ArticleNature methods2022
Cellpose 2.0: how to train your own model.
Article in Nature methods, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 760 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
760 citing papers in PubMed, 1 synthesis or guideline pooled it.
- A standardized framework resolves ambiguity in motor neuron loss across neurodegenerative diseases.Acta neuropathologica communications · 2026Pooled it
- Application of MR Cytometry in Predicting Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer: A Comparative Study.Journal of magnetic resonance imaging : JMRI · 2026Article
- Alternative splicing fine-tunes modular protein interfaces to control protein localization.Nature structural & molecular biology · 2026Article
- Enhancer binding kinetics explain transcription factor hub formation.Science advances · 2026Article
- Deep learning-enhanced single-shot triorganelle STED-FLIM imaging of lipid dynamics in living cells.Science advances · 2026Article
- 3D multi-omics tumour atlases: from technology to biology and clinical translation.Nature reviews. Cancer · 2026Review
- Spatially coordinated RTK-ERK signaling dynamics shape osteosarcoma single-cell drug response in the lung microenvironment.bioRxiv : the preprint server for biology · 2026Article
- Basal Marker ΔNp63α Is Enriched in Pancreatic Cancer Metastases but Not in Primary Tumors Post-Chemotherapy.Cancer medicine · 2026Article
- Spatially resolved multiomics of human meningeal development reveal lineage and disease dynamics.Nature cell biology · 2026Article
- Article
- Clathrin adaptors drive phase separation in endocytosis and trafficking.Communications biology · 2026Article
- Article
- Decay chemicals activate a pH-sensing pathway to initiate a persistent state.bioRxiv : the preprint server for biology · 2026Article
- Targeting the peripheral nervous system in adipose tissue with engineered AAV vectors.Cell reports methods · 2026Article
- Microenvironment-derived acetylated amino acids promote glioblastoma treatment resistance.Research square · 2026Article
- Distinct cellular phenotypes of language and executive decline in amyotrophic lateral sclerosis.Cell · 2026Article
- GCL pruning of PIP3 establishes the soma-germline boundary.The Journal of cell biology · 2026Article
- Tripartite ER-mitochondria-lipid droplets contact sites control adipocyte metabolic flexibility.The EMBO journal · 2026Article
- Artificial Intelligence-Powered High-Content Analysis: Methodologies and Applications in Bioactive Compound Discovery from Natural Sources.Molecules (Basel, Switzerland) · 2026Review
- Targeting HDAC and proteostasis to eradicate quiescent cancer cells.Cancer gene therapy · 2026Article
700 more citing papers are in PubMed but not listed here.
Corrections and comments
- Commented on by
Authors and funding
2 authors.
Funding
Abstract
Pretrained neural network models for biological segmentation can provide good out-of-the-box results for many image types. However, such models do not allow users to adapt the segmentation style to their specific needs and can perform suboptimally for test images that are very different from the training images. Here we introduce Cellpose 2.0, a new package that includes an ensemble of diverse pretrained models as well as a human-in-the-loop pipeline for rapid prototyping of new custom models. We show that models pretrained on the Cellpose dataset can be fine-tuned with only 500-1,000 user-annotated regions of interest (ROI) to perform nearly as well as models trained on entire datasets with up to 200,000 ROI. A human-in-the-loop approach further reduced the required user annotation to 100-200 ROI, while maintaining high-quality segmentations. We provide software tools such as an annotation graphical user interface, a model zoo and a human-in-the-loop pipeline to facilitate the adoption of Cellpose 2.0.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.