Brain Deformation Estimation With Transfer Learning for Head Impact Datasets Across Impact Types

OBJECTIVE

The machine-learning head model (MLHM) to accelerate the calculation of brain strain and strain rate, which are the predictors for traumatic brain injury (TBI), but the model accuracy was found to decrease sharply when the training/test datasets were from different head impacts types (i.e., car crash, college football), which limits the applicability of MLHMs to different types of head impacts and sports. Particularly, small sizes of target dataset for specific impact types with tens of impacts may not be enough to train an accurate impact-type-specific MLHM.

METHODS

To overcome this, we propose data fusion and transfer learning to develop a series of MLHMs to predict the maximum principal strain (MPS) and maximum principal strain rate (MPSR).

RESULTS

The strategies were tested on American football (338), mixed martial arts (457), reconstructed car crash (48) and reconstructed American football (36) and we found that the MLHMs developed with transfer learning are significantly more accurate in estimating MPS and MPSR than other models, with a mean absolute error (MAE) smaller than 0.03 in predicting MPS and smaller than [Formula: see text] in predicting MPSR on all target impact datasets. High performance in concussion detection was observed based on the MPS and MPSR estimated by the transfer-learning-based models.

CONCLUSION

The MLHMs can be applied to various head impact types for rapidly and accurately calculating brain strain and strain rate.

SIGNIFICANCE

This study enables developing MLHMs for the head impact type with limited availability of data, and will accelerate the applications of MLHMs.

AI-based denoising of head impact kinematics measurements with convolutional neural network for traumatic brain injury prediction

OBJECTIVE

Wearable devices are developed to measure head impact kinematics but are intrinsically noisy because of the imperfect interface with human bodies. This study aimed to improve the head impact kinematics measurements obtained from instrumented mouthguards using deep learning to enhance traumatic brain injury (TBI) risk monitoring.

METHODS

We developed one-dimensional convolutional neural network (1D-CNN) models to denoise mouthguard kinematics measurements for tri-axial linear acceleration and tri-axial angular velocity from 163 laboratory dummy head impacts. The performance of the denoising models was evaluated on three levels: kinematics, brain injury criteria, and tissue-level strain and strain rate. Additionally, we performed a blind test on an on-field dataset of 118 college football impacts and a test on 413 post-mortem human subject (PMHS) impacts.

RESULTS

On the dummy head impacts, the denoised kinematics showed better correlation with reference kinematics, with relative reductions of 36% for pointwise root mean squared error and 56% for peak absolute error. Absolute errors in six brain injury criteria were reduced by a mean of 82%. For maximum principal strain and maximum principal strain rate, the mean error reduction was 35% and 69%, respectively. On the PMHS impacts, similar denoising effects were observed and the peak kinematics after denoising were more accurate (relative error reduction for 10% noisiest impacts was 75.6%).

CONCLUSION

The 1D-CNN denoising models effectively reduced errors in mouthguard-derived kinematics measurements on dummy and PMHS impacts.

SIGNIFICANCE

This study provides a novel approach for denoising head kinematics measurements in dummy and PMHS impacts, which can be further validated on more real-human kinematics data before real-world applications.

Machine-learning-based head impact subtyping based on the spectral densities of the measurable head kinematics

BACKGROUND

Traumatic brain injury can be caused by head impacts, but many brain injury risk estimation models are not equally accurate across the variety of impacts that patients may undergo, and the characteristics of different types of impacts are not well studied. We investigated the spectral characteristics of different head impact types with kinematics classification.

METHODS

Data were analyzed from 3262 head impacts from lab reconstruction, American football, mixed martial arts, and publicly available car crash data. A random forest classifier with spectral densities of linear acceleration and angular velocity was built to classify head impact types (e.g., football, car crash, mixed martial arts). To test the classifier robustness, another 271 lab-reconstructed impacts were obtained from 5 other instrumented mouthguards. Finally, with the classifier, type-specific, nearest-neighbor regression models were built for brain strain.

