CellSeg: a robust, pre-trained nucleus segmentation and pixel quantification software for highly multiplexed fluorescence images.

Journal: BMC bioinformatics
Published Date: Jan 18, 2022

Abstract

BACKGROUND: Algorithmic cellular segmentation is an essential step for the quantitative analysis of highly multiplexed tissue images. Current segmentation pipelines often require manual dataset annotation and additional training, significant parameter tuning, or a sophisticated understanding of programming to adapt the software to the researcher's need. Here, we present CellSeg, an open-source, pre-trained nucleus segmentation and signal quantification software based on the Mask region-convolutional neural network (R-CNN) architecture. CellSeg is accessible to users with a wide range of programming skills.

Authors

  • Michael Y Lee
    Department of Microbiology and Immunology, Stanford University School of Medicine, Stanford, CA, 94305, USA.
  • Jacob S Bedia
    Department of Urology, Stanford University School of Medicine, Stanford, CA, 94305, USA.
  • Salil S Bhate
    Department of Microbiology and Immunology, Stanford University School of Medicine, Stanford, CA, 94305, USA.
  • Graham L Barlow
    Department of Microbiology and Immunology, Stanford University School of Medicine, Stanford, CA, 94305, USA.
  • Darci Phillips
    Department of Microbiology and Immunology, Stanford University School of Medicine, Stanford, CA, 94305, USA.
  • Wendy J Fantl
    Department of Urology, Stanford University School of Medicine, Stanford, CA, 94305, USA.
  • Garry P Nolan
    Department of Microbiology & Immunology, Stanford University, CA, USA.
  • Christian M Schürch
    Department of Microbiology and Immunology, Stanford University School of Medicine, Stanford, CA, 94305, USA. christian.schuerch@med.uni-tuebingen.de.

Keywords

External Resources

Popular Topics
Recent Journals