T1-weighted (T1-w) anatomical magnetic resonance imaging (MRI) enable us to identify injuries (e.g., extent, location, type of lesion, size etc.) within the brains of individuals with moderate-to-severe traumatic brain injury (ms-TBI). Lesion segmentation is a key step prior to running advanced neuroimaging analyses (such as connectomics, tractography); however, to date, no automated lesion segmentation tools have been developed for T1-w images of patients with ms-TBI. To find a solution to this, we established this second edition of the MICCAI challenge with two key improvements. First, the number of images available for training was increased. All images were shared through the Enhancing NeuroImaging Genetics through Meta-Analysis (ENIGMA) Brain Injury working group. Overall, 1100 T1-w scans from individuals with ms-TBI across 12 sites. Data from 875 images underwent manual lesion segmentation using a team of 13 manual raters. For these analyses, 552 images were used in the training dataset, 100 for validation, and 223 for the final test set. Secondly, the metrics used to rank teams based on performance were improved to better reflect the dual nature of the detection and segmentation task at hand by looking at the accuracy of images with visible lesions, and those without visible lesions separately. During the validation phase, 19 submissions were received, and 9 teams submitted the final test set.