Connectome mapping with edge density imaging differentiates pediatric mild traumatic brain injury from typically developing controls: proof of concept

Abstract

Background-Although acute neurologic impairment might be transient, other long-term effects can be observed with mild traumatic brain injury. However, when pediatric patients with mild traumatic brain injury present for medical care, conventional imaging with CT and MR imaging often does not reveal abnormalities.Objective-To determine whether edge density imaging can separate pediatric mild traumatic brain injury from typically developing controls.Materials and methods-Subjects were recruited as part of the "Therapeutic Resources for Attention Improvement using Neuroimaging in Traumatic Brain Injury" (TRAIN-TBI) study. We included 24 adolescents (χ=14.1 years of age, σ=1.6 years, range 10-16 years), 14 with mild traumatic brain injury (TBI) and 10 typically developing controls. Neurocognitive assessments included the pediatric version of the California Verbal Learning Test (CVLT) and the Attention Network Task (ANT). Diffusion MR imaging was acquired on a 3-tesla (T) scanner. Edge density images were computed utilizing fiber tractography. Principal component analysis (PCA) and support vector machines (SVM) were used in an exploratory analysis to separate mild TBI and control groups. The diagnostic accuracy of edge density imaging, neurocognitive tests, and fractional anisotropy (FA) from diffusion tensor imaging (DTI) was computed with two-sample ttests and receiver operating characteristic (ROC) metrics.Results-Support vector machine-principal component analysis of edge density imaging maps identified three white matter regions distinguishing pediatric mild TBI from controls. The bilateral tapetum, sagittal stratum, and callosal splenium identified mild TBI subjects with sensitivity of Terms of use and reuse: academic research for non-commercial purposes, see here for full terms. http://www.springer.com/gb/openaccess/authors-rights/aam-terms-v1

Structural connectome differences in pediatric mild traumatic brain and orthopedic injury

“…This may limit scientific understanding of outcomes following pediatric mTBI, which typically causes nonspecific postconcussive symptoms and subtle, heterogeneous, and diffuse alterations in brain tissue (Lumba-Brown et al, 2018;Mayer et al, 2018). Instead, sophisticated network-based approaches, particularly structural connectomics (i.e., applying graph theory and dMRI techniques to study white matter connections among distributed brain regions), are proving superior in identifying a biomarker of mTBI in adults and pediatric traumatic brain injury (TBI) more generally (i.e., across severities) that is sensitive and specific enough for clinical use (Raji et al, 2020;Rubinov & Sporns, 2010;Yuan, Treble-Barna, Sohlberg, Harn, & Wade, 2017).…”

Safeguarding Athletes Against Head Injuries Through Advances in Technology: A Scoping Review of the Uses of Machine Learning in the Management of Sports-Related Concussion

“…This could be a valuable way of mitigating the millions of SRC incidents worldwide every year. The remaining 9 studies [excluding those of Wu et al ( 2019 ) and Thanjavur et al ( 2021 )] are based on machine learning algorithms, such as TotalBoost (McNerny et al, 2019 ), Support Vector Machine (SVM) (Falcone et al, 2013 ; Tremblay et al, 2017 ; Raji et al, 2020 ), or Kohenn's Self-Organizing Map (SOM) (Visscher et al, 2019 ).…”

“…These sports include American football, ice hockey, soccer, basketball, lacrosse, rugby, volleyball, water polo and handball. The most prominent team sport is American football, with seven studies dedicated to this sport (see Table 2 ), as well as being included in 9 of 11 studies with mixed sports (Cao et al, 2008 ; Helfer et al, 2014 ; Tremblay et al, 2017 ; Reynolds et al, 2018 ; Bergeron et al, 2019 ; Wu et al, 2019 ; Raji et al, 2020 ; Bazarian et al, 2021 ; Castellanos et al, 2021 ). While many individual sports are included in the mixed samples, such as track and field (Helfer et al, 2014 ; Castellanos et al, 2021 ), mixed martial arts (Wu et al, 2019 ), snowboard (Visscher et al, 2019 ), skiing (Raji et al, 2020 ), tennis (Castellanos et al, 2021 ) and wrestling (Bergeron et al, 2019 ), there is only one individual sport with its own study: boxing (Falcone et al, 2013 ).…”

MaPPeRTrac: A Massively Parallel, Portable, and Reproducible Tractography Pipeline

“…Tractography results are binarized to create a mask of white matter voxels needed to connect each pair of cortical/subcortical regions. This uses a consensus connectome based on (Raji et al, 2020). The resulting connectome can be processed into an edge density image (EDI), which counts of the number of edges that pass through each voxel. s4_render.py – runs the VTK render suite on EDI outputs using a copy of vtkpython bundled in the Singularity container.…”

“…Connectomes can be evaluated using a plethora of well-developed techniques based on graph theory and matrix analysis. As a result, they show great promise towards the timely diagnosis and treatment of disorders of white matter connectivity such as traumatic brain injury (TBI) (Raji et al, 2020).…”