Cellpose: a generalist algorithm for cellular segmentation

• Published in: Nature methods Vol. 18; no. 1; pp. 100 - 106
• Main Authors: Stringer, Carsen, Wang, Tim, Michaelos, Michalis, Pachitariu, Marius
• Format: Journal Article
• Language: English
• Published: New York Nature Publishing Group US 01.01.2021; Nature Publishing Group
• Subjects: 631/114; 631/80; Algorithms; Animals; Bioinformatics; Biological Microscopy; Biological Techniques; Biomedical and Life Sciences; Biomedical Engineering/Biotechnology; Cell Nucleus - chemistry; Datasets; Deep Learning; Female; Humans; Image Processing, Computer-Assisted - methods; Image segmentation; Life Sciences; Machine learning; Male; Mathematical models; Mice; Mice, Inbred C57BL; Neural Networks, Computer; Neurons - cytology; Parameters; Proteomics; Retraining; Software; Technology application; Three dimensional models; Training; Two dimensional models; United States
• ISSN: 1548-7091; 1548-7105; 1548-7105
• DOI: 10.1038/s41592-020-01018-x

Many biological applications require the segmentation of cell bodies, membranes and nuclei from microscopy images. Deep learning has enabled great progress on this problem, but current methods are specialized for images that have large training datasets. Here we introduce a generalist, deep learning-based segmentation method called Cellpose, which can precisely segment cells from a wide range of image types and does not require model retraining or parameter adjustments. Cellpose was trained on a new dataset of highly varied images of cells, containing over 70,000 segmented objects. We also demonstrate a three-dimensional (3D) extension of Cellpose that reuses the two-dimensional (2D) model and does not require 3D-labeled data. To support community contributions to the training data, we developed software for manual labeling and for curation of the automated results. Periodically retraining the model on the community-contributed data will ensure that Cellpose improves constantly. Cellpose is a generalist, deep learning-based approach for segmenting structures in a wide range of image types. Cellpose does not require parameter adjustment or model retraining and outperforms established methods on 2D and 3D datasets.