{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:08:01Z","timestamp":1785420481604,"version":"3.56.0"},"reference-count":49,"publisher":"ASME International","issue":"2","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/100000147","name":"Division of Civil, Mechanical and Manufacturing Innovation","doi-asserted-by":"publisher","award":["2114697"],"award-info":[{"award-number":["2114697"]}],"id":[{"id":"10.13039\/100000147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["R21NS136884"],"award-info":[{"award-number":["R21NS136884"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Efficient deep learning brain injury models enable large-scale, strain-based investigations of traumatic brain injury (TBI). Here, we extend a previous model based on a generic 50th percentile adult male brain to a more individualized surrogate (applicable to male, female, and youth) for rapid estimation of brain deformation over impact duration. We utilize a previous training dataset (N\u2009=\u20091363) based on the randomly scaled anisotropic Worcester Head Injury Model (WHIM) V1.0 simulating random head impacts generated from real-world datasets. Brain\u2013skull relative displacement was voxelized according to the three scaling factors along the anatomical axes at a temporal resolution of 1\u2009ms. The earlier multitask convolutional neural network (CNN) architecture (i.e., splitting the impact duration into multiple time segments) was modified to take the scaling factors as three additional inputs for training with transfer learning. Based on \u223c10% of the samples unseen from the training, the scaled CNN achieved an overall R2 of 0.96\u00b10.05 and root mean squared error (RMSE) of 0.25\u00b10.20\u2009mm, respectively, at peak displacement magnitude with high efficiency (&amp;lt;1\u2009s on laptop versus &amp;gt;30\u2009min on a high-end cluster for direct model simulation). It also achieved an R2 of 0.83\u00b10.16 and RMSE of 0.02\u00b10.01 for the corresponding maximum principal strain (MPS). When using linear regression slope, k, and Pearson correlation coefficient, r, at time of peak displacement, the CNN achieved a success rate of 81.0% and 70.8% for displacement and MPS, respectively. This work could facilitate more individualized integration of repetitive head impacts in modeling and axonal injury model simulations in the future, important to fill a critical gap in a multiscale modeling framework to investigate white matter injury.<\/jats:p>","DOI":"10.1115\/1.4070192","type":"journal-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T15:44:21Z","timestamp":1761320661000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":3,"title":["A Shape and Size-Scaled Deep Learning Brain Injury Model for Near Real-Time Dynamic Impact Simulation"],"prefix":"10.1115","volume":"148","author":[{"given":"Wei","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Worcester Polytechnic Institute , 60 Prescott Street , Worcester, MA 01605"},{"id":[{"id":"https:\/\/ror.org\/05ejpqr48","id-type":"ROR","asserted-by":"publisher"}],"name":"Worcester Polytechnic Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songbai","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Worcester Polytechnic Institute , 60 Prescott Street , Worcester, MA 01605 ; , 100 Institute Road , Worcester, MA 01609"},{"name":"Department of Mechanical Engineering, Worcester Polytechnic Institute , 60 Prescott Street , Worcester, MA 01605 ; , 100 Institute Road , Worcester, MA 01609"},{"id":[{"id":"https:\/\/ror.org\/05ejpqr48","id-type":"ROR","asserted-by":"publisher"}],"name":"Worcester Polytechnic Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"issue":"9","key":"2025111210590533900_bib1","doi-asserted-by":"crossref","first-page":"1832","DOI":"10.1007\/s10439-019-02205-4","article-title":"Finite Element Methods in Human Head Impact Simulations: A Review","volume":"47","year":"2019","journal-title":"Ann. Biomed. Eng."},{"issue":"11","key":"2025111210590533900_bib2","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1007\/s10439-022-02999-w","article-title":"Use of Brain Biomechanical Models for Monitoring Impact Exposure in Contact Sports","volume":"50","year":"2022","journal-title":"Ann. Biomed. Eng."},{"key":"2025111210590533900_bib3","first-page":"429","article-title":"Development of Numerical Models for Injury Biomechanics Research: A Review of 50 Years of Publications in the Stapp Car Crash Conference","volume":"50","year":"2006","journal-title":"Stapp Car Crash J."