Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning.

Journal: Nature biotechnology
PMID: 34795433

Abstract

A principal challenge in the analysis of tissue imaging data is cell segmentation-the task of identifying the precise boundary of every cell in an image. To address this problem we constructed TissueNet, a dataset for training segmentation models that contains more than 1 million manually labeled cells, an order of magnitude more than all previously published segmentation training datasets. We used TissueNet to train Mesmer, a deep-learning-enabled segmentation algorithm. We demonstrated that Mesmer is more accurate than previous methods, generalizes to the full diversity of tissue types and imaging platforms in TissueNet, and achieves human-level performance. Mesmer enabled the automated extraction of key cellular features, such as subcellular localization of protein signal, which was challenging with previous approaches. We then adapted Mesmer to harness cell lineage information in highly multiplexed datasets and used this enhanced version to quantify cell morphology changes during human gestation. All code, data and models are released as a community resource.

Authors

  • Noah F Greenwald
    Cancer Biology Program, Stanford University, Stanford, CA, USA.
  • Geneva Miller
    Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA.
  • Erick Moen
    Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA.
  • Alex Kong
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Adam Kagel
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Thomas Dougherty
    Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA.
  • Christine Camacho Fullaway
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Brianna J McIntosh
    Cancer Biology Program, Stanford University, Stanford, CA, USA.
  • Ke Xuan Leow
    Cancer Biology Program, Stanford University, Stanford, CA, USA.
  • Morgan Sarah Schwartz
    Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA.
  • Cole Pavelchek
    Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA.
  • Sunny Cui
    Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, USA.
  • Isabella Camplisson
    Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA.
  • Omer Bar-Tal
    Department of Molecular Cell Biology, Weizmann Institute of Science, Rehovot, Israel.
  • Jaiveer Singh
    Bakar Computational Health Sciences Institute, University of California, San Francisco, CA 94158.
  • Mara Fong
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Gautam Chaudhry
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Zion Abraham
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Jackson Moseley
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Shiri Warshawsky
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Erin Soon
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Shirley Greenbaum
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Tyler Risom
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Travis Hollmann
    Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
  • Sean C Bendall
    Department of Pathology, Stanford University, Stanford, CA, USA.
  • Leeat Keren
    Department of Molecular Cell Biology, Weizmann Institute of Science, Rehovot, Israel.
  • William Graf
    Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA.
  • Michael Angelo
    Department of Pathology, Stanford University, Stanford, CA, USA. mangelo0@stanford.edu.
  • David Van Valen
    Division of Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA. vanvalen@caltech.edu.

Keywords

External Resources

Popular Topics
Recent Journals