An adaptive digital stain separation method for deep learning-based automatic cell profile counts.

Journal: Journal of neuroscience methods
Published Date: Feb 17, 2021

Abstract

BACKGROUND: Quantifying cells in a defined region of biological tissue is critical for many clinical and preclinical studies, especially in the fields of pathology, toxicology, cancer and behavior. As part of a program to develop accurate, precise and more efficient automatic approaches for quantifying morphometric changes in biological tissue, we have shown that both deep learning-based and hand-crafted algorithms can estimate the total number of histologically stained cells at their maximal profile of focus in Extended Depth of Field (EDF) images. Deep learning-based approaches show accuracy comparable to manual counts on EDF images but significant enhancement in reproducibility, throughput efficiency and reduced error from human factors. However, a majority of the automated counts are designed for single-immunostained tissue sections.

Authors

  • Palak Dave
    Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA. Electronic address: palakdave@usf.edu.
  • Saeed Alahmari
    Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA.
  • Dmitry Goldgof
    Computer Science and Engineering Department University of South Florida Tampa FL USA.
  • Lawrence O Hall
    Department of Computer Science and Engineering, University of South Florida, Tampa, FL, USA.
  • Hunter Morera
    Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA.
  • Peter R Mouton
    SRC Biosciences Tampa FL USA.

Keywords

External Resources

Popular Topics
Recent Journals