},{"key":"2025111210590533900_bib4","doi-asserted-by":"crossref","first-page":"111036","DOI":"10.1016\/j.jbiomech.2022.111036","article-title":"Influence of Morphological Variation on Brain Impact Responses Among Youth and Young Adults","volume":"135","year":"2022","journal-title":"J. Biomech."},{"key":"2025111210590533900_bib5","doi-asserted-by":"crossref","first-page":"706566","DOI":"10.3389\/fbioe.2021.706566","article-title":"Subject-Specific Head Model Generation by Mesh Morphing: A Personalization Framework and Its Applications","volume":"9","year":"2021","journal-title":"Front. Bioeng. Biotechnol."},{"key":"2025111210590533900_bib6","article-title":"An Anatomically Accurate and Personalizable Head Injury Model: Significance of Brain and White Matter Tract Morphological Variability on Strain","year":"2021","journal-title":"Biomech. Model. Mechanobiol."},{"issue":"7","key":"2025111210590533900_bib7","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1089\/neu.2013.3268","article-title":"Group-Wise Evaluation and Comparison of White Matter Fiber Strain and Maximum Principal Strain in Sports-Related Concussion","volume":"32","year":"2015","journal-title":"J. Neurotrauma"},{"issue":"1","key":"2025111210590533900_bib8","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s10237-022-01638-6","article-title":"Approximating Subject-Specific Brain Injury Models Via Scaling Based on Head\u2013Brain Morphological Relationships","volume":"22","year":"2023","journal-title":"Biomech. Model. Mechanobiol."},{"issue":"Suppl. 3","key":"2025111210590533900_bib9","first-page":"608","article-title":"Effect of Human Head Shape on the Risk of Traumatic Brain Injury: A Gaussian Process Regression-Based Machine Learning Approach","volume":"189","year":"2024","journal-title":"Mil. Med."},{"issue":"5","key":"2025111210590533900_bib10","doi-asserted-by":"crossref","first-page":"3925","DOI":"10.1007\/s00366-022-01697-4","article-title":"Combining Advanced Magnetic Resonance Imaging (MRI) With Finite Element (FE) Analysis for Characterising Subject-Specific Injury Patterns in the Brain After Traumatic Brain Injury","volume":"38","year":"2022","journal-title":"Eng. Comput."},{"issue":"9","key":"2025111210590533900_bib11","doi-asserted-by":"crossref","first-page":"1855","DOI":"10.1007\/s10439-018-02161-5","article-title":"An Analytical Review of the Numerical Methods Used for Finite Element Modeling of Traumatic Brain Injury","volume":"47","year":"2019","journal-title":"Ann. Biomed. Eng."},{"issue":"10","key":"2025111210590533900_bib12","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1053\/apmr.2001.25137","article-title":"Current Concepts: Diffuse Axonal Injury-Associated Traumatic Brain Injury","volume":"82","year":"2001","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"2025111210590533900_bib13","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.expneurol.2012.01.013","article-title":"Axonal Pathology in Traumatic Brain Injury","volume":"246","year":"2013","journal-title":"Exp. Neurol."},{"issue":"4","key":"2025111210590533900_bib14","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1016\/j.bpj.2011.11.4024","article-title":"Computational Modeling of Axonal Microtubule Bundles Under Tension","volume":"102","year":"2012","journal-title":"Biophys. J."},{"issue":"2","key":"2025111210590533900_bib15","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.bpj.2015.06.029","article-title":"Torsional Behavior of Axonal Microtubule Bundles","volume":"109","year":"2015","journal-title":"Biophys. J."},{"issue":"7","key":"2025111210590533900_bib16","doi-asserted-by":"crossref","first-page":"1718","DOI":"10.1016\/j.bpj.2015.01.030","article-title":"Buckling Behavior of Individual and Bundled Microtubules","volume":"108","year":"2015","journal-title":"Biophys. J."},{"issue":"5","key":"2025111210590533900_bib17","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1016\/j.bpj.2014.01.024","article-title":"Viscoelasticity of Tau Proteins Leads to Strain Rate-Dependent Breaking of Microtubules During Axonal Stretch Injury: Predictions From a Mathematical Model","volume":"106","year":"2014","journal-title":"Biophys. J."},{"key":"2025111210590533900_bib18","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.expneurol.2017.11.001","article-title":"Newfound Sex Differences in Axonal Structure Underlie Differential Outcomes From In Vitro Traumatic Axonal Injury","volume":"300","year":"2018","journal-title":"Exp. Neurol."