RESULTS

The classifier reached a median accuracy of 96% over 1000 random partitions of training and test sets. The most important features in the classification included both low- and high-frequency features, both linear acceleration features and angular velocity features. Different head impact types had different distributions of spectral densities in low- and high-frequency ranges (e.g., the spectral densities of mixed martial arts impacts were higher in the high-frequency range than in the low-frequency range). The type-specific regression showed a generally higher R2 value than baseline models without classification.

CONCLUSION

The machine-learning-based classifier enables a better understanding of the impact kinematics spectral density in different sports, and it can be applied to evaluate the quality of impact-simulation systems and on-field data augmentation.

Finite element evaluation of an American football helmet featuring liquid shock absorbers for protecting against concussive and subconcussive head impacts

Introduction: Concern has grown over the potential long-term effects of repeated head impacts and concussions in American football. Recent advances in impact engineering have yielded the development of soft, collapsible, liquid shock absorbers, which have demonstrated the ability to dramatically attenuate impact forces relative to existing helmet shock absorbers. Methods: To further explore how liquid shock absorbers can improve the efficacy of an American football helmet, we developed and optimized a finite element (FE) helmet model including 21 liquid shock absorbers spread out throughout the helmet. Using FE models of an anthropomorphic test headform and linear impactor, a previously published impact test protocol representative of concussive National Football League impacts (six impact locations, three velocities) was performed on the liquid FE helmet model and four existing FE helmet models. We also evaluated the helmets at three lower impact velocities representative of subconcussive football impacts. Head kinematics were recorded for each impact and used to compute the Head Acceleration Response Metric (HARM), a metric factoring in both linear and angular head kinematics and used to evaluate helmet performance. The head kinematics were also input to a FE model of the head and brain to calculate the resulting brain strain from each impact. Results: The liquid helmet model yielded the lowest value of HARM at 33 of the 36 impact conditions, offering an average 33.0% (range: -37.5% to 56.0%) and 32.0% (range: -2.2% to 50.5%) reduction over the existing helmet models at each impact condition in the subconcussive and concussive tests, respectively. The liquid helmet had a Helmet Performance Score (calculated using a summation of HARM values weighted based on injury incidence data) of 0.71, compared to scores ranging from 1.07 - 1.21 from the other four FE helmet models. Resulting brain strains were also lower in the liquid helmet. Discussion: The results of this study demonstrate the promising ability of liquid shock absorbers to improve helmet safety performance and encourage the development of physical prototypes of helmets featuring this technology. The implications of the observed reductions on brain injury risk are discussed.

Toward more accurate and generalizable brain deformation estimators for traumatic brain injury detection with unsupervised domain adaptation

Machine learning head models (MLHMs) are developed to estimate brain deformation for early detection of traumatic brain injury (TBI). However, the overfitting to simulated impacts and the lack of generalizability caused by distributional shift of different head impact datasets hinders the broad clinical applications of current MLHMs. We propose brain deformation estimators that integrates unsupervised domain adaptation with a deep neural network to predict whole-brain maximum principal strain (MPS) and MPS rate (MPSR). With 12,780 simulated head impacts, we performed unsupervised domain adaptation on on-field head impacts from 302 college football (CF) impacts and 457 mixed martial arts (MMA) impacts using domain regularized component analysis (DRCA) and cycle-GAN-based methods. The new model improved the MPS/MPSR estimation accuracy, with the DRCA method significantly outperforming other domain adaptation methods in prediction accuracy ( p < 0.001 ) : MPS RMSE: 0.027 (CF) and 0.037 (MMA); MPSR RMSE: 7.159 (CF) and 13.022 (MMA). On another two hold-out testsets with 195 college football impacts and 260 boxing impacts, the DRCA model significantly outperformed the baseline model without domain adaptation in MPS and MPSR estimation accuracy ( p < 0.001 ) . The DRCA domain adaptation reduces the MPS/MPSR estimation error to be well below TBI thresholds, enabling accurate brain deformation estimation to detect TBI in future clinical applications.

Padded Helmet Shell Covers in American Football: A Comprehensive Laboratory Evaluation with Preliminary On-Field Findings

Protective headgear effects measured in the laboratory may not always translate to the field. In this study, we evaluated the impact attenuation capabilities of a commercially available padded helmet shell cover in the laboratory and on the field. In the laboratory, we evaluated the padded helmet shell cover's efficacy in attenuating impact magnitude across six impact locations and three impact velocities when equipped to three different helmet models. In a preliminary on-field investigation, we used instrumented mouthguards to monitor head impact magnitude in collegiate linebackers during practice sessions while not wearing the padded helmet shell covers (i.e., bare helmets) for one season and whilst wearing the padded helmet shell covers for another season. The addition of the padded helmet shell cover was effective in attenuating the magnitude of angular head accelerations and two brain injury risk metrics (DAMAGE, HARM) across most laboratory impact conditions, but did not significantly attenuate linear head accelerations for all helmets. Overall, HARM values were reduced in laboratory impact tests by an average of 25% at 3.5 m/s (range: 9.7 to 39.6%), 18% at 5.5 m/s (range: - 5.5 to 40.5%), and 10% at 7.4 m/s (range: - 6.0 to 31.0%). However, on the field, no significant differences in any measure of head impact magnitude were observed between the bare helmet impacts and padded helmet impacts. Further laboratory tests were conducted to evaluate the ability of the padded helmet shell cover to maintain its performance after exposure to repeated, successive impacts and across a range of temperatures. This research provides a detailed assessment of padded helmet shell covers and supports the continuation of in vivo helmet research to validate laboratory testing results.

Finding the Spatial Co-Variation of Brain Deformation With Principal Component Analysis

OBJECTIVE

Strain and strain rate are effective traumatic brain injury metrics. In finite element (FE) head model, thousands of elements were used to represent the spatial distribution of these metrics. Owing that these metrics are resulted from brain inertia, their spatial distribution can be represented in more concise pattern. Since head kinematic features and brain deformation vary largely across head impact types (Zhan et al., 2021), we applied principal component analysis (PCA) to find the spatial co-variation of injury metrics (maximum principal strain (MPS), MPS rate (MPSR) and MPS × MPSR) in four impact types: simulation, football, mixed martial arts and car crashes, and used the PCA to find patterns in these metrics and improve the machine learning head model (MLHM).

METHODS

We applied PCA to decompose the injury metrics for all impacts in each impact type, and investigate the spatial co-variation using the first principal component (PC1). Furthermore, we developed a MLHM to predict PC1 and then inverse-transform to predict for all brain elements. The accuracy, the model complexity and the size of training dataset of PCA-MLHM are compared with previous MLHM (Zhan et al., 2021).

RESULTS

PC1 explained variance on the datasets. Based on PC1 coefficients, the corpus callosum and midbrain exhibit high variance on all datasets. Finally, the PCA-MLHM reduced model parameters by 74% with a similar MPS estimation accuracy.

CONCLUSION

The brain injury metric in a dataset can be decomposed into mean components and PC1 with high explained variance.

SIGNIFICANCE

The spatial co-variation analysis enables better interpretation of the patterns in brain injury metrics. It also improves the efficiency of MLHM.

Piecewise Multivariate Linearity Between Kinematic Features and Cumulative Strain Damage Measure (CSDM) Across Different Types of Head Impacts

In a previous study, we found that the relationship between brain strain and kinematic features cannot be described by a generalized linear model across different types of head impacts. In this study, we investigate if such a linear relationship exists when partitioning head impacts using a data-driven approach. We applied the K-means clustering method to partition 3161 impacts from various sources including simulation, college football, mixed martial arts, and car crashes. We found piecewise multivariate linearity between the cumulative strain damage (CSDM; assessed at the threshold of 0.15) and head kinematic features. Compared with the linear regression models without partition and the partition according to the types of head impacts, K-means-based data-driven partition showed significantly higher CSDM regression accuracy, which suggested the presence of piecewise multivariate linearity across types of head impacts. Additionally, we compared the piecewise linearity with the partitions based on individual features used in clustering. We found that the partition with maximum angular acceleration magnitude at 4706 rad/s² led to the highest piecewise linearity. This study may contribute to an improved method for the rapid prediction of CSDM in the future.

