Chinese Journal of Magnetic Resonance ›› 2021, Vol. 38 ›› Issue (3): 367-380.doi: 10.11938/cjmr20212883

• Articles • Previous Articles     Next Articles

Automatic Segmentation of Breast and Fibroglandular Tissues in DCE-MR Images Based on nnU-Net

Lu HUO1,2,Xiao-xin HU3,Qin XIAO3,Ya-jia GU3,Xu CHU1,4,Luan JIANG1,*()   

  1. 1. Center for Advanced Medical Imaging Technology, Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
    3. Department of Radiology, Shanghai Cancer Hospital of Fudan University, Shanghai 200032, China
    4. Digital Industry Group, Shanghai United Imaging Healthcare Co., Ltd., Shanghai 201807, China
  • Received:2021-01-14 Online:2021-09-05 Published:2021-03-12
  • Contact: Luan JIANG E-mail:jiangl@sari.ac.cn

Abstract:

Segmentation of whole breast and fibroglandular tissue (FGT) is an important task for quantitative analysis of breast cancer risk in dynamic contrast enhanced magnetic resonance (DCE-MR) images. In this study, an automated segmentation model based on nnU-Net is proposed to segment the whole breast and FGT in 3D fat-suppressed breast DCE-MR images, taking the advantages of hierarchical image features learning, as well as the fusion of deep features and shallow features. The model could automatically perform preprocessing, data augmentation and dynamic adaptation of network configurations with respect to different imaging parameters. Experimental results show that the method could accurately and efficiently segment the whole breast and FGT in the collected dataset of 3D fat-suppressed breast DCE-MR images with variable imaging characteristics, achieving the average Dice similarity coefficients 0.969±0.007 and 0.893±0.054, respectively, for breast and FGT segmentation.

Key words: breast dynamic contrast enhanced magnetic resonance image, breast segmentation, fibroglandular tissue segmentation, deep learning, nnU-Net model

CLC Number: