DCANet: Dual contextual affinity network for mass segmentation in whole mammograms.

Journal: Medical physics
Published Date: Jul 7, 2021

Abstract

PURPOSE: Breast mass segmentation in mammograms remains a crucial yet challenging topic in computer-aided diagnosis systems. Existing algorithms mainly used mass-centered patches to achieve mass segmentation, which is time-consuming and unstable in clinical diagnosis. Therefore, we aim to directly perform fully automated mass segmentation in whole mammograms with deep learning solutions.

Authors

  • Meng Lou
    School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China.
  • Yunliang Qi
    School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China.
  • Jie Meng
    School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China.
  • Chunbo Xu
    School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China.
  • Yiming Wang
    Teaching Resource Information Service Center, Changchun Institute of Education, Changchun, China.
  • Jiande Pi
    School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China.
  • Yide Ma
    School of Information Science and Engineering, Lanzhou University, No. 222, South Tianshui Road, Lanzhou, Gansu Province, 730000, People's Republic of China. dm880612dm@163.com.

Keywords

External Resources

Popular Topics
Recent Journals