# MouseLand/cellpose

a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

Repository: https://github.com/MouseLand/cellpose
Canonical: https://ross.abutalabs.com/products/cellpose
Homepage: https://huggingface.co/spaces/mouseland/cellpose
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: segmentation, cell-segmentation, cell-biology
Last push: 2026-06-14T13:21:03+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 76, longevity 100
- inputs: {"age_days": 2405, "days_push": 80, "days_rel": 80, "gap_med": 56, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2331, forks 644 (observed 2026-08-28T04:06:37.752758+00:00)

## What it is
Cellpose is a generalist deep learning algorithm for cellular and nucleus segmentation in microscopy images, with human-in-the-loop capabilities and fine-tuning support. It works across diverse imaging conditions and object sizes, including 3D data.

## Use cases
- segment cells in microscopy images
- segment nuclei automatically
- fine-tune a segmentation model on my own cell data
- run cell segmentation in 3D
- annotate cells with human-in-the-loop correction
- segment cells in noisy or blurred images

## When to choose
- you need generalist cell/nucleus segmentation without training from scratch
- your microscopy data has noise, blur, or varying channel orders
- you want human-in-the-loop correction of segmentations
- you need 3D segmentation support

## When to avoid
- you need general object segmentation outside biological imagery
- you need a lightweight non-deep-learning image analysis tool
- you lack GPU resources for fast inference or fine-tuning

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: bioinformatics, computer-vision, image-processing, machine-learning
- platform: python, cross-platform
- tags: cell-segmentation, microscopy, cell-biology, human-in-the-loop, sam, nucleus-segmentation, gpu

## Member repositories
- MouseLand/cellpose (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.752758+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:37:58.279615+00:00, confidence not recorded.
  - readme: https://github.com/MouