Combining Multiple Indices of Diffusion Tensor Imaging Can Better Differentiate Patients with Traumatic Brain Injury from Healthy Subjects

White Matter Alterations in Military Service Members With Remote Mild Traumatic Brain Injury

Importance

Mild traumatic brain injury (mTBI) is the signature injury experienced by military service members and is associated with poor neuropsychiatric outcomes. Yet, there is a lack of reliable clinical tools for mTBI diagnosis and prognosis.

Objective

To examine the white matter microstructure and neuropsychiatric outcomes of service members with a remote history of mTBI (ie, mTBI that occurred over 2 years ago) using diffusion tensor imaging (DTI) and neurite orientation dispersion and density imaging (NODDI).

Design, Setting, and Participants

This case-control study examined 98 male service members enrolled in a study at the National Intrepid Center of Excellence. Eligible participants were active duty status or able to enroll in the Defense Enrollment Eligibility Reporting system, ages 18 to 60 years, and had a remote history of mTBI; controls were matched by age.

Exposures

Remote history of mTBI.

Main Outcomes and Measures

White matter microstructure was assessed using a region-of-interest approach of skeletonized diffusion images, including DTI (fractional anisotropy, mean diffusivity, radial diffusivity and axial diffusivity) and NODDI (orientation dispersion index [ODI], isotropic volume fraction, intra-cellular volume fraction). Neuropsychiatric outcomes associated with posttraumatic stress disorder (PTSD) and postconcussion syndrome were assessed.

Results

A total of 65 male patients with a remote history of mTBI (mean [SD] age, 40.5 [5.0] years) and 33 age-matched male controls (mean [SD] age, 38.9 [5.6] years) were included in analysis. Compared with the control cohort, the 65 service members with mTBI presented with significantly more severe PTSD-like symptoms (mean [SD] PTSD CheckList-Civilian [PCL-C] version scores: control, 19.0 [3.8] vs mTBI, 41.2 [11.6]; P < .001). DTI and NODDI metrics were altered in the mTBI group compared with the control, including intra-cellular volume fraction of the right cortico-spinal tract (β = -0.029, Cohen d = 0.66; P < .001), ODI of the left posterior thalamic radiation (β = -0.006, Cohen d = 0.55; P < .001), and ODI of the left uncinate fasciculus (β = 0.013, Cohen d = 0.61; P < .001). In service members with mTBI, fractional anisotropy of the left uncinate fasciculus was associated with postconcussion syndrome (β = 5.4 × 10-3; P = .003), isotropic volume fraction of the genu of the corpus callosum with PCL-C (β = 4.3 × 10-4; P = .01), and ODI of the left fornix and stria terminalis with PCL-C avoidance scores (β = 1.2 × 10-3; P = .02).

Conclusions and Relevance

In this case-control study of military-related mTBI, the results suggest that advanced magnetic resonance imaging techniques using NODDI can reveal white matter microstructural alterations associated with neuropsychiatric symptoms in the chronic phase of mTBI. Diffusion trends observed throughout widespread white matter regions-of-interest may reflect mechanisms of neurodegeneration as well as postinjury tissue scarring and reorganization.

Clinical performance of a multiparametric MRI-based post concussive syndrome index

Introduction

Diffusion Tensor Imaging (DTI) has revealed measurable changes in the brains of patients with persistent post-concussive syndrome (PCS). Because of inconsistent results in univariate DTI metrics among patients with mild traumatic brain injury (mTBI), there is currently no single objective and reliable MRI index for clinical decision-making in patients with PCS.

Purpose

This study aimed to evaluate the performance of a newly developed PCS Index (PCSI) derived from machine learning of multiparametric magnetic resonance imaging (MRI) data to classify and differentiate subjects with mTBI and PCS history from those without a history of mTBI.

Materials and methods

Data were retrospectively extracted from 139 patients aged between 18 and 60 years with PCS who underwent MRI examinations at 2 weeks to 1-year post-mTBI, as well as from 336 subjects without a history of head trauma. The performance of the PCS Index was assessed by comparing 69 patients with a clinical diagnosis of PCS with 264 control subjects. The PCSI values for patients with PCS were compared based on the mechanism of injury, time interval from injury to MRI examination, sex, history of prior concussion, loss of consciousness, and reported symptoms.

Results

Injured patients had a mean PCSI value of 0.57, compared to the control group, which had a mean PCSI value of 0.12 (p = 8.42e-23) with accuracy of 88%, sensitivity of 64%, and specificity of 95%, respectively. No statistically significant differences were found in the PCSI values when comparing the mechanism of injury, sex, or loss of consciousness.

Conclusion

The PCSI for individuals aged between 18 and 60 years was able to accurately identify patients with post-concussive injuries from 2 weeks to 1-year post-mTBI and differentiate them from the controls. The results of this study suggest that multiparametric MRI-based PCSI has great potential as an objective clinical tool to support the diagnosis, treatment, and follow-up care of patients with post-concussive syndrome. Further research is required to investigate the replicability of this method using other types of clinical MRI scanners.

Brain disease research based on functional magnetic resonance imaging data and machine learning: a review

Brain diseases, including neurodegenerative diseases and neuropsychiatric diseases, have long plagued the lives of the affected populations and caused a huge burden on public health. Functional magnetic resonance imaging (fMRI) is an excellent neuroimaging technology for measuring brain activity, which provides new insight for clinicians to help diagnose brain diseases. In recent years, machine learning methods have displayed superior performance in diagnosing brain diseases compared to conventional methods, attracting great attention from researchers. This paper reviews the representative research of machine learning methods in brain disease diagnosis based on fMRI data in the recent three years, focusing on the most frequent four active brain disease studies, including Alzheimer's disease/mild cognitive impairment, autism spectrum disorders, schizophrenia, and Parkinson's disease. We summarize these 55 articles from multiple perspectives, including the effect of the size of subjects, extracted features, feature selection methods, classification models, validation methods, and corresponding accuracies. Finally, we analyze these articles and introduce future research directions to provide neuroimaging scientists and researchers in the interdisciplinary fields of computing and medicine with new ideas for AI-aided brain disease diagnosis.