Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation.

Journal: Yearbook of medical informatics
Published Date: Aug 21, 2020

Abstract

INTRODUCTION: There has been a rapid development of deep learning (DL) models for medical imaging. However, DL requires a large labeled dataset for training the models. Getting large-scale labeled data remains a challenge, and multi-center datasets suffer from heterogeneity due to patient diversity and varying imaging protocols. Domain adaptation (DA) has been developed to transfer the knowledge from a labeled data domain to a related but unlabeled domain in either image space or feature space. DA is a type of transfer learning (TL) that can improve the performance of models when applied to multiple different datasets.

Authors

  • Anirudh Choudhary
    Department of Computational Science and Engineering, Georgia Institute of Technology, GA, USA.
  • Li Tong
    Dept. of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA 30332.
  • Yuanda Zhu
    School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA.
  • May D Wang
    Dept. of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA 30332.

Keywords

External Resources

Popular Topics
Recent Journals