Rapidly and accurately estimating brain strain and strain rate across head impact types with transfer learning and data fusion

Abstract

Brain strain and strain rate are effective in predicting traumatic brain injury (TBI) caused by head impacts. However, state-of-the-art finite element modeling (FEM) demands considerable computational time in the computation, limiting its application in real-time TBI risk monitoring. To accelerate, machine learning head models (MLHMs) were developed, and the model accuracy was found to decrease when the training/test datasets were from different head impacts types. However, the size of dataset for specific impact types may not be enough for model training. To address the computational cost of FEM, the limited strain rate prediction, and the generalizability of MLHMs to on-field datasets, 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). We trained and tested the MLHMs on 13,623 head impacts from simulations, American football, mixed martial arts, car crash, and compared against the models trained on only simulations or only on-field impacts. 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 7s −1 in predicting MPSR on all impact datasets. The MLHMs can be applied to various head impact types for rapidly and accurately calculating brain strain and strain rate. Besides the clinical applications in real-time brain strain and strain rate monitoring, this model helps researchers estimate the brain strain and strain rate caused by head impacts more efficiently than FEM.

Data-driven decomposition of brain dynamics with principal component analysis in different types of head impacts

“…The application of PCA in the development of DLHM to estimate whole-brain MPS, MPSR and MPS×MPSR is also worth further discussion. DLHMs have shown their effectiveness in reducing the computational cost associated with the state-of-the-art FEM in previous studies [23], [27], [36]. They are developed for different FEM and act as function approximators of FEM when the mapping between the head impact kinematics and the brain dynamics is learned through large quantities of impact data.…”

“…The decomposition of brain dynamics with PCA can reduce the dimensionality of output and therefore simplify the training objective in the development of DLHMs. To verify this, we leveraged the PCA models to get the low-dimensional brain dynamics representations, developed DLHMs to predict the value on the k PCs based on 510 kinematics features [36] (with k determined in the first results section), and reconstructed the whole-brain MPS, MPSR and MPS×MPSR with the accuracy evaluated by several metrics. The details are shown as follows:…”

The Impact of Drop Test Conditions on Brain Strain Location and Severity: A Novel Approach Using a Deep Learning Model

“…In contrast, the pre-computation technique put forward by Ji et al has enabled element-wise, whole-brain MPS to be computed instantly [27]. Once trained on a large library of head impacts, machine learning head models (MLHMs) have enabled whole-brain MPS to be computed in seconds [48,49]. Recently, a convolutional neural network (CNN) has been developed and trained using simulation results of head impacts using the Worcester Head Injury Model (WHIM) [50,51].…”