The auto segmentation for cardiac structures using a dual-input deep learning network based on vision saliency and transformer.

Journal: Journal of applied clinical medical physics
Published Date: Apr 1, 2022

Abstract

PURPOSE: Accurate segmentation of cardiac structures on coronary CT angiography (CCTA) images is crucial for the morphological analysis, measurement, and functional evaluation. In this study, we achieve accurate automatic segmentation of cardiac structures on CCTA image by adopting an innovative deep learning method based on visual attention mechanism and transformer network, and its practical application value is discussed.

Authors

  • Jing Wang
    Endoscopy Center, Peking University Cancer Hospital and Institute, Beijing, China.
  • Shuyu Wang
    Department of Control Engineering, Northeastern University, Qinhuangdao, Hebei, 066001, PR China. Electronic address: wangshuyu@neuq.edu.cn.
  • Wei Liang
    Department of Radiation Oncology, The First Affiliated Hospital of Anhui Medical University, Hefei, 230022, China.
  • Nan Zhang
    Department of Pulmonary and Critical Care Medicine II, Emergency General Hospital, Beijing, China.
  • Yan Zhang
    Affiliated Hospital of Liaoning University of Traditional Chinese Medicine, Shenyang, 110032, China.

Keywords

External Resources

Popular Topics
Recent Journals