Cargando…

Convolutional neural network for efficient estimation of regional brain strains

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 prof...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Shaoju, Zhao, Wei, Ghazi, Kianoosh, Ji, Songbai
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6874599/
https://www.ncbi.nlm.nih.gov/pubmed/31758002
http://dx.doi.org/10.1038/s41598-019-53551-1
_version_ 1783472869539315712
author Wu, Shaoju
Zhao, Wei
Ghazi, Kianoosh
Ji, Songbai
author_facet Wu, Shaoju
Zhao, Wei
Ghazi, Kianoosh
Ji, Songbai
author_sort Wu, Shaoju
collection PubMed
description 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 testing R(2) of 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 an R(2) of 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 detection via a 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.
format Online
Article
Text
id pubmed-6874599
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-68745992019-12-04 Convolutional neural network for efficient estimation of regional brain strains Wu, Shaoju Zhao, Wei Ghazi, Kianoosh Ji, Songbai Sci Rep Article 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 testing R(2) of 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 an R(2) of 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 detection via a 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. Nature Publishing Group UK 2019-11-22 /pmc/articles/PMC6874599/ /pubmed/31758002 http://dx.doi.org/10.1038/s41598-019-53551-1 Text en © The Author(s) 2019 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
spellingShingle Article
Wu, Shaoju
Zhao, Wei
Ghazi, Kianoosh
Ji, Songbai
Convolutional neural network for efficient estimation of regional brain strains
title Convolutional neural network for efficient estimation of regional brain strains
title_full Convolutional neural network for efficient estimation of regional brain strains
title_fullStr Convolutional neural network for efficient estimation of regional brain strains
title_full_unstemmed Convolutional neural network for efficient estimation of regional brain strains
title_short Convolutional neural network for efficient estimation of regional brain strains
title_sort convolutional neural network for efficient estimation of regional brain strains
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6874599/
https://www.ncbi.nlm.nih.gov/pubmed/31758002
http://dx.doi.org/10.1038/s41598-019-53551-1
work_keys_str_mv AT wushaoju convolutionalneuralnetworkforefficientestimationofregionalbrainstrains
AT zhaowei convolutionalneuralnetworkforefficientestimationofregionalbrainstrains
AT ghazikianoosh convolutionalneuralnetworkforefficientestimationofregionalbrainstrains
AT jisongbai convolutionalneuralnetworkforefficientestimationofregionalbrainstrains