Benchmark on Automatic Six-Month-Old Infant Brain Segmentation Algorithms: The iSeg-2017 Challenge

TLDR

Accurate segmentation of six‑month infant brain MR images into white matter, gray matter, and cerebrospinal fluid is essential for studying brain growth and neurodevelopmental disorders, yet the isointense T1‑ and T2‑weighted signals at this age make WM and GM indistinguishable, and few studies have addressed this challenge. The iSeg‑2017 challenge supplies six‑month infant MR datasets with manual labels to stimulate methodological development and benchmark segmentation algorithms. We review the eight top‑ranked segmentation methods from the challenge, describing their pipelines, implementations, and providing source code links. We discuss limitations of current methods, propose future directions, and hope the dataset and paper will guide further methodological advances.

Abstract

Accurate segmentation of infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid is an indispensable foundation for early studying of brain growth patterns and morphological changes in neurodevelopmental disorders. Nevertheless, in the isointense phase (approximately 6-9 months of age), due to inherent myelination and maturation process, WM and GM exhibit similar levels of intensity in both T1-weighted and T2-weighted MR images, making tissue segmentation very challenging. Although many efforts were devoted to brain segmentation, only a few studies have focused on the segmentation of six-month infant brain images. With the idea of boosting methodological development in the community, iSeg-2017 challenge (http://iseg2017.web.unc.edu) provides a set of six-month infant subjects with manual labels for training and testing the participating methods. Among the 21 automatic segmentation methods participating in iSeg-2017, we review the eight top-ranked teams, in terms of Dice ratio, modified Hausdorff distance, and average surface distance, and introduce their pipelines, implementations, as well as source codes. We further discuss the limitations and possible future directions. We hope the dataset in iSeg-2017, and this paper could provide insights into methodological development for the community.