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

Jennifer J Muller; Ruixuan Wang; Devon Milddleton; Mahdi Alizadeh; Ki Chang Kang; Ryan Hryczyk; George Zabrecky; Chloe Hriso; Emily Navarreto; Nancy Wintering; Anthony J Bazzan; Chengyuan Wu; Daniel A Monti; Xun Jiao; Qianhong Wu; Andrew B Newberg; Feroze B Mohamed

doi:10.3389/fnins.2023.1182509

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

Front Neurosci. 2023 Aug 24:17:1182509. doi: 10.3389/fnins.2023.1182509. eCollection 2023.

Authors

Jennifer J Muller^#^{1

2}, Ruixuan Wang^#^{1

2}, Devon Milddleton², Mahdi Alizadeh², Ki Chang Kang², Ryan Hryczyk², George Zabrecky³, Chloe Hriso³, Emily Navarreto³, Nancy Wintering³, Anthony J Bazzan³, Chengyuan Wu⁴, Daniel A Monti³, Xun Jiao¹, Qianhong Wu¹, Andrew B Newberg³, Feroze B Mohamed²

Affiliations

¹ College of Engineering, Villanova University, Villanova, PA, United States.
² Department of Radiology, Thomas Jefferson University, Philadelphia, PA, United States.
³ Marcus Institute of Integrative Health, Thomas Jefferson University, Philadelphia, PA, United States.
⁴ Vickie and Jack Farber Institute for Neuroscience, Thomas Jefferson University, Philadelphia, PA, United States.

^# Contributed equally.

Abstract

Background and purpose: Traumatic brain injury (TBI) 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 diffusion tensor imaging (DTI) and neurite orientation dispersion imaging (NODDI) to develop biomarkers to infer symptom severity and determine whether 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 extracted the useful features from the hybrid diffusion imaging (HYDI) data and then used supervised learning algorithms to classify the outcome of TBI. We developed three models based on DTI, NODDI, and T1-weighted imaging, and we compared the accuracy results across different models.

Results: Compared with the conventional T1-weighted imaging-based classification with an accuracy of 51.7-56.8%, our machine learning-based models achieved 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-weighted imaging. The results suggest that advanced algorithms can be developed for inferring symptoms of chronic brain injury using feature selection and diffusion-weighted imaging.

Keywords: diffusion tensor imaging (DTI); hybrid diffusion imaging; machine learning; neurite orientation dispersion and density imaging (NODDI); traumatic brain injury.