Automatic diagnosis for adenomyosis in ultrasound images by deep neural networks.

Journal: European journal of obstetrics, gynecology, and reproductive biology
Published Date:

Abstract

OBJECTIVE: To present a new noninvasive technique for automatic diagnosis of adenomyosis, using a novel end-to-end unified network framework based on transformer networks.

Authors

  • Qinghong Zhao
    Department of Ultrasound in Medicine, Renmin Hospital of Wuhan University, China.
  • Tongyu Yang
    School of Cyber Science and Engineering, Wuhan University, China.
  • Changyong Xu
    IT Department, China Southern Airlines Hubei Branch, Wuhan, China.
  • Jiaqi Hu
    University of Shanghai for Science and Technology, No. 516, Jungong Rd., Shanghai, 200093, Shanghai, China.
  • Yu Shuai
    Department of Ultrasound in Medicine, Renmin Hospital of Wuhan University, China.
  • Hua Zou
    School of Computer Science, Wuhan University, China. Electronic address: zouhua@whu.edu.cn.
  • Wei Hu
    State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China.