Hybrid generative adversarial network based on frequency and spatial domain for histopathological image synthesis.

Journal: BMC bioinformatics
PMID:

Abstract

BACKGROUND: Due to the complexity and cost of preparing histopathological slides, deep learning-based methods have been developed to generate high-quality histological images. However, existing approaches primarily focus on spatial domain information, neglecting the periodic information in the frequency domain and the complementary relationship between the two domains. In this paper, we proposed a generative adversarial network that employs a cross-attention mechanism to extract and fuse features across spatial and frequency domains. The method optimizes frequency domain features using spatial domain guidance and refines spatial features with frequency domain information, preserving key details while eliminating redundancy to generate high-quality histological images.

Authors

  • Qifeng Liu
    Centre for Big Data Research in Health, University of New South Wales, Sydney, Australia.
  • Tao Zhou
    Department of Otorhinolaryngology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China.
  • Chi Cheng
    School of Computer Science and Engineering, University of New South Wales, Sydney, Australia.
  • Jin Ma
    State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China. Electronic address: majin@craes.org.cn.
  • Marzia Hoque Tania
    Centre for Big Data Research in Health, University of New South Wales, Sydney, Australia. m.hoque_tania@unsw.edu.au.