Rapid Prediction of Brain Injury Pattern in mTBI by Combining FE Analysis With a Machine-Learning Based Approach

Abstract

Mild traumatic brain injury (mTBI) is a significant issue worldwide. Public awareness of the dangers of mTBI has increased sharply in recent years, yet there is no easy-to-use tool available for early detection and post injury management. Computational models of the head impact, usually in the form of finite element analysis, are a method of choice for characterizing how mechanical impacts lead to brain damage by causing high strains in certain regions of the brain. However, those models require a prohibitively large amount of computational power as well as pre and post processing expertise, making them unrealistic to be used in clinical settings. In this study, we propose a framework that combines finite element analysis with a machine learning based approach where a large number of pre-computed FE results are used to train a statistical model. We analyzed a number of different head impact scenarios in which a football player would sustain a minor brain injury and computed brain internal strain patterns. These pre-computed strain patterns were then used to train a partial least squares regression model to be able to predict the general strain pattern and the location and magnitude of peak strains. Our models were able to predict the overall distribution pattern, including the location of the peak strain, with an average error of 3%. The peak strain magnitudes were also predicted accurately with the average error of 9% at almost real time speed (less than 10 seconds). This model may play an important role in developing a diagnostic tool for mTBI that can predict the severity of head impacts. INDEX TERMS diffusion tensor imaging, finite element analysis, magnetic resonance imaging, mild traumatic brain injury, partial least squares regression

Analyzing the changes in the brain material properties after a mild traumatic brain injury—A pilot study

“…We have developed a subject-specific FE model of the human brain using their MR images. 11,31 However, the material properties for this model came from the literature, limiting its subject-specificity to the geometry and white matter fiber tracts only. Therefore, the location-specific material properties obtained from our study along with the MRI scans taken both pre and post-impact are being used to create a completely subject-specific finite element model (both geometry and material propertywise), which will be the first fully subject-specific brain FE model.…”

“…Moreover, one of the aims of our overall study is to create a subject‐specific computational model of the sheep brain for mTBI. We have developed a subject‐specific FE model of the human brain using their MR images 11,31 . However, the material properties for this model came from the literature, limiting its subject‐specificity to the geometry and white matter fiber tracts only.…”

“…Some biomechanical studies on TBI injury mechanisms such as diffuse axonal injury suggest that brain material responses affect the pattern of white matter injuries 7,10 . In fact, we have developed such model and showed that the material properties obtained from MR images are critical in predicting brain damage patterns 11 . As such, it is vital to accurately characterize the relationship between head motion from the impact and the subsequent responses of the brain tissues in different regions of the brain.…”

Robust Quantification of Regional Patterns of Migration in Three-Dimensional Cell Culture Models

“…One way of analysing regional migration is to create a computational model of the collective cell migration shape and measure the shape changes over time. In computational image analysis, shape changes can be quantified by measuring the amount of deformation between original undeformed and deformed states [25], which is often described as strain. This has advantages over other methods that measure quantitative shape features, such as area and length, because the strain-based method allows more detailed and region-specific analysis in the cell migration patterns.…”

“…One method that allows such analysis is Finite Element (FE) models, which have been used extensively in various bioengineering related problems such as joint biomechanics [26,27], tissue deformation [28] and injury prediction [25]. FE analysis has also been used on a microscale such as the work by Saeed and Weihs who simulated a 3D FE cell model and investigated the cell's morphology changes as it underwent uniformly applied compressions [29].…”