Physics-Informed Machine Learning Improves Detection of Head Impacts

In this work we present a new physics-informed machine learning model that can be used to analyze kinematic data from an instrumented mouthguard and detect impacts to the head. Monitoring player impacts is vitally important to understanding and protecting from injuries like concussion. Typically, to analyze this data, a combination of video analysis and sensor data is used to ascertain the recorded events are true impacts and not false positives. In fact, due to the nature of using wearable devices in sports, false positives vastly outnumber the true positives. Yet, manual video analysis is time-consuming. This imbalance leads traditional machine learning approaches to exhibit poor performance in both detecting true positives and preventing false negatives. Here, we show that by simulating head impacts numerically using a standard Finite Element head-neck model, a large dataset of synthetic impacts can be created to augment the gathered, verified, impact data from mouthguards. This combined physics-informed machine learning impact detector reported improved performance on test datasets compared to traditional impact detectors with negative predictive value and positive predictive values of 88 and 87% respectively. Consequently, this model reported the best results to date for an impact detection algorithm for American football, achieving an F₁ score of 0.95. In addition, this physics-informed machine learning impact detector was able to accurately detect true and false impacts from a test dataset at a rate of 90% and 100% relative to a purely manual video analysis workflow. Saving over 12 h of manual video analysis for a modest dataset, at an overall accuracy of 92%, these results indicate that this model could be used in place of, or alongside, traditional video analysis to allow for larger scale and more efficient impact detection in sports such as American Football.

Time Window of Head Impact Kinematics Measurement for Calculation of Brain Strain and Strain Rate in American Football

Wearable devices have been shown to effectively measure the head's movement during impacts in sports like American football. When a head impact occurs, the device is triggered to collect and save the kinematic measurements during a predefined time window. Then, based on the collected kinematics, finite element (FE) head models can calculate brain strain and strain rate, which are used to evaluate the risk of mild traumatic brain injury. To find a time window that can provide a sufficient duration of kinematics for FE analysis, we investigated 118 on-field video-confirmed football head impacts collected by the Stanford Instrumented Mouthguard. The simulation results based on the kinematics truncated to a shorter time window were compared with the original to determine the minimum time window needed for football. Because the individual differences in brain geometry influence these calculations, we included six representative brain geometries and found that larger brains need a longer time window of kinematics for accurate calculation. Among the different sizes of brains, a pre-trigger time of 40 ms and a post-trigger time of 70 ms were found to yield calculations of brain strain and strain rate that were not significantly different from calculations using the original 200 ms time window recorded by the mouthguard. Therefore, approximately 110 ms is recommended for complete modeling of impacts for football.

Head impact exposure and concussion in women's collegiate club lacrosse

This study sought to describe head impact exposure in women's collegiate club lacrosse. Eleven women's collegiate club lacrosse players wore head impact sensors during eight intercollegiate competitions. Video recordings of competitions were used to verify impact data. Athletes completed questionnaires detailing their concussion history and perceived head impact exposure. During the monitored games, no diagnosed concussions were sustained. Three athletes reported sustaining head impacts (median = 0; range: 0-3 impacts per game). Six impacts registered by the sensors were verified on video across a total of 81 athlete-game exposures. Verified impacts had a median peak linear acceleration of 21.0 g (range: 18.3 g - 48.3 g) and peak rotational acceleration of 1.1 krad/s² (range: 0.7 krad/s² - 5.7 krad/s²). Women competing in collegiate club lacrosse are at a low risk of sustaining head impacts, comparable to previous reports of the high school and collegiate varsity levels of play.

A Dose Relationship Between Brain Functional Connectivity and Cumulative Head Impact Exposure in Collegiate Water Polo Players

A growing body of evidence suggests that chronic, sport-related head impact exposure can impair brain functional integration and brain structure and function. Evidence of a robust inverse relationship between the frequency and magnitude of repeated head impacts and disturbed brain network function is needed to strengthen an argument for causality. In pursuing such a relationship, we used cap-worn inertial sensors to measure the frequency and magnitude of head impacts sustained by eighteen intercollegiate water polo athletes monitored over a single season of play. Participants were evaluated before and after the season using computerized cognitive tests of inhibitory control and resting electroencephalography. Greater head impact exposure was associated with increased phase synchrony [r₍₁₆₎ > 0.626, p < 0.03 corrected], global efficiency [r₍₁₆₎ > 0.601, p < 0.04 corrected], and mean clustering coefficient [r₍₁₆₎ > 0.625, p < 0.03 corrected] in the functional networks formed by slow-wave (delta, theta) oscillations. Head impact exposure was not associated with changes in performance on the inhibitory control tasks. However, those with the greatest impact exposure showed an association between changes in resting-state connectivity and a dissociation between performance on the tasks after the season [r₍₁₆₎ = 0.481, p = 0.043] that could also be attributed to increased slow-wave synchrony [F_{(4, 135)} = 113.546, p < 0.001]. Collectively, our results suggest that athletes sustaining the greatest head impact exposure exhibited changes in whole-brain functional connectivity that were associated with altered information processing and inhibitory control.

Patterns of head impact exposure in men's and women's collegiate club water polo

OBJECTIVES

Recent reports have demonstrated a risk of concussion and subconcussive head impacts in collegiate varsity and international elite water polo. We sought to characterize patterns of head impact exposure at the collegiate club level of water polo.

DESIGN

Prospective cohort study.

METHODS

Head impact sensors (SIM-G, Triax Technologies) were worn by men's (n=16) and women's (n=15) collegiate club water polo players during 11 games. Peak linear acceleration (PLA) and peak rotational acceleration (PRA) of head impacts were recorded by the sensors. Two streams of competition video were used to verify and describe the nature of head impacts.

RESULTS

Men's players sustained 52 verified head impacts of magnitude 39.7±16.3g PLA and 5.2±3.2 krad/s² PRA, and women's players sustained 43 verified head impacts of magnitude 33.7±12.6g PLA and 4.0±2.8krad/s² PRA. Impacts sustained by men had greater PLA than those sustained by women (p=.045). Athletes were impacted most frequently at the offensive center position, to the back of the head, and by an opponent's torso or limb.

CONCLUSIONS

Our cohort of male and female athletes sustained relatively infrequent head impacts during water polo competitions played at the collegiate club level. The amount of head impact exposure in our cohort was dependent on player position, with offensive centers prone to sustaining the most impacts. Head impact sensors are subject to large amounts of false positives and should be used in conjunction with video recordings to verify the validity of impact data.

The Effectiveness of Protective Headgear in Attenuating Ball-to-Forehead Impacts in Water Polo

Recent reports have demonstrated that there is a serious risk of head impact and injury in water polo. The use of protective headgear in contact sports is a commonly accepted strategy for reducing the risk of head injury, but there are few available protective headgears for use in water polo. Many of those that are available are banned by the sport's governing bodies due to a lack of published data supporting the effectiveness of those headgears in reducing head impact kinematics. To address this gap in knowledge, we launched a water polo ball at the forehead of an anthropomorphic testing device fitted with either a standard water polo headgear or one of two protective headgears. We selected a range of launch speeds representative of those observed across various athlete ages. Mixed-model ANOVAs revealed that, relative to standard headgear, protective headgears reduced peak linear acceleration (by 10.8-21.6%; p < 0.001), and peak rotational acceleration (by 24.5-48.5%; p < 0.001) induced by the simulated ball-to-forehead impacts. We discuss the possibility of using protective headgears in water polo to attenuate head impact kinematics.