},{"issue":"9","key":"2025111210590533900_bib19","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1089\/neu.2015.4007","article-title":"Nodal Versus Total Axonal Strain and the Role of Cholesterol in Traumatic Brain Injury","volume":"33","year":"2016","journal-title":"J. Neurotrauma"},{"key":"2025111210590533900_bib20","doi-asserted-by":"crossref","first-page":"643","DOI":"10.3389\/fneur.2018.00643","article-title":"Utilizing a Structural Mechanics Approach to Assess the Primary Effects of Injury Loads Onto the Axon and Its Components","volume":"9","year":"2018","journal-title":"Front. Neurol."},{"issue":"19\u201320","key":"2025111210590533900_bib21","first-page":"2217","article-title":"Sex Differences in Axonal Dynamic Responses Under Realistic Tension Using Finite Element Models","volume":"40","year":"2023","journal-title":"J. Neurotrauma"},{"key":"2025111210590533900_bib22","doi-asserted-by":"crossref","first-page":"100027","DOI":"10.1016\/j.brain.2021.100027","article-title":"Subject-Specific Multiscale Analysis of Concussion: From Macroscopic Loads to Molecular-Level Damage","volume":"2","year":"2021","journal-title":"Brain Multiphys."},{"key":"2025111210590533900_bib23","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1016\/j.nicl.2017.03.006","article-title":"The Effect of Repetitive Subconcussive Collisions on Brain Integrity in Collegiate Football Players Over a Single Football Season: A Multi-Modal Neuroimaging Study","volume":"14","year":"2017","journal-title":"NeuroImage Clin."},{"issue":"3","key":"2025111210590533900_bib24","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1007\/s10439-020-02685-9","article-title":"Brain Strain: Computational Model-Based Metrics for Head Impact Exposure and Injury Correlation","volume":"49","year":"2021","journal-title":"Ann. Biomed. Eng."},{"key":"2025111210590533900_bib25","article-title":"Large-Scale Mechanistic Axonal Injury Modeling via Deep Learning","year":"2025","journal-title":"Biomech. Model. Mechanobiol."},{"issue":"1","key":"2025111210590533900_bib26","doi-asserted-by":"crossref","first-page":"17326","DOI":"10.1038\/s41598-019-53551-1","article-title":"Convolutional Neural Network for Efficient Estimation of Regional Brain Strains","volume":"9","year":"2019","journal-title":"Sci. Rep."},{"issue":"8","key":"2025111210590533900_bib27","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1089\/neu.2020.7281","article-title":"Instantaneous Whole-Brain Strain Estimation in Dynamic Head Impact","volume":"38","year":"2021","journal-title":"J. Neurotrauma"},{"issue":"6","key":"2025111210590533900_bib28","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1080\/13588265.2022.2130600","article-title":"Deep Learning Method to Assess Brain Injury Risk","volume":"28","year":"2023","journal-title":"Int. J. Crashworthiness"},{"issue":"11","key":"2025111210590533900_bib29","doi-asserted-by":"crossref","first-page":"3424","DOI":"10.1109\/TBME.2021.3073380","article-title":"Rapid Estimation of Entire Brain Strain Using Deep Learning Models","volume":"68","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2025111210590533900_bib30","doi-asserted-by":"crossref","first-page":"114913","DOI":"10.1016\/j.cma.2022.114913","article-title":"Real-Time Dynamic Simulation for Highly Accurate Spatiotemporal Brain Deformation From Impact","volume":"394","year":"2022","journal-title":"Comput. Methods Appl. Mech. Eng."},{"issue":"19\u201320","key":"2025111210590533900_bib31","first-page":"2233","article-title":"A Morphologically Individualized Deep Learning Brain Injury Model","volume":"40","year":"2023","journal-title":"J. Neurotrauma"},{"key":"2025111210590533900_bib32","first-page":"139","article-title":"Instantaneous Brain Strain Estimation for Automotive Head Impacts Via Deep Learning","volume":"65","year":"2021","journal-title":"Stapp Car Crash J."},{"key":"2025111210590533900_bib33","doi-asserted-by":"crossref","first-page":"106528","DOI":"10.1016\/j.cmpb.2021.106528","article-title":"Displacement Voxelization to Resolve Mesh-Image Mismatch: Application in Deriving Dense White Matter Fiber Strains","volume":"213","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"2025111210590533900_bib34","doi-asserted-by":"crossref","first-page":"108109","DOI":"10.1016\/j.compbiomed.2024.108109","article-title":"A Computational Pipeline Towards Large-Scale and Multiscale Modeling of Traumatic Axonal Injury","volume":"171","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"2025111210590533900_bib35","unstructured":"Chollet, F., 2023, \u201cTransfer Learning & Fine-Tuning, Keras Documentation,\u201d Keras, Mountain View, CA, accessed July 4, 2025, https:\/\/keras.io\/guides\/transfer_learning\/"},{"issue":"8","key":"2025111210590533900_bib36","doi-asserted-by":"crossref","first-page":"1918","DOI":"10.1007\/s10439-014-1212-4","article-title":"Six Degree-of-Freedom Measurements of Human Mild Traumatic Brain Injury","volume":"43","year":"2015","journal-title":"Ann. Biomed. Eng."