Skeleton-guided 3D convolutional neural network for tubular structure segmentation.

Journal: International journal of computer assisted radiology and surgery
Published Date: Sep 12, 2024

Abstract

PURPOSE: Accurate segmentation of tubular structures is crucial for clinical diagnosis and treatment but is challenging due to their complex branching structures and volume imbalance. The purpose of this study is to propose a 3D deep learning network that incorporates skeleton information to enhance segmentation accuracy in these tubular structures.

Authors

  • Ruiyun Zhu
    Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi, Japan. rzhu@mori.m.is.nagoya-u.ac.jp.
  • Masahiro Oda
    Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, 464-8601, Japan.
  • Yuichiro Hayashi
    Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Japan.
  • Takayuki Kitasaka
    Graduate School of Information Science, Aichi Institute of Technology, 1247 Yachigusa, Yagusa-cho, Toyota, Aichi, Japan.
  • Kazunari Misawa
    Aichi Cancer Center, Kanokoden, Chikusa-ku, Nagoya, Japan.
  • Michitaka Fujiwara
    Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Kensaku Mori
    Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, 464-8601, Japan.

Keywords

External Resources

Popular Topics
Recent Journals