# Concussion classification via deep learning using whole-brain white matter fiber strains

## TL;DR

This study develops a deep learning model that uses whole-brain white matter fiber strains to accurately classify concussions, outperforming traditional scalar metrics and other machine learning methods in NFL injury cases.

## Contribution

It introduces a novel deep learning approach utilizing voxel-wise white matter fiber strains for concussion classification, demonstrating superior performance over existing scalar metrics and classifiers.

## Key findings

- Deep learning achieved higher accuracy and AUC than baseline methods.
- Whole-brain fiber strain features outperform scalar injury metrics.
- Cross-validation confirms the robustness of the deep learning model.

## Abstract

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based deep learning and machine learning classifiers consistently outperformed all scalar injury metrics across all performance categories in cross-validation (e.g., average accuracy of 0.844 vs. 0.746, and average area under the receiver operating curve (AUC) of 0.873 vs. 0.769, respectively, based on the testing dataset). Nevertheless, deep learning achieved the best cross-validation accuracy, sensitivity, and AUC (e.g., accuracy of 0.862 vs. 0.828 and 0.842 for SVM and RF, respectively). These findings demonstrate the superior performances of deep learning in concussion prediction, and suggest its promise for future applications in biomechanical investigations of traumatic brain injury.

---
Source: https://tomesphere.com/paper/1705.04600