Elizabeth M. Davenport

Subconcussive impacts and imaging findings over a season of contact sports

The effect of repeated subconcussive head impacts in youth and high school sports on the developing brain is poorly understood. Emerging neuroimaging data correlated with biomechanical exposure metrics are beginning to demonstrate relationships across a variety of modalities. The long-term consequences of these changes are unknown. A review of the currently available literature on the effect of subconcussive head impacts on youth and high school-age male football players provides compelling evidence for more focused studies of these effects in these vulnerable populations.

Head Impact Exposure in Youth Football: Comparing Age- and Weight-Based Levels of Play

Approximately 5,000,000 athletes play organized football in the United States, and youth athletes constitute the largest proportion with ∼3,500,000 participants. Investigations of head impact exposure (HIE) in youth football have been limited in size and duration. The objective of this study was to evaluate HIE of athletes participating in three age- and weight-based levels of play within a single youth football organization over four seasons. Head impact data were collected using the Head Impact Telemetry (HIT) System. Mixed effects linear models were fitted, and Wald tests were used to assess differences in head accelerations and number of impacts among levels and session type (competitions vs. practices). The three levels studied were levels A (n = 39, age = 10.8 ± 0.7 years, weight = 97.5 ± 11.8 lb), B (n = 48, age = 11.9 ± 0.5 years, weight = 106.1 ± 13.8 lb), and C (n = 32, age = 13.0 ± 0.5 years, weight = 126.5 ± 18.6 lb). A total of 40,538 head impacts were measured. The median/95th percentile linear head acceleration for levels A, B, and C was 19.8/49.4g, 20.6/51.0g, and 22.0/57.9g, respectively. Level C had significantly greater mean linear acceleration than both levels A (p = 0.005) and B (p = 0.02). There were a significantly greater number of impacts per player in a competition than in a practice session for all levels (A, p = 0.0005, B, p = 0.0019, and C, p < 0.0001). Athletes at lower levels experienced a greater percentage of their high magnitude impacts (≥ 80g) in practice, whereas those at the highest level experienced a greater percentage of their high magnitude impacts in competition. These data improve our understanding of HIE within youth football and are an important step in making evidence-based decisions to reduce HIE.

Using Convolutional Neural Networks to Automatically Detect Eye-Blink Artifacts in Magnetoencephalography Without Resorting to Electrooculography

Magnetoencephelography (MEG) is a functional neuroimaging tool that records the magnetic fields induced by neuronal activity; however, signal from muscle activity often corrupts the data. Eye-blinks are one of the most common types of muscle artifact. They can be recorded by affixing eye proximal electrodes, as in electrooculography (EOG), however this complicates patient preparation and decreases comfort. Moreover, it can induce further muscular artifacts from facial twitching. We propose an EOG free, data driven approach. We begin with Independent Component Analysis (ICA), a well-known preprocessing approach that factors observed signal into statistically independent components. When applied to MEG, ICA can help separate neuronal components from non-neuronal ones, however, the components are randomly ordered. Thus, we develop a method to assign one of two labels, non-eye-blink or eye-blink, to each component. Our contributions are two-fold. First, we develop a 10-layer Convolutional Neural Network (CNN), which directly labels eye-blink artifacts. Second, we visualize the learned spatial features using attention mapping, to reveal what it has learned and bolster confidence in the methods ability to generalize to unseen data. We acquired 8-min, eyes open, resting state MEG from 44 subjects. We trained our method on the spatial maps from ICA of 14 subjects selected randomly with expertly labeled ground truth. We then tested on the remaining 30 subjects. Our approach achieves a test classification accuracy of 99.67%, sensitivity: 97.62%, specificity: 99.77%, and ROC AUC: 98.69%. We also show the learned spatial features correspond to those human experts typically use which corroborates our models validity. This work (1) facilitates creation of fully automated processing pipelines in MEG that need to remove motion artifacts related to eye blinks, and (2) potentially obviates the use of additional EOG electrodes for the recording of eye-blinks in MEG studies.

