1
|
Abstract
The brain injury modeling community has recommended improving model subject specificity and simulation efficiency. Here, we extend an instantaneous (< 1 sec) convolutional neural network (CNN) brain model based on the anisotropic Worcester Head Injury Model (WHIM) V1.0 to account for strain differences due to individual morphological variations. Linear scaling factors relative to the generic WHIM along the three anatomical axes are used as additional CNN inputs. To generate training samples, the WHIM is randomly scaled to pair with augmented head impacts randomly generated from real-world data for simulation. An estimation of voxelized peak maximum principal strain of the whole-brain is said to be successful when the linear regression slope and Pearson's correlation coefficient relative to directly simulated do not deviate from 1.0 (when identical) by more than 0.1. Despite a modest training dataset (N = 1363 vs. ∼5.7 k previously), the individualized CNN achieves a success rate of 86.2% in cross-validation for scaled model responses, and 92.1% for independent generic model testing for impacts considered as complete capture of kinematic events. Using 11 scaled subject-specific models (with scaling factors determined from pre-established regression models based on head dimensions and sex and age information, and notably, without neuroimages), the morphologically individualized CNN remains accurate for impacts that also yield successful estimations for the generic WHIM. The individualized CNN instantly estimates subject-specific and spatially detailed peak strains of the entire brain and thus, supersedes others that report a scalar peak strain value incapable of informing the location of occurrence. This tool could be especially useful for youths and females due to their anticipated greater morphological differences relative to the generic model, even without the need for individual neuroimages. It has potential for a wide range of applications for injury mitigation purposes and the design of head protective gears. The voxelized strains also allow for convenient data sharing and promote collaboration among research groups.
Collapse
Affiliation(s)
- Nan Lin
- Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, Massachusetts, USA
| | - Shaoju Wu
- Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, Massachusetts, USA
| | - Songbai Ji
- Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, Massachusetts, USA
- Department of Mechanical Engineering, Worcester Polytechnic Institute, Worcester, Massachusetts, USA
| |
Collapse
|
2
|
Lin N, Wu S, Wu Z, Ji S. Efficient Generation of Pretraining Samples for Developing a Deep Learning Brain Injury Model via Transfer Learning. Ann Biomed Eng 2023:10.1007/s10439-023-03354-3. [PMID: 37642795 DOI: 10.1007/s10439-023-03354-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2023] [Accepted: 08/18/2023] [Indexed: 08/31/2023]
Abstract
The large amount of training samples required to develop a deep learning brain injury model demands enormous computational resources. Here, we study how a transformer neural network (TNN) of high accuracy can be used to efficiently generate pretraining samples for a convolutional neural network (CNN) brain injury model to reduce computational cost. The samples use synthetic impacts emulating real-world events or augmented impacts generated from limited measured impacts. First, we verify that the TNN remains highly accurate for the two impact types (N = 100 each; [Formula: see text] of 0.948-0.967 with root mean squared error, RMSE, ~ 0.01, for voxelized peak strains). The TNN-estimated samples (1000-5000 for each data type) are then used to pretrain a CNN, which is further finetuned using directly simulated training samples (250-5000). An independent measured impact dataset considered of complete capture of impact event is used to assess estimation accuracy (N = 191). We find that pretraining can significantly improve CNN accuracy via transfer learning compared to a baseline CNN without pretraining. It is most effective when the finetuning dataset is relatively small (e.g., 2000-4000 pretraining synthetic or augmented samples improves success rate from 0.72 to 0.81 with 500 finetuning samples). When finetuning samples reach 3000 or more, no obvious improvement occurs from pretraining. These results support using the TNN to rapidly generate pretraining samples to facilitate a more efficient training strategy for future deep learning brain models, by limiting the number of costly direct simulations from an alternative baseline model. This study could contribute to a wider adoption of deep learning brain injury models for large-scale predictive modeling and ultimately, enhancing safety protocols and protective equipment.
