ABCnet: Adversarial bias correction network for infant brain MR images

Liangjun Chen, Zhengwang Wu, Dan Hu, Fan Wang, J. Keith Smith, Weili Lin, Li Wang, Dinggang Shen, Gang Li

Abstract: Highlights•The first investigation of correcting the intensity nonuniformity of infant brain MR images.•The first employment of a 3D adversarial framework to accurately predict the bias fields.•A novel local intensity uniformity loss to cope with the dynamic and heterogeneous intensity changes in infant brain MR images.•Extensive evaluations on a total of 1492 T1w and T2w MR images from neonates, infants, and adults show state-of-the-art performance and wide applicability of our method.