AIMS TBI - Automated Identification of Moderate-Severe Traumatic Brain Injury Lesions

Moderate to Severe Traumatic Brain Injury (msTBI) is caused by external forces (eg: traffic accidents, falls, sports) causing the brain to move rapidly within the skull, resulting in complex pathophysiological changes. Primary injuries arising from the initial forces can include haematoma, hemorrhages, and contusions among others. These primary injuries subsequently induce a cascade of secondary injuries that evolve over hours to days including gliosis, encephalomalacia and life threatening disorders such as raised intracranial pressure, which can require acute surgical intervention. Each of these primary, secondary and surgery related processes has the potential to cause structural deformation in the brain. Each patient with msTBI has a unique accumulation of these structural changes, contributing to extremely heterogeneous lesions, considered a hallmark of msTBI. These lesions differ from other common brain pathologies (stroke, MS, brain tumor) in that they can be both focal or diffuse, varying in size, number and laterality, extending through multiple tissue types (GM/WM/CSF), and can also occur in homologous regions of both hemispheres. Lesions such as these can complicate image registration, normalization, and are known to introduce both local and global errors in brain parcellation. While multiple tools exist to compensate for lesions in neuroimaging pre-processing (HD_Bet, VBG, FastSurfer), many require the time consuming manual creation of lesion masks and subsequent manual quality assessment. Furthermore, in our experience, methods that have been developed for lesions of different etiologies (e.g. stroke, tumors) do not perform well in TBI. 
 
In the absence of appropriate processing tools, current lesion compensation techniques in msTBI include ignoring the lesions (resulting in unreliable findings), excluding msTBI patients with large lesions (limiting the generalizability), or manual segmentation of lesions prior to analysis (time consuming). This last step of manual segmentation is often only feasible in smaller, single-site studies which lack the statistical power to perform subgroup analyses (i.e.,divide the TBI sample according to lesion characteristics). These restrictive approaches limit the ability to investigate how factors such as type of injury (axonal injury, focal lesions, and diffuse microlesions), severity of brain injury (mild, moderate, severe), and presence of comorbid injuries or complications (especially those that affect pulmonary and cardiovascular function and post-traumatic seizure) impact the relationship between lesion characteristics and patient’s functional outcomes. To capture this information, msTBI researchers need access to an accurate, automatic lesion segmentation algorithm trained on large consortium analyses of multi‐cohort MRI datasets, where MRI data is pooled/aggregated across centers. Whilst a handful of TBI specific algorithms exist, they require either multiple image types (T1, T2, FLAIR, GE & PD) or can run on only CT images. However, the necessity for multiple image types limits the ability of large-scale consortia to aggregate common MRI scans across sites and there is a larger variability in scanning sequence parameters in other MRI modalities (such as diffusion MRI). Therefore, this challenge will focus on identifying lesions in T1-weighted MRI data only as it is the most common MRI scan across our ENIGMA TBI consortium. Moreover, anatomical T1 weighted MRI scans show less parameter variation (e.g. 1 mm3 voxel size was relatively common in our previous published work. 
 
The Enhancing NeuroImaging Genetics through Meta-Analysis (ENIGMA) Consortium is a global collaborative framework for neuroimaging researchers with >50 working groups examining various neurological, psychiatric, and developmental disorders. The ENIGMA TBI working group formed in 2016, and has since grown to over 200 researchers. Within the ENIGMA TBI WG, there are subgroups based on the TBI patient population, two of which focus on msTBI - Pediatric msTBI and Adult msTBI. This challenge will leverage the data shared with these subgroups. There are nearly 1,300 T1-weighted MRI datasets from msTBI patients across these groups (age range=5-85 years) and based on preliminary rates of manual lesion identification in the dataset, we expect that approximately 1,000 datasets will include lesions that are visible on T1w MRI. 800 of these will be made available for the purposes of this challenge. Advances in lesion segmentation and the implementation of an accurate lesion mask resulting from the lesion segmentation into the next image processing and analyses (such as parcellation, functional connectivity analyses, connectomics, fixel-based analysis) will allow for a more accurate prognostication and may improve patients long-term outcomes.