Liver segmentation in abdominal CT images via auto-context neural network and self-supervised contour attention.

Journal: Artificial intelligence in medicine
Published Date: Jan 23, 2021

Abstract

OBJECTIVE: Accurate image segmentation of the liver is a challenging problem owing to its large shape variability and unclear boundaries. Although the applications of fully convolutional neural networks (CNNs) have shown groundbreaking results, limited studies have focused on the performance of generalization. In this study, we introduce a CNN for liver segmentation on abdominal computed tomography (CT) images that focus on the performance of generalization and accuracy.

Authors

  • Minyoung Chung
    School of Computer Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 151-742, Korea. Electronic address: chungmy@cglab.snu.ac.kr.
  • Jingyu Lee
    School of Computer Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 151-742, Korea. Electronic address: leejingyu@cglab.snu.ac.kr.
  • Sanguk Park
    Department of Computer Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, South Korea.
  • Chae Eun Lee
    Department of Computer Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, South Korea.
  • Jeongjin Lee
    School of Computer Science and Engineering, Soongsil University, Seoul, Korea.
  • Yeong-Gil Shin
    School of Computer Science and Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 151-742, Korea. Electronic address: yshin@snu.ac.kr.

Keywords

External Resources

Popular Topics
Recent Journals