Convolutional neural network for efficient estimation of regional brain strains
Convolutional neural network for efficient estimation of regional brain strains
复制标题
DOI：
10.1038/s41598-019-53551-1
复制
发表时间：
2019-11
影响因子：
4.6
通讯作者：
Shaoju Wu;Wei Zhao;Kianoosh Ghazi;Songbai Ji
中科院分区：
文献类型：
--
作者：
Shaoju Wu;Wei Zhao;Kianoosh Ghazi;Songbai Ji
头部损伤模型是研究脑震荡生物力学的重要工具，但对于现实世界的使用是不切实际的，因为它们太慢了。在这里，我们开发了一个卷积神经网络（CNN），通过将头部旋转速度曲线概念化为二维图像输入来立即准确地估计区域大脑应变。我们使用两个具有增强功能的影响数据集来研究CNN在各种训练测试配置下的预测性能。三个应变措施，包括最大主应变（MPS）的整个大脑，MPS的胼胝体，胼胝体的纤维应变。CNN使用在美式足球中测量的独立影响数据集（N = 314）进行进一步测试。在2592个训练样本的基础上，对全脑MPS的测试R2为0.916，均方根误差（RMSE）为0.014。结合所有可用的冲击应变响应数据（N = 3069），CNN在10倍交叉验证中实现了0.966的R2和0.013的RMSE。该技术可以实现对复杂的头部损伤模型的临床诊断能力，诸如通过移动终端促进脑震荡检测中的头部撞击传感器。此外，它可能会将目前基于加速度的损伤研究转变为关注区域性脑损伤。经过训练的CNN连同相关代码和示例在https://github.com/Jilab-biomechanics/CNN-brain-strains上公开沿着。今后将根据需要予以更新。
Head injury models are important tools to study concussion biomechanics but are impractical for real-world use because they are too slow. Here, we develop a convolutional neural network (CNN) to estimate regional brain strains instantly and accurately by conceptualizing head rotational velocity profiles as two-dimensional images for input. We use two impact datasets with augmentation to investigate the CNN prediction performances with a variety of training-testing configurations. Three strain measures are considered, including maximum principal strain (MPS) of the whole brain, MPS of the corpus callosum, and fiber strain of the corpus callosum. The CNN is further tested using an independent impact dataset (N = 314) measured in American football. Based on 2592 training samples, it achieves a testingR2of 0.916 and root mean squared error (RMSE) of 0.014 for MPS of the whole brain. Combining all impact-strain response data available (N = 3069), the CNN achieves anR2of 0.966 and RMSE of 0.013 in a 10-fold cross-validation. This technique may enable a clinical diagnostic capability to a sophisticated head injury model, such as facilitating head impact sensors in concussion detectionviaa mobile device. In addition, it may transform current acceleration-based injury studies into focusing on regional brain strains. The trained CNN is publicly available along with associated code and examples at https://github.com/Jilab-biomechanics/CNN-brain-strains. They will be updated as needed in the future.