Fully automated cardiac MRI segmentation using dilated residual network.

Journal: Medical physics
Published Date:

Abstract

PURPOSE: Cardiac ventricle segmentation from cine magnetic resonance imaging (CMRI) is a recognized modality for the noninvasive assessment of cardiovascular pathologies. Deep learning based algorithms achieved state-of-the-art result performance from CMRI cardiac ventricle segmentation. However, most approaches received less attention at the bottom layer of UNet, where main features are lost due to pixel degradation. To increase performance, it is important to handle the bottleneck layer of UNet properly. Considering this problem, we enhanced the performance of main features at the bottom layer of network.

Authors

  • Faizan Ahmad
    Soft Robotics Research Center, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
  • Wenguo Hou
    Soft Robotics Research Center, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
  • Jing Xiong
    College of Computer Science, Sichuan Normal University, Chengdu, China.
  • Zeyang Xia
    Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, ShenZhen, China.