FDB-Net: Fusion double branch network combining CNN and transformer for medical image segmentation.

Journal: Journal of X-ray science and technology
Published Date:

Abstract

BACKGROUND: The rapid development of deep learning techniques has greatly improved the performance of medical image segmentation, and medical image segmentation networks based on convolutional neural networks and Transformer have been widely used in this field. However, due to the limitation of the restricted receptive field of convolutional operation and the lack of local fine information extraction ability of the self-attention mechanism in Transformer, the current neural networks with pure convolutional or Transformer structure as the backbone still perform poorly in medical image segmentation.

Authors

  • Zhongchuan Jiang
    State Key Laboratory of Public Big Data, Guiyang, China.
  • Yun Wu
    Department of Biomedical Engineering, University at Buffalo, The State University of New York, Buffalo, NY 14260, USA.
  • Lei Huang
    School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China.
  • Maohua Gu
    State Key Laboratory of Public Big Data, Guiyang, China.