Collapse
Affiliation(s)
- Nan Lin
- Department of Biomedical Engineering, Worcester Polytechnic Institute, 60 Prescott Street, Worcester, MA, 01605, USA
| | - Shaoju Wu
- Department of Biomedical Engineering, Worcester Polytechnic Institute, 60 Prescott Street, Worcester, MA, 01605, USA
| | - Zheyang Wu
- Mathematical Sciences, Worcester Polytechnic Institute, Worcester, MA, 01609, USA
| | - Songbai Ji
- Department of Biomedical Engineering, Worcester Polytechnic Institute, 60 Prescott Street, Worcester, MA, 01605, USA.
- Department of Mechanical Engineering, Worcester Polytechnic Institute, 100 Institute Road, Worcester, MA, 01609, USA.
| |
Collapse
|
3
|
Chavoshnejad P, Chen L, Yu X, Hou J, Filla N, Zhu D, Liu T, Li G, Razavi MJ, Wang X. An integrated finite element method and machine learning algorithm for brain morphology prediction. Cereb Cortex 2023; 33:9354-9366. [PMID: 37288479 PMCID: PMC10393506 DOI: 10.1093/cercor/bhad208] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2023] [Revised: 05/18/2023] [Accepted: 05/19/2023] [Indexed: 06/09/2023] Open
Abstract
The human brain development experiences a complex evolving cortical folding from a smooth surface to a convoluted ensemble of folds. Computational modeling of brain development has played an essential role in better understanding the process of cortical folding, but still leaves many questions to be answered. A major challenge faced by computational models is how to create massive brain developmental simulations with affordable computational sources to complement neuroimaging data and provide reliable predictions for brain folding. In this study, we leveraged the power of machine learning in data augmentation and prediction to develop a machine-learning-based finite element surrogate model to expedite brain computational simulations, predict brain folding morphology, and explore the underlying folding mechanism. To do so, massive finite element method (FEM) mechanical models were run to simulate brain development using the predefined brain patch growth models with adjustable surface curvature. Then, a GAN-based machine learning model was trained and validated with these produced computational data to predict brain folding morphology given a predefined initial configuration. The results indicate that the machine learning models can predict the complex morphology of folding patterns, including 3-hinge gyral folds. The close agreement between the folding patterns observed in FEM results and those predicted by machine learning models validate the feasibility of the proposed approach, offering a promising avenue to predict the brain development with given fetal brain configurations.
Collapse
Affiliation(s)
- Poorya Chavoshnejad
- Department of Mechanical Engineering, Binghamton University, Binghamton, NY 13902, United States
| | - Liangjun Chen
- Department of Radiology and BRIC, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| | - Xiaowei Yu
- Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX 76019, United States
| | - Jixin Hou
- School of ECAM, University of Georgia, Athens, GA 30602, United States
| | - Nicholas Filla
- School of ECAM, University of Georgia, Athens, GA 30602, United States
| | - Dajiang Zhu
- Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX 76019, United States
| | - Tianming Liu
- School of Computing, University of Georgia, Athens, GA 30602, United States
| | - Gang Li
- Department of Radiology and BRIC, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States
| | - Mir Jalil Razavi
- Department of Mechanical Engineering, Binghamton University, Binghamton, NY 13902, United States
| | - Xianqiao Wang
- School of ECAM, University of Georgia, Athens, GA 30602, United States
| |
Collapse
|
4
|
Hanna ME, Pfister BJ. Advancements in in vitro models of traumatic brain injury. CURRENT OPINION IN BIOMEDICAL ENGINEERING 2022. [DOI: 10.1016/j.cobme.2022.100430] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
5
|
Biochemical Pathways of Cellular Mechanosensing/Mechanotransduction and Their Role in Neurodegenerative Diseases Pathogenesis. Cells 2022; 11:cells11193093. [PMID: 36231055 PMCID: PMC9563116 DOI: 10.3390/cells11193093] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Revised: 09/27/2022] [Accepted: 09/29/2022] [Indexed: 12/11/2022] Open
Abstract
In this review, we shed light on recent advances regarding the characterization of biochemical pathways of cellular mechanosensing and mechanotransduction with particular attention to their role in neurodegenerative disease pathogenesis. While the mechanistic components of these pathways are mostly uncovered today, the crosstalk between mechanical forces and soluble intracellular signaling is still not fully elucidated. Here, we recapitulate the general concepts of mechanobiology and the mechanisms that govern the mechanosensing and mechanotransduction processes, and we examine the crosstalk between mechanical stimuli and intracellular biochemical response, highlighting their effect on cellular organelles' homeostasis and dysfunction. In particular, we discuss the current knowledge about the translation of mechanosignaling into biochemical signaling, focusing on those diseases that encompass metabolic accumulation of mutant proteins and have as primary characteristics the formation of pathological intracellular aggregates, such as Alzheimer's Disease, Huntington's Disease, Amyotrophic Lateral Sclerosis and Parkinson's Disease. Overall, recent findings elucidate how mechanosensing and mechanotransduction pathways may be crucial to understand the pathogenic mechanisms underlying neurodegenerative diseases and emphasize the importance of these pathways for identifying potential therapeutic targets.
