Improved deep learning for automatic localisation and segmentation of rectal cancer on T2-weighted MRI.

Journal: Journal of medical radiation sciences
PMID: 38654675

Abstract

INTRODUCTION: The automatic segmentation approaches of rectal cancer from magnetic resonance imaging (MRI) are very valuable to relieve physicians from heavy workloads and enhance working efficiency. This study aimed to compare the segmentation accuracy of a proposed model with the other three models and the inter-observer consistency.

Authors

  • Zaixian Zhang
    Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao 266000, Shandong, People's Republic of China (X.S., Z.Z., T.B.).
  • Junqi Han
    Department of Breast Imaging, The Affiliated Hospital of Qingdao University, Qingdao, People's Republic of China.
  • Weina Ji
    Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Henan Lou
    Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Zhiming Li
    Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China. Electronic address: lizhiming@qdu.edu.cn.
  • Yabin Hu
    Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Mingjia Wang
    College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao, China.
  • Baozhu Qi
    College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao, China.
  • Shunli Liu
    Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, 266003, Shandong, China.

Keywords

External Resources

Popular Topics
Recent Journals