},{"key":"2025111210590533900_bib37","doi-asserted-by":"crossref","first-page":"100046","DOI":"10.1016\/j.brain.2022.100046","article-title":"Dynamic Characteristics of Impact-Induced Brain Strain in the Corpus Callosum","volume":"3","year":"2022","journal-title":"Brain Multiphys."},{"key":"2025111210590533900_bib38","volume-title":"Finite Element Method for Engineers From Theory to Practice","year":"2011"},{"issue":"10","key":"2025111210590533900_bib39","doi-asserted-by":"crossref","first-page":"2437","DOI":"10.1007\/s10439-017-1888-3","article-title":"Performance Evaluation of a Pre-Computed Brain Response Atlas in Dummy Head Impacts","volume":"45","year":"2017","journal-title":"Ann. Biomed. Eng."},{"issue":"9","key":"2025111210590533900_bib40","doi-asserted-by":"crossref","first-page":"2781","DOI":"10.1109\/TBME.2024.3392859","article-title":"Effect of Impact Kinematic Filters on Brain Strain Responses in Contact Sports","volume":"71","year":"2024","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2025111210590533900_bib41","doi-asserted-by":"crossref","first-page":"103576","DOI":"10.1016\/j.ijplas.2023.103576","article-title":"Deep Active Learning for Constitutive Modelling of Granular Materials: From Representative Volume Elements to Implicit Finite Element Modelling","volume":"164","year":"2023","journal-title":"Int. J. Plast."},{"issue":"1","key":"2025111210590533900_bib42","first-page":"1","article-title":"Active Learning of Deep Surrogates for PDEs: Application to Metasurface Design","volume":"6","year":"2020","journal-title":"npj Comput. Mater."},{"issue":"3","key":"2025111210590533900_bib43","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1038\/s43588-023-00406-5","article-title":"Uncertainty-Driven Dynamics for Active Learning of Interatomic Potentials","volume":"3","year":"2023","journal-title":"Nat. Comput. Sci."},{"issue":"6","key":"2025111210590533900_bib44","doi-asserted-by":"crossref","first-page":"2301","DOI":"10.1007\/s10237-021-01508-7","article-title":"Toward Subject-Specific Evaluation: Methods of Evaluating Finite Element Brain Models Using Experimental High-Rate Rotational Brain Motion","volume":"20","year":"2021","journal-title":"Biomech. Model. Mechanobiol."},{"issue":"11","key":"2025111210590533900_bib45","doi-asserted-by":"crossref","first-page":"2580","DOI":"10.1007\/s10439-020-02629-3","article-title":"Validation and Comparison of Instrumented Mouthguards for Measuring Head Kinematics and Assessing Brain Deformation in Football Impacts","volume":"48","year":"2020","journal-title":"Ann. Biomed. Eng."},{"key":"2025111210590533900_bib46","first-page":"2282","article-title":"On-Field Head Acceleration Exposure Measurement Using Instrumented Mouthguards: Missing Data Imputation for Complete Exposure Analysis","year":"2025","journal-title":"Ann. Biomed. Eng."},{"issue":"5","key":"2025111210590533900_bib47","doi-asserted-by":"crossref","first-page":"E11","DOI":"10.3171\/2023.8.FOCUS23421","article-title":"Racial and Gender Disparities in Traumatic Brain Injury Clinical Trial Enrollment","volume":"55","year":"2023","journal-title":"Neurosurg. Focus"},{"issue":"6","key":"2025111210590533900_bib48","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1007\/s10439-020-02496-y","article-title":"Displacement- and Strain-Based Discrimination of Head Injury Models Across a Wide Range of Blunt Conditions","volume":"48","year":"2020","journal-title":"Ann. Biomed. Eng."},{"issue":"2","key":"2025111210590533900_bib49","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1089\/neu.2018.5634","article-title":"White Matter Anisotropy for Impact Simulation and Response Sampling in Traumatic Brain Injury","volume":"36","year":"2019","journal-title":"J. Neurotrauma"}],"container-title":["Journal of Biomechanical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/biomechanical\/article-pdf\/148\/2\/021001\/7556430\/bio-25-1179.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/biomechanical\/article-pdf\/148\/2\/021001\/7556430\/bio-25-1179.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T15:59:26Z","timestamp":1762963166000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/biomechanical\/article\/148\/2\/021001\/1225653\/A-Shape-and-Size-Scaled-Deep-Learning-Brain-Injury"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4070192","relation":{},"ISSN":["0148-0731","1528-8951"],"issn-type":[{"value":"0148-0731","type":"print"},{"value":"1528-8951","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"article-number":"021001"}}