Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning Journal Article
| Authors: | Greenwald, N. F.; Miller, G.; Moen, E.; Kong, A.; Kagel, A.; Dougherty, T.; Camacho Fullaway, C.; McIntosh, B. J.; Leow, K. X.; Schwartz, M. S.; Pavelchek, C.; Cui, S.; Camplisson, I.; Bar-Tal, O.; Singh, J.; Fong, M.; Chaudhry, G.; Abraham, Z.; Moseley, J.; Warshawsky, S.; Soon, E.; Greenbaum, S.; Risom, T.; Hollmann, T.; Bendall, S. C.; Keren, L.; Graf, W.; Angelo, M.; Van Valen, D. |
| Article Title: | Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning |
| 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. © 2021, The Author(s), under exclusive licence to Springer Nature America, Inc. |
| Keywords: | human tissue; cytology; algorithms; information processing; cell lineage; algorithm; quantitative analysis; cellular distribution; pregnancy; image processing, computer-assisted; image processing; tissue; human experiment; extraction; cells; tissues; image segmentation; procedures; whole cell; humans; human; article; deep learning; tissue imaging; image annotation; segmentation algorithm; data curation; cell segmentation; data annotation; human-level performance; imaging data; labeled cells; large scale data; segmentation models; tissue images |
| Journal Title: | Nature Biotechnology |
| Volume: | 40 |
| Issue: | 4 |
| ISSN: | 1087-0156 |
| Publisher: | Nature Publishing Group |
| Date Published: | 2022-04-01 |
| Start Page: | 555 |
| End Page: | 565 |
| Language: | English |
| DOI: | 10.1038/s41587-021-01094-0 |
| PUBMED: | 34795433 |
| PROVIDER: | scopus |
| PMCID: | PMC9010346 |
| DOI/URL: | |
| Notes: | Article -- Export Date: 25 April 2022 -- Source: Scopus |
