Uncertainty-aware domain alignment for anatomical structure segmentation.

Journal: Medical image analysis
Published Date:

Abstract

Automatic and accurate segmentation of anatomical structures on medical images is crucial for detecting various potential diseases. However, the segmentation performance of established deep neural networks may degenerate on different modalities or devices owing to the significant difference across the domains, a problem known as domain shift. In this work, we propose an uncertainty-aware domain alignment framework to address the domain shift problem in the cross-domain Unsupervised Domain Adaptation (UDA) task. Specifically, we design an Uncertainty Estimation and Segmentation Module (UESM) to obtain the uncertainty map estimation. Then, a novel Uncertainty-aware Cross Entropy (UCE) loss is proposed to leverage the uncertainty information to boost the segmentation performance on highly uncertain regions. To further improve the performance in the UDA task, an Uncertainty-aware Self-Training (UST) strategy is developed to choose the optimal target samples by uncertainty guidance. In addition, the Uncertainty Feature Recalibration Module (UFRM) is applied to enforce the framework to minimize the cross-domain discrepancy. The proposed framework is evaluated on a private cross-device Optical Coherence Tomography (OCT) dataset and a public cross-modality cardiac dataset released by MMWHS 2017. Extensive experiments indicate that the proposed UESM is both efficient and effective for the uncertainty estimation in the UDA task, achieving state-of-the-art performance on both cross-modality and cross-device datasets.

Authors

  • Cheng Bian
    Tencent Jarvis Lab, Shenzhen, 518057, China.
  • Chenglang Yuan
    School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China.
  • Jiexiang Wang
  • Meng Li
    Co-Innovation Center for the Sustainable Forestry in Southern China; Cerasus Research Center; College of Biology and the Environment, Nanjing Forestry University, Nanjing, China.
  • Xin Yang
    Department of Oral Maxillofacial-Head Neck Oncology, Ninth People's Hospital, College of Stomatology, Shanghai Jiao Tong University School of Medicine, National Clinical Research Center for Oral Diseases, Shanghai Key Laboratory of Stomatology & Shanghai Research Institute of Stomatology, Shanghai, China.
  • Shuang Yu
    College of Life Science and Engineering, Lanzhou University of TechnologyLanzhou 730050, P. R. China; The Key Lab of Screening, Evaluation and Advanced Processing of TCM and Tibetan Medicine, Education Department of Gansu Provincial GovernmentLanzhou 730050, P. R. China.
  • Kai Ma
    Tencent Jarvis Lab, Shenzhen, 518057, China.
  • Jin Yuan
    State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sunyat-sen University, Guangzhou, 510060, China.
  • Yefeng Zheng