r = 0.49, p < 0.0001), PCLM (r = 0.47, p < 0.0001), and BDI (r = 0.36 p = 0.0005).ConclusionsSomatic, behavioral, and cognitive symptoms and performance deficits are substantially elevated in acute blast-related mTBI. Postconcussive symptoms and performance on measures of posttraumatic stress disorder, depression, and neurocognitive performance at initial presentation correlate with return-to-duty time. Although changes in fractional anisotropy are uncommon and subtle, DTI is more sensitive than conventional MRI in imaging white matter integrity in blast-related mTBI acutely.

Project description:ObjectiveThe purpose of this study was to develop an algorithm incorporating MRI metrics to classify patients with mild traumatic brain injury (mTBI) and controls.MethodsThis was an institutional review board-approved, Health Insurance Portability and Accountability Act-compliant prospective study. We recruited patients with mTBI and healthy controls through the emergency department and general population. We acquired data on a 3.0T Siemens Trio magnet including conventional brain imaging, resting-state fMRI, diffusion-weighted imaging, and magnetic field correlation (MFC), and performed multifeature analysis using the following MRI metrics: mean kurtosis (MK) of thalamus, MFC of thalamus and frontal white matter, thalamocortical resting-state networks, and 5 regional gray matter and white matter volumes including the anterior cingulum and left frontal and temporal poles. Feature selection was performed using minimal-redundancy maximal-relevance. We used classifiers including support vector machine, naive Bayesian, Bayesian network, radial basis network, and multilayer perceptron to test maximal accuracy.ResultsWe studied 24 patients with mTBI and 26 controls. Best single-feature classification uses thalamic MK yielding 74% accuracy. Multifeature analysis yields 80% accuracy using the full feature set, and up to 86% accuracy using minimal-redundancy maximal-relevance feature selection (MK thalamus, right anterior cingulate volume, thalamic thickness, thalamocortical resting-state network, thalamic microscopic MFC, and sex).ConclusionMultifeature analysis using diffusion-weighted imaging, MFC, fMRI, and volumetrics may aid in the classification of patients with mTBI compared with controls based on optimal feature selection and classification methods.Classification of evidenceThis study provides Class III evidence that classification algorithms using multiple MRI features accurately identifies patients with mTBI as defined by American Congress of Rehabilitation Medicine criteria compared with healthy controls.

Dataset Information

Resting-state magnetoencephalography source magnitude imaging with deep-learning neural network for classification of symptomatic combat-related mild traumatic brain injury.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets