This is not possible for the nominal peak velocity or any other conventional injury metric. The CNN-estimated effective peak rotation velocity and rotational axis are sufficiently accurate for ~ 73.5% of the impacts. Impacts from a subset of data (N = 1900) are also successfully matched with pcBRA idealized impacts based on elementwise MPS, where their regression slope and Pearson correlation coefficient do not deviate from 1.0 (when identical) by more than 0.1. When preserving peak MPS alone, the CNN-estimated effective peak rotational velocity achieves a coefficient of determination (R2) of ~ 0.96 relative to the directly identified counterpart, far outperforming nominal peak velocity from the resultant profiles (R2 of ~ 0.34). A training dataset (N = 3069) is used to develop a convolutional neural network (CNN) to automate impact simplification. A pre-computed brain response atlas (pcBRA) serves as a common reference.
In this study, we develop effective impact kinematics consisting of peak rotational velocity and the associated rotational axis to preserve not only peak MPS but also spatially detailed MPS. This is the first study aimed at instantly estimating spatially detailed brain strains for automotive head impacts, which employs >8.8 thousand impact simulations generated from ~1.5 years of nonstop computations on a high-performance computing platform.Ĭonventional kinematics-based brain injury metrics often approximate peak maximum principal strain (MPS) of the whole brain but ignore the anatomical location of occurrence. The CNN technique developed here may offer enhanced utility in the design and development of head protective countermeasures, including in the automotive industry. Therefore, the CNN has the potential to supersede current kinematic injury metrics that can only approximate a global peak MPS or CSDM.
Importantly, the CNN is able to efficiently estimate elementwise MPS with sufficient accuracy while conventional kinematic injury metrics cannot. Finally, the CNN achieved an average k and r of 0.98☐.12 and 0.90☐.07, respectively, for six reconstructed car crash impacts drawn from two other sources independent of the training dataset. Cumulative strain damage measure (CSDM) from the CNN estimation was also highly accurate compared to those from direct simulation across a range of thresholds (R2 of 0.899–0.943 with RMSE of 0.054–0.069). It also achieved a success rate of 60.5% and 94.8% for elementwise MPS, where the linear regression slope, k, and correlation coefficient, r, between estimated and simulated MPS did not deviate from 1.0 (when identical) by more than 0.1 and 0.2, respectively. For peak MPS, the CNN achieved a coefficient of determination (R2) of 0.932 and root mean squared error (RMSE) of 0.031 for the real-world testing dataset. The combined training achieved the best performances. Three training strategies were evaluated: 1) “baseline”, using random initial weights 2) “transfer learning”, using weight transfer from a previous CNN model trained on head impacts drawn from contact sports and 3) “combined training”, combining previous training data from contact sports (N=5661) for training. For each augmented impact, rotational velocity (v_rot) and the corresponding rotational acceleration (a_rot) profiles were concatenated as static images to serve as CNN input. They were simulated using the anisotropic Worcester Head Injury Model (WHIM) V1.0, which provided baseline elementwise peak maximum principal strain (MPS). Head impact kinematics (N=458) from two public databases were used to generate augmented impacts (N=2694). Here, we extend its application to automotive head impacts, where impact profiles are typically more complex with longer durations. Lately, a convolutional neural network (CNN) has been successfully developed to estimate spatially detailed brain strains instantly and accurately in contact sports. Efficient brain strain estimation is critical for routine application of a head injury model.
0 kommentar(er)
