Identification of chronic mild traumatic brain injury using resting state functional MRI and machine learning techniques

Machine Learning Approaches to Identify Affected Brain Regions in Movement Disorders Using MRI Data: A Systematic Review and Diagnostic Meta-analysis

BACKGROUND

Movement disorders such as Parkinson's disease are associated with structural and functional changes in specific brain regions. Advanced magnetic resonance imaging (MRI) techniques combined with machine learning (ML) are promising tools for identifying imaging biomarkers and patterns associated with these disorders.

PURPOSE/HYPOTHESIS

We aimed to systematically identify the brain regions most commonly affected in movement disorders using ML approaches applied to structural and functional MRI data. We searched the PubMed and Scopus databases using relevant keywords up to June 2023 for studies that used ML approaches to detect brain regions associated with movement disorders using MRI data.

STUDY TYPE

A systematic review and diagnostic meta-analysis.

POPULATION/SUBJECTS

Sixty-seven studies with 6,285 patients were included.

FIELD STRENGTH/SEQUENCE

Studies utilizing 1.5T or 3T MR scanners and the acquisition of diffusion tensor imaging (DTI), structural MRI (sMRI), functional MRI (fMRI), or a combination of these were included.

ASSESSMENT

The authors independently assessed the study quality using the CLAIM and QUADAS-2 criteria and extracted data on diagnostic accuracy measures.

STATISTICAL TESTS

Sensitivity, specificity, accuracy, and area under the curve were pooled using random-effects models. Q statistics and the I2 index were used to evaluate heterogeneity, and Begg's funnel plot was used to identify publication bias.

RESULTS

sMRI showed the highest sensitivity (93%) and mixed modalities had the highest specificity (90%) for detecting regional abnormalities. sMRI had a 94% sensitivity for identifying subcortical changes. The support vector machine (93%) and logistic regression (91%) models exhibited high diagnostic accuracies.

DATA CONCLUSION

The combination of advanced MR neuroimaging techniques and ML is a promising approach for identifying brain biomarkers and affected regions in movement disorders with subcortical structures frequently implicated. Structural MRI, in particular, showed strong performance.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 2.

Electroencephalography connectome changes in chronic insomnia disorder are correlated with neurochemical signatures

STUDY OBJECTIVES

This study aimed to investigate the alterations in resting-state electroencephalography (EEG) global brain connectivity (GBC) in patients with chronic insomnia disorder (CID) and to explore the correlation between macroscale connectomic variances and microscale neurotransmitter distributions.

METHODS

We acquired 64-channel EEG from 35 female CID patients and 34 healthy females. EEG signals were source-localized using individual brain anatomy and orthogonalized to mitigate volume conduction. Correlation coefficients between band-limited source-space power envelopes of the DK 68 atlas were computed and averaged across regions to determine specific GBC values. A support vector machine (SVM) classifier utilizing GBC features was employed to differentiate CID patients from controls. We further used Neurosynth and a 3D atlas of neurotransmitter receptors/transporters to assess the cognitive functions and neurotransmitter landscape associated with CID cortical abnormality maps, respectively.

RESULTS

CID patients exhibited elevated GBC within the medial prefrontal cortex and limbic cortex, particularly at the gamma carrier frequency, compared to controls (pFDR < .05). GBC patterns were found to effectively distinguish CID patients from controls with a precision of 90.8% in the SVM model. The cortical abnormality maps were significantly correlated with meta-analytic terms like "cognitive control" and "emotion regulation." Notably, GBC patterns were associated with neurotransmitter profiles (pspin < .05), with neurotransmitter systems such as norepinephrine, dopamine, and serotonin making significant contributions.

CONCLUSIONS

This work characterizes the EEG connectomic profile of CID, facilitating the cost-effective clinical translation of EEG-derived markers. Additionally, the linkage between GBC patterns and neurotransmitter distribution offers promising avenues for developing targeted treatment strategies for CID.

Repetitive mild closed-head injury induced synapse loss and increased local BOLD-fMRI signal homogeneity

Repeated mild head injuries due to sports, or domestic violence and military service are increasingly linked to debilitating symptoms in the long term. Although symptoms may take decades to manifest, potentially treatable neurobiological alterations must begin shortly after injury. Better means to diagnose and treat traumatic brain injuries, requires an improved understanding of the mechanisms underlying progression and means through which they can be measured. Here, we employ a repetitive mild closed-head injury (rmTBI) and chronic variable stress (CVS) mouse model to investigate emergent structural and functional brain abnormalities. Brain imaging is achieved with [ 18 F]SynVesT-1 positron emission tomography, with the synaptic vesicle glycoprotein 2A ligand marking synapse density and BOLD (blood-oxygen-level-dependent) functional magnetic resonance imaging (fMRI). Animals were scanned six weeks after concluding rmTBI/Stress procedures. Injured mice showed widespread decreases in synaptic density coupled with an i ncrease in local BOLD-fMRI synchrony detected as regional homogeneity. Injury-affected regions with higher synapse density showed a greater increase in fMRI regional homogeneity. Taken together, these observations may reflect compensatory mechanisms following injury. Multimodal studies are needed to provide deeper insights into these observations.

