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

Synaptic Plasticity in the Injured Brain Depends on the Temporal Pattern of Stimulation

Neurostimulation protocols are increasingly used as therapeutic interventions, including for brain injury. In addition to the direct activation of neurons, these stimulation protocols are also likely to have downstream effects on those neurons' synaptic outputs. It is well known that alterations in the strength of synaptic connections (long-term potentiation, LTP; long-term depression, LTD) are sensitive to the frequency of stimulation used for induction; however, little is known about the contribution of the temporal pattern of stimulation to the downstream synaptic plasticity that may be induced by neurostimulation in the injured brain. We explored interactions of the temporal pattern and frequency of neurostimulation in the normal cerebral cortex and after mild traumatic brain injury (mTBI), to inform therapies to strengthen or weaken neural circuits in injured brains, as well as to better understand the role of these factors in normal brain plasticity. Whole-cell (WC) patch-clamp recordings of evoked postsynaptic potentials in individual neurons, as well as field potential (FP) recordings, were made from layer 2/3 of visual cortex in response to stimulation of layer 4, in acute slices from control (naive), sham operated, and mTBI rats. We compared synaptic plasticity induced by different stimulation protocols, each consisting of a specific frequency (1 Hz, 10 Hz, or 100 Hz), continuity (continuous or discontinuous), and temporal pattern (perfectly regular, slightly irregular, or highly irregular). At the individual neuron level, dramatic differences in plasticity outcome occurred when the highly irregular stimulation protocol was used at 1 Hz or 10 Hz, producing an overall LTD in controls and shams, but a robust overall LTP after mTBI. Consistent with the individual neuron results, the plasticity outcomes for simultaneous FP recordings were similar, indicative of our results generalizing to a larger scale synaptic network than can be sampled by individual WC recordings alone. In addition to the differences in plasticity outcome between control (naive or sham) and injured brains, the dynamics of the changes in synaptic responses that developed during stimulation were predictive of the final plasticity outcome. Our results demonstrate that the temporal pattern of stimulation plays a role in the polarity and magnitude of synaptic plasticity induced in the cerebral cortex while highlighting differences between normal and injured brain responses. Moreover, these results may be useful for optimization of neurostimulation therapies to treat mTBI and other brain disorders, in addition to providing new insights into downstream plasticity signaling mechanisms in the normal brain.

Sensor-level MEG combined with machine learning yields robust classification of mild traumatic brain injury patients

OBJECTIVE

Diagnosis of mild traumatic brain injury (mTBI) is challenging despite its high incidence, due to the unspecificity and variety of symptoms and the frequent lack of structural imaging findings. There is a need for reliable and simple-to-use diagnostic tools that would be feasible across sites and patient populations.

METHODS

We evaluated linear machine learning (ML) methods' ability to separate mTBI patients from healthy controls, based on their sensor-level magnetoencephalographic (MEG) power spectra in the subacute phase (<2 months) after a head trauma. We recorded resting-state MEG data from 25 patients and 25 age-sex matched controls and utilized a previously collected data set of 20 patients and 20 controls from a different site. The data sets were analyzed separately with three ML methods.

RESULTS

The median classification accuracies varied between 80 and 95%, without significant differences between the applied ML methods or data sets. The classification accuracies were significantly higher with ML than with traditional sensor-level MEG analysis based on detecting pathological low-frequency activity.

CONCLUSIONS

Easily applicable linear ML methods provide reliable and replicable classification of mTBI patients using sensor-level MEG data.

SIGNIFICANCE

Power spectral estimates combined with ML can classify mTBI patients with high accuracy and have high promise for clinical use.

Teasing apart trauma: neural oscillations differentiate individual cases of mild traumatic brain injury from post-traumatic stress disorder even when symptoms overlap

Post-traumatic stress disorder (PTSD) and mild traumatic brain injury (mTBI) are highly prevalent and closely related disorders. Affected individuals often exhibit substantially overlapping symptomatology - a major challenge for differential diagnosis in both military and civilian contexts. According to our symptom assessment, the PTSD group exhibited comparable levels of concussion symptoms and severity to the mTBI group. An objective and reliable system to uncover the key neural signatures differentiating these disorders would be an important step towards translational and applied clinical use. Here we explore use of MEG (magnetoencephalography)-multivariate statistical learning analysis in identifying the neural features for differential PTSD/mTBI characterisation. Resting state MEG-derived regional neural activity and coherence (or functional connectivity) across seven canonical neural oscillation frequencies (delta to high gamma) were used. The selected features were consistent and largely confirmatory with previously established neurophysiological markers for the two disorders. For regional power from theta, alpha and high gamma bands, the amygdala, hippocampus and temporal areas were identified. In line with regional activity, additional connections within the occipital, parietal and temporal regions were selected across a number of frequency bands. This study is the first to employ MEG-derived neural features to reliably and differentially stratify the two disorders in a multi-group context. The features from alpha and beta bands exhibited the best classification performance, even in cases where distinction by concussion symptom profiles alone were extremely difficult. We demonstrate the potential of using 'invisible' neural indices of brain functioning to understand and differentiate these debilitating conditions.

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

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.