Semantic segmentation to identify bladder layers from H&E Images.

Journal: Diagnostic pathology
Published Date: Jul 16, 2020

Abstract

BACKGROUND: Identification of bladder layers is a necessary prerequisite to bladder cancer diagnosis and prognosis. We present a method of multi-class image segmentation, which recognizes urothelium, lamina propria, muscularis propria, and muscularis mucosa layers as well as regions of red blood cells, cauterized tissue, and inflamed tissue from images of hematoxylin and eosin stained slides of bladder biopsies.

Authors

  • Muhammad Khalid Khan Niazi
    Center for Biomedical Informatics, Wake Forest School of Medicine, Winston-Salem, North Carolina, United States of America.
  • Enes Yazgan
    Center for Biomedical Informatics, Wake Forest School of Medicine, Winston-Salem, NC, USA.
  • Thomas E Tavolara
    Center for Biomedical Informatics, Wake Forest School of Medicine, Winston-Salem, USA.
  • Wencheng Li
    Department of Pathology, Wake Forest School of Medicine, Winston-Salem, NC, USA.
  • Cheryl T Lee
    Department of Urology, The Ohio State University, Columbus, OH, USA.
  • Anil Parwani
    Department of Pathology.
  • Metin N Gurcan
    Department of Biomedical Informatics, The Ohio State University, Columbus, OH 43210, USA. Electronic address: metin.gurcan@osumc.edu.

Keywords

External Resources

Popular Topics
Recent Journals