Collapse
|
6
|
Wu S, Zhao W, Barbat S, Ruan J, Ji S. Instantaneous Brain Strain Estimation for Automotive Head Impacts via Deep Learning. STAPP CAR CRASH JOURNAL 2021; 65:139-162. [PMID: 35512787 DOI: 10.4271/2021-22-0006] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
Efficient brain strain estimation is critical for routine application of a head injury model. Lately, a convolutional neural network (CNN) has been successfully developed to estimate spatially detailed brain strains instantly and accurately in contact sports. Here, we extend its application to automotive head impacts, where impact profiles are typically more complex with longer durations. Head impact kinematics (N=458) from two public databases were used to generate augmented impacts (N=2694). They were simulated using the anisotropic Worcester Head Injury Model (WHIM) V1.0, which provided baseline elementwise peak maximum principal strain (MPS). For each augmented impact, rotational velocity (vrot) and the corresponding rotational acceleration (arot) profiles were concatenated as static images to serve as CNN input. Three training strategies were evaluated: 1) "baseline", using random initial weights; 2) "transfer learning", using weight transfer from a previous CNN model trained on head impacts drawn from contact sports; and 3) "combined training", combining previous training data from contact sports (N=5661) for training. The combined training achieved the best performances. For peak MPS, the CNN achieved a coefficient of determination (R2) of 0.932 and root mean squared error (RMSE) of 0.031 for the real-world testing dataset. It also achieved a success rate of 60.5% and 94.8% for elementwise MPS, where the linear regression slope, k, and correlation coefficient, r, between estimated and simulated MPS did not deviate from 1.0 (when identical) by more than 0.1 and 0.2, respectively. Cumulative strain damage measure (CSDM) from the CNN estimation was also highly accurate compared to those from direct simulation across a range of thresholds (R2 of 0.899-0.943 with RMSE of 0.054-0.069). Finally, the CNN achieved an average k and r of 0.98±0.12 and 0.90±0.07, respectively, for six reconstructed car crash impacts drawn from two other sources independent of the training dataset. Importantly, the CNN is able to efficiently estimate elementwise MPS with sufficient accuracy while conventional kinematic injury metrics cannot. Therefore, the CNN has the potential to supersede current kinematic injury metrics that can only approximate a global peak MPS or CSDM. The CNN technique developed here may offer enhanced utility in the design and development of head protective countermeasures, including in the automotive industry. This is the first study aimed at instantly estimating spatially detailed brain strains for automotive head impacts, which employs >8.8 thousand impact simulations generated from ~1.5 years of nonstop computations on a high-performance computing platform.
Collapse
Affiliation(s)
- Shaoju Wu
- Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01605, USA
| | - Wei Zhao
- Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01605, USA
| | | | - Jesse Ruan
- Tianjin University of Science and Technology, Tianjin, 300222, China
| | - Songbai Ji
- Department of Biomedical Engineering, Worcester Polytechnic Institute, Worcester, MA 01605, USA
| |
Collapse
|