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

By N. Greenwald, G. Miller, Erick Moen, Alex Y. W. Kong, Adam Kagel, T. Dougherty, C. Fullaway, Brianna J. McIntosh, K. Leow, Morgan Schwartz and 19 more. Nature Biotechnology, 2021

814 citations recorded by the source corpus.

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. Deep learning algorithms perform as well as humans in identifying cells in tissue images.

Subfields: Artificial Intelligence, Biophysics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/40af8e077b162551888ea348d16f458a12c147e5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. C. Stringer
2. Marius Pachitariu
3. Yarin Gal

In Biophysics

1. Marius Pachitariu
2. C. Stringer

In Molecular Biology

1. C. Stringer
2. Marius Pachitariu

Citations in the corpus

• Cellpose3: one-click image restoration for improved cellular segmentation (2024, neutral): “There are other datasets that we could have used such as TissueNet [22], LiveCell [21], Om-nipose [24], Yeaz [26], DeepBacs [25].”
• High resolution mapping of the tumor microenvironment using integrated single-cell, spatial and in situ analysis (2023, neutral): “We adopted the evaluation methodology used by Greenwald et al., 2021 37 and fi rst proposed in Moen et al., 2019 38 .”
• Cellpose 2.0: how to train your own model (2022, methodology): “We reasoned that annotation times can be reduced further if we used a ”human-in-the-loop” approach [6, 19].”