Changes in resting state MRI networks from a single season of football distinguishes controls, low, and high head impact exposure

Sub-concussive asymptomatic head impacts during contact sports may develop potential neurological changes and may have accumulative effect through repetitive occurrences in contact sports like American football. The effects of sub-concussive head impacts on the functional connectivity of the brain are still unclear with no conclusive results yet presented. Although various studies have been performed on the topic, they have yielded mixed results with some concluding that sub concussive head impacts do not have any effect on functional connectivity, while others concluding that there are acute to chronic effects. The purpose of this study is to determine whether there is an effect on the functional connectivity of the brain from repetitive sub concussive head impacts. First, we applied a model free group ICA based intrinsic network selection to consider the relationship between all voxels while avoiding an arbitrary choice of seed selection. Second, unlike most other studies, we have utilized the default mode network along with other extracted intrinsic networks for classification. Third, we systematically tested multiple supervised machine learning classification algorithms to predict whether a player was a non-contact sports youth player, a contact sports player with low levels of cumulative biomechanical force impacts, or one with high levels of exposure. The 10-fold cross validation results show robust classification between the groups with accuracy up to 78% establishing the potential of data driven approaches coupled with machine learning to study connectivity changes in youth football players. This work adds to the growing body of evidence that there are detectable changes in brain signature from playing a single season of contact sports.

Quantifying the association between white matter integrity changes and subconcussive head impact exposure from a single season of youth and high school football using 3D convolutional neural networks

The effect of subconcussive head impact exposure during contact sports, including American football, on brain health is poorly understood particularly in young and adolescent players, who may be more vulnerable to brain injury during periods of rapid brain maturation. This study aims to quantify the association between cumulative effects of head impact exposure from a single season of football on white matter (WM) integrity as measured with diffusion MRI. The study targets football players aged 9-18 years old. All players were imaged pre- and post-season with structural MRI and diffusion tensor MRI (DTI). Fractional Anisotropy (FA) maps, shown to be closely correlated with WM integrity, were computed for each subject, co-registered and subtracted to compute the change in FA per subject. Biomechanical metrics were collected at every practice and game using helmet mounted accelerometers. Each head impact was converted into a risk of concussion, and the risk of concussion-weighted cumulative exposure (RWE) was computed for each player for the season. Athletes with high and low RWE were selected for a two-category classification task. This task was addressed by developing a 3D Convolutional Neural Network (CNN) to automatically classify players into high and low impact exposure groups from the change in FA maps. Using the proposed model, high classification performance, including ROC Area Under Curve score of 85.71% and F1 score of 83.33% was achieved. This work adds to the growing body of evidence for the presence of detectable neuroimaging brain changes in white matter integrity from a single season of contact sports play, even in the absence of a clinically diagnosed concussion.

Single season changes in resting state network power and the connectivity between regions distinguish head impact exposure level in high school and youth football players

The effect of repetitive sub-concussive head impact exposure in contact sports like American football on brain health is poorly understood, especially in the understudied populations of youth and high school players. These players, aged 9-18 years old may be particularly susceptible to impact exposure as their brains are undergoing rapid maturation. This study helps fill the void by quantifying the association between head impact exposure and functional connectivity, an important aspect of brain health measurable via resting-state fMRI (rs-fMRI). The contributions of this paper are three fold. First, the data from two separate studies (youth and high school) are combined to form a high-powered analysis with 60 players. These players experience head acceleration within overlapping impact exposure making their combination particularly appropriate. Second, multiple features are extracted from rs-fMRI and tested for their association with impact exposure. One type of feature is the power spectral density decomposition of intrinsic, spatially distributed networks extracted via independent components analysis (ICA). Another feature type is the functional connectivity between brain regions known often associated with mild traumatic brain injury (mTBI). Third, multiple supervised machine learning algorithms are evaluated for their stability and predictive accuracy in a low bias, nested cross-validation modeling framework. Each classifier predicts whether a player sustained low or high levels of head impact exposure. The nested cross validation reveals similarly high classification performance across the feature types, and the Support Vector, Extremely randomized trees, and Gradboost classifiers achieve F1-score up to 75%.

Microstructural correlates of 3D steady-state inhomogeneous magnetization transfer (ihMT) in the human brain white matter assessed by myelin water imaging and diffusion tensor imaging

To compare the recently introduced inhomogeneous magnetization transfer (ihMT) technique with more established MRI techniques including myelin water imaging (MWI) and diffusion tensor imaging (DTI), and to evaluate the microstructural attributes correlating with this new contrast method in the human brain white matter.

