Accurate segmentation of infant brain MR images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) in this critical developmental phase is of fundamental importance in studying the normal and abnormal early brain development. At around 6 months of age, the intensity ranges of voxels in GM and WM in structural MR images are largely overlapping (especially around the cortical regions), thus leading to the lowest tissue contrast and creating the most challenge for tissue segmentation. In 2017, we have successfully organized iSeg-2017 Challenge by providing 10 training subjects and 13 testing subjects chosen from the Multi-visit Advanced Pediatric (MAP) Brain Imaging Study. So far, 40+ teams in the world have participated in iSeg-2017. Please have a check on the review aricle on iSeg-2017: IEEE Transactions on Medical Imaging, 38(9): 2219-2230, 2019. However, one of their major common limitations is that their trained models may not be applicable to the images acquired from different sites, scanners or imaging protocols.
This challenge aims to promote automatic segmentation algorithms on 6-month infant brain MRI from multiple sites.