Hybrid U-Net-based deep learning model for volume segmentation of lung nodules in CT images.

Journal: Medical physics
Published Date: Aug 17, 2022

Abstract

OBJECTIVE: Accurate segmentation of the lung nodule in computed tomography images is a critical component of a computer-assisted lung cancer detection/diagnosis system. However, lung nodule segmentation is a challenging task due to the heterogeneity of nodules. This study is to develop a hybrid deep learning (H-DL) model for the segmentation of lung nodules with a wide variety of sizes, shapes, margins, and opacities.

Authors

  • Yifan Wang
    School of Bioscience and Bioengineering, South China University of Technology, Guangzhou, China.
  • Chuan Zhou
    Department of Radiology, The University of Michigan, Ann Arbor, MI, 48109, USA.
  • Heang-Ping Chan
    Department of Radiology, University of Michigan, Ann Arbor, Michigan.
  • Lubomir M Hadjiiski
    Department of Radiology, University of Michigan, Ann Arbor, Michigan.
  • Aamer Chughtai
    Department of Radiology, Michigan Medicine, University of Michigan, Ann Arbor, Michigan, United States of America.
  • Ella A Kazerooni
    Departments of Radiology & Internal Medicine, University of Michigan Medical School, Michigan, MI, USA.

Keywords

External Resources

Popular Topics
Recent Journals