[论文解读] Deep Learning Head Model for Real-time Estimation of Entire Brain Deformation in Concussion

Xianghao Zhan, Yuzhe Liu+7 more|arXiv (Cornell University)|Oct 16, 2020

Traumatic Brain Injury Research参考文献 48被引用 7

一句话总结

该论文提出了一种基于五层神经网络的深度学习头部模型，结合工程化的运动学特征，可在0.001秒内预测全脑最大主应变，基于模拟和真实运动数据的1,803次头部撞击中，均方根误差达到0.025，显著加速了轻度创伤性脑损伤（mTBI）风险评估，相比传统有限元方法具有明显优势。

ABSTRACT

Objective: Many recent studies have suggested that brain deformation resulting from a head impact is linked to the corresponding clinical outcome, such as mild traumatic brain injury (mTBI). Even though several finite element (FE) head models have been developed and validated to calculate brain deformation based on impact kinematics, the clinical application of these FE head models is limited due to the time-consuming nature of FE simulations. This work aims to accelerate the process of brain deformation calculation and thus improve the potential for clinical applications. Methods: We propose a deep learning head model with a five-layer deep neural network and feature engineering, and trained and tested the model on 1803 total head impacts from a combination of head model simulations and on-field college football and mixed martial arts impacts. Results: The proposed deep learning head model can calculate the maximum principal strain for every element in the entire brain in less than 0.001s (with an average root mean squared error of 0.025, and with a standard deviation of 0.002 over twenty repeats with random data partition and model initialization). The contributions of various features to the predictive power of the model were investigated, and it was noted that the features based on angular acceleration were found to be more predictive than the features based on angular velocity. Conclusion: Trained using the dataset of 1803 head impacts, this model can be applied to various sports in the calculation of brain strain with accuracy, and its applicability can even further be extended by incorporating data from other types of head impacts. Significance: In addition to the potential clinical application in real-time brain deformation monitoring, this model will help researchers estimate the brain strain from a large number of head impacts more efficiently than using FE models.

研究动机与目标

• 解决有限元（FE）模型在mTBI研究中因计算耗时而难以实现实时应用的临床局限性。
• 开发一种快速、可扩展的替代方案，用于从头部撞击运动学数据中估计全脑形变。
• 利用可穿戴传感器数据与机器学习技术，在运动场景中实现实时脑应变监测。
• 通过使用学习得到的代理模型替代计算成本高昂的有限元模拟，提升大规模头部撞击分析的效率。
• 探究工程化运动学特征（尤其是角加速度）在脑应变预测中的重要性。

提出的方法

• 在1,803次头部撞击数据的融合数据集上训练五层深度神经网络，数据来源于有限元模拟和大学橄榄球及综合格斗运动中的真实可穿戴牙套传感器测量。
• 将基于头部撞击运动学的工程化特征（包括线性加速度和角速度的时间域信号）作为模型输入。
• 应用特征选择与工程化技术，提取与脑应变相关的机械预测因子，重点关注角加速度波形。
• 采用随机梯度下降优化，并结合早停法与随机数据划分策略，以确保模型的鲁棒性与泛化能力。
• 通过均方根误差（RMSE）、重复运行的均方差以及特征重要性分析来验证模型性能。
• 可视化预测的全脑应变分布，以支持临床实时解读与干预指导。

实验结果

研究问题

• RQ1 基于模拟与真实世界头部撞击数据训练的深度学习模型，能否实现实时、准确预测全脑最大主应变？
• RQ2 不同工程化运动学特征（尤其是角加速度与角速度）对模型预测精度的贡献如何？
• RQ3 深度学习代理模型在保持高精度的同时，能在多大程度上超越传统有限元模拟的速度表现？
• RQ4 该模型能否在不同撞击类型（如不同运动或撞击严重程度）之间实现泛化？
• RQ5 通过分析模型隐藏层中学习到的表征，能否揭示脑应变机制的潜在见解？

主要发现

• 该深度学习头部模型每批次撞击的计算时间少于0.001秒，支持实时应用。
• 在二十次独立训练运行中，模型的平均均方根误差为0.025，标准差为0.002，表明其具备高度的一致性与准确性。
• 基于角加速度的特征在预测最大主应变方面比基于角速度的特征更具预测力，凸显其生物力学相关性。
• 该模型在不同撞击类型（包括模拟撞击、橄榄球撞击与综合格斗撞击）之间均表现出良好泛化能力，显示出对数据变异的鲁棒性。
• 特征重要性分析表明，捕捉旋转动力学的运动学特征对准确预测应变至关重要。
• 该模型可提供全脑范围的高分辨率应变图谱，支持临床决策中对损伤风险的空间定位。