Harnessing clinical annotations to improve deep learning performance in prostate segmentation.

Journal: PloS one
PMID: 34170972

Abstract

PURPOSE: Developing large-scale datasets with research-quality annotations is challenging due to the high cost of refining clinically generated markup into high precision annotations. We evaluated the direct use of a large dataset with only clinically generated annotations in development of high-performance segmentation models for small research-quality challenge datasets.

Authors

  • Karthik V Sarma
    Department of Bioengineering, University of California, Los Angeles, CA, USA.
  • Alex G Raman
    University of California, Los Angeles, Los Angeles, CA, United States of America.
  • Nikhil J Dhinagar
    University of California, Los Angeles, Los Angeles, CA, United States of America.
  • Alan M Priester
    University of California, Los Angeles, Los Angeles, CA, United States of America.
  • Stephanie Harmon
  • Thomas Sanford
    Molecular Imaging Program, National Cancer Institute, NIH, Bethesda, MD, USA.
  • Sherif Mehralivand
    Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, Maryland, USA.
  • Baris Turkbey
    Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Leonard S Marks
    University of California, Los Angeles, Los Angeles, CA, United States of America.
  • Steven S Raman
    Department of Radiologic Sciences David Geffen School of Medicine, University of California Los Angeles CA.
  • William Speier
    Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, USA.
  • Corey W Arnold
    Department of Bioengineering; University of California, Los Angeles, CA.

Keywords

External Resources

Popular Topics
Recent Journals