Machine learning-based classification of chronic traumatic brain injury using hybrid diffusion imaging

BACKGROUND AND PURPOSE: Traumatic brain injury can cause progressive neuropathology that leads to chronic impairments, creating a need for biomarkers to detect and monitor this condition to improve outcomes. This study aimed to analyze the ability of data-driven analysis of DTI and NODDI to develop biomarkers to predict symptom severity and determine if they outperform conventional T1-weighted imaging. MATERIALS AND METHODS: A machine learning-based model was developed using a dataset of hybrid diffusion imaging of patients with chronic traumatic brain injury. We first extract the useful features from the HYDI data and then use supervised learning algorithms to classify the outcome of traumatic brain injury. We developed three models based on DTI, NODDI, and T1-imaging, and we compare the accuracy results across different models. RESULTS: Compared with the conventional T1-imaging-based classification with an accuracy of 51.7 – 56.8%, our machine learning-based models achieve significantly better results with DTI-based models at 58.7– 73.0% accuracy, and NODDI with an accuracy of 64.0 – 72.3%. CONCLUSION: The machine learning-based feature selection and classification algorithm based on hybrid diffusion features significantly outperform conventional T1-imaging. The results suggest that advanced algorithms can be developed for predicting symptoms of chronic brain injury using feature selection and diffusion-weighted imaging.