Adaptive Feature Medical Segmentation Network: an adaptable deep learning paradigm for high-performance 3D brain lesion segmentation in medical imaging

Introduction

In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic.

Methods

We introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability.

Results

AFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision.

Discussion

The proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing.

Long Noncoding RNA VLDLR-AS1 Levels in Serum Correlate with Combat-Related Chronic Mild Traumatic Brain Injury and Depression Symptoms in US Veterans

More than 75% of traumatic brain injuries (TBIs) are mild (mTBI) and military service members often experience repeated combat-related mTBI. The chronic comorbidities concomitant with repetitive mTBI (rmTBI) include depression, post-traumatic stress disorder or neurological dysfunction. This study sought to determine a long noncoding RNA (lncRNA) expression signature in serum samples that correlated with rmTBI years after the incidences. Serum samples were obtained from Long-Term Impact of Military-Relevant Brain-Injury Consortium Chronic Effects of Neurotrauma Consortium (LIMBIC CENC) repository, from participants unexposed to TBI or who had rmTBI. Four lncRNAs were identified as consistently present in all samples, as detected via droplet digital PCR and packaged in exosomes enriched for CNS origin. The results, using qPCR, demonstrated that the lncRNA VLDLR-AS1 levels were significantly lower among individuals with rmTBI compared to those with no lifetime TBI. ROC analysis determined an AUC of 0.74 (95% CI: 0.6124 to 0.8741; p = 0.0012). The optimal cutoff for VLDLR-AS1 was ≤153.8 ng. A secondary analysis of clinical data from LIMBIC CENC was conducted to evaluate the psychological symptom burden, and the results show that lncRNAs VLDLR-AS1 and MALAT1 are correlated with symptoms of depression. In conclusion, lncRNA VLDLR-AS1 may serve as a blood biomarker for identifying chronic rmTBI and depression in patients.

Deep learning-based multimodality classification of chronic mild traumatic brain injury using resting-state functional MRI and PET imaging

Mild traumatic brain injury (mTBI) is a public health concern. The present study aimed to develop an automatic classifier to distinguish between patients with chronic mTBI (n = 83) and healthy controls (HCs) (n = 40). Resting-state functional MRI (rs-fMRI) and positron emission tomography (PET) imaging were acquired from the subjects. We proposed a novel deep-learning-based framework, including an autoencoder (AE), to extract high-level latent and rectified linear unit (ReLU) and sigmoid activation functions. Single and multimodality algorithms integrating multiple rs-fMRI metrics and PET data were developed. We hypothesized that combining different imaging modalities provides complementary information and improves classification performance. Additionally, a novel data interpretation approach was utilized to identify top-performing features learned by the AEs. Our method delivered a classification accuracy within the range of 79-91.67% for single neuroimaging modalities. However, the performance of classification improved to 95.83%, thereby employing the multimodality model. The models have identified several brain regions located in the default mode network, sensorimotor network, visual cortex, cerebellum, and limbic system as the most discriminative features. We suggest that this approach could be extended to the objective biomarkers predicting mTBI in clinical settings.

Treatment effects of N-acetyl cysteine on resting-state functional MRI and cognitive performance in patients with chronic mild traumatic brain injury: a longitudinal study

Mild traumatic brain injury (mTBI) is a significant public health concern, specially characterized by a complex pattern of abnormal neural activity and functional connectivity. It is often associated with a broad spectrum of short-term and long-term cognitive and behavioral symptoms including memory dysfunction, headache, and balance difficulties. Furthermore, there is evidence that oxidative stress significantly contributes to these symptoms and neurophysiological changes. The purpose of this study was to assess the effect of N-acetylcysteine (NAC) on brain function and chronic symptoms in mTBI patients. Fifty patients diagnosed with chronic mTBI participated in this study. They were categorized into two groups including controls (CN, n = 25), and patients receiving treatment with N-acetyl cysteine (NAC, n = 25). NAC group received 50 mg/kg intravenous (IV) medication once a day per week. In the rest of the week, they took one 500 mg NAC tablet twice per day. Each patient underwent rs-fMRI scanning at two timepoints including the baseline and 3 months later at follow-up, while the NAC group received a combination of oral and IV NAC over that time. Three rs-fMRI metrics were measured including fractional amplitude of low frequency fluctuations (fALFF), degree centrality (DC), and functional connectivity strength (FCS). Neuropsychological tests were also assessed at the same day of scanning for each patient. The alteration of rs-fMRI metrics and cognitive scores were measured over 3 months treatment with NAC. Then, the correlation analysis was executed to estimate the association of rs-fMRI measurements and cognitive performance over 3 months (p < 0.05). Two significant group-by-time effects demonstrated the changes of rs-fMRI metrics particularly in the regions located in the default mode network (DMN), sensorimotor network, and emotional circuits that were significantly correlated with cognitive function recovery over 3 months treatment with NAC (p < 0.05). NAC appears to modulate neural activity and functional connectivity in specific brain networks, and these changes could account for clinical improvement. This study confirmed the short-term therapeutic efficacy of NAC in chronic mTBI patients that may contribute to understanding of neurophysiological effects of NAC in mTBI. These findings encourage further research on long-term neurobehavioral assessment of NAC assisting development of therapeutic plans in mTBI.