TY - JOUR
T1 - ABCnet
T2 - Adversarial bias correction network for infant brain MR images
AU - Chen, Liangjun
AU - Wu, Zhengwang
AU - Hu, Dan
AU - Wang, Fan
AU - Smith, J. Keith
AU - Lin, Weili
AU - Wang, Li
AU - Shen, Dinggang
AU - Li, Gang
AU - Consortium, for UNC/UMN Baby Connectome Project
N1 - Funding Information:
This work was partially supported by NIH grants (MH116225, MH117943, and MH123202). This work also utilizes approaches developed by an NIH grant (1U01MH110274) and the efforts of the UNC/UMN Baby Connectome Project Consortium.
Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/8
Y1 - 2021/8
N2 - 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.
AB - 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.
KW - Generative adversarial networks (GANs)
KW - Infant
KW - Intensity nonuniformity
KW - MRI
UR - http://www.scopus.com/inward/record.url?scp=85109465122&partnerID=8YFLogxK
U2 - 10.1016/j.media.2021.102133
DO - 10.1016/j.media.2021.102133
M3 - Article
C2 - 34225011
AN - SCOPUS:85109465122
VL - 72
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
M1 - 102133
ER -