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, for UNC/UMN Baby Connectome Project Consortium

Research output: Contribution to journalArticlepeer-review

Abstract

Automatic correction of intensity nonuniformity (also termed as the bias correction) is an essential step in brain MR image analysis. Existing methods are typically developed for adult brain MR images based on the assumption that the image intensities within the same brain tissue are relatively uniform. However, this assumption is not valid in infant brain MR images, due to the dynamic and regionally-heterogeneous image contrast and appearance changes, which are caused by the underlying spatiotemporally-nonuniform myelination process. Therefore, it is not appropriate to directly use existing methods to correct the infant brain MR images. In this paper, we propose an end-to-end 3D adversarial bias correction network (ABCnet), tailored for direct prediction of bias fields from the input infant brain MR images for bias correction. The “ground-truth” bias fields for training our network are carefully defined by an improved N4 method, which integrates manually-corrected tissue segmentation maps as anatomical prior knowledge. The whole network is trained alternatively by minimizing generative and adversarial losses. To handle the heterogeneous intensity changes, our generative loss includes a tissue-aware local intensity uniformity term to reduce the local intensity variation in the corrected image. Besides, it also integrates two additional terms to enhance the smoothness of the estimated bias field and to improve the robustness of the proposed method, respectively. Comprehensive experiments with different sizes of training datasets have been carried out on a total of 1492 T1w and T2w MR images from neonates, infants, and adults, respectively. Both qualitative and quantitative evaluations on simulated and real datasets consistently demonstrate the superior performance of our ABCnet in both accuracy and efficiency, compared with popularly available methods.

Original languageEnglish
Article number102133
JournalMedical Image Analysis
Volume72
DOIs
Publication statusPublished - 2021 Aug

Keywords

  • Generative adversarial networks (GANs)
  • Infant
  • Intensity nonuniformity
  • MRI

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'ABCnet: Adversarial bias correction network for infant brain MR images'. Together they form a unique fingerprint.

Cite this