In-Season Variations in Head Impact Exposure among Youth Football Players

Head impact exposure (HIE) is often summarized by the total exposure measured during the season and does not indicate how the exposure was accumulated, or how it varied during the season. Therefore, the objective of this study was to compare HIE during pre-season, the first and second halves of the regular season, and playoffs in a sample of youth football players (n = 119, aged 9-13 years). Athletes were divided into one of four exposure groups based on quartiles computed from the distribution of risk-weighted cumulative exposure (RWECP). Mean impacts per session and mean 95th percentile linear and rotational acceleration in practices and games were compared across the four exposure groups and time frames using mixed effects models. Within games, the mean 95th percentile accelerations for the entire sample ranged from 47.2g and 2331.3 rad/sec2 during pre-season to 52.1g and 2533.4 rad/sec2 during the second half of regular season. Mean impacts per practice increased from pre-season to the second half of regular season and declined into playoffs among all exposure groups; however, the variation between time frames was not greater than two impacts per practice. Time of season had a significant relationship with mean 95th percentile linear and rotational acceleration in games (both, p = 0.01) but not with practice accelerations or impacts per session. The in-practice mean levels of 95th percentile linear and rotational acceleration remained fairly constant across the four time frames, but in games these changed over time depending on exposure group (interactions, p ≤ 0.05). The results of this study improve our understanding of in-season variations in HIE in youth football and may inform important opportunities for future interventions.

Automatic 1D convolutional neural network-based detection of artifacts in MEG acquired without electrooculography or electrocardiography

Magnetoencephalography (MEG) is a functional neuroimaging tool that records the magnetic fields induced by electrical neuronal activity; however, signal from non-neuronal sources can corrupt the data. Eye-Blinks (EB) and Cardiac Activity (CA) are two of the most common types of non-neuronal artifacts. They can be measured by affixing eye proximal electrodes, as in electrooculography (EOG) and chest electrodes, as in electrocardiography (EKG), however this complicates imaging setup, decreases patient comfort, and often induces further artifacts from facial twitching and postural muscle movement. We propose an EOG- and EKG-free approach to identify eye-blink, cardiac, or neuronal signals for automated artifact suppression. Our contributions are two-fold. First, we combine a data driven, multivariate decomposition approach based on Independent Component Analysis (ICA) and a highly accurate classifier constructed as a deep 1-D Convolutional Neural Network. Second, we visualize the features learned to reveal what features the model uses and to bolster user confidence in our model’s training and potential for generalization. We train and test three variants of our method on resting state MEG data from 49 subjects. Our cardiac model achieves a 96% sensitivity and 99% specificity on the set-aside test-set. Our eye-blink model achieves a sensitivity of 85% and specificity of 97%. This work facilitates automated MEG processing for both, clinical and research use, and can obviate the need for EOG or EKG electrodes.

Automatic identification of successful memory encoding in stereo-eeg of refractory, mesial temporal lobe epilepsy

Surgical resection of portions of the temporal lobe is the standard of care for patients with refractory mesial temporal lobe epilepsy. While this reduces seizures, it often results in an inability to form new memories, which leads to difficulties in social situations, learning, and suboptimal quality of life. Learning about the success or failure to form new memory in such patients is critical if we are to generate neuromodulation-based therapies. To this end, we tackle the many challenges in analyzing memory formation when their brains are recorded using stereoencephalography (sEEG) in a Free Recall task. Our contributions are threefold. First, we compute a rich measure of brain connectivity by computing the phase locking value statistic (synchrony) between pairs of regions, over hundreds of word memorization trials. Second, we leverage the rich information (over 400 values per pair of probed brain regions) to form consistent length feature vectors for classifier training. Third, we train and evaluate seven different types of classifier models and identify which ones achieve the highest accuracy and which brain features are most important for high accuracy. We assess our approach on data from 37 patients pre-resection surgery. We achieve up to 73% accuracy distinguishing successful from unsuccessful memory formation in the human brain from just 1.6 sec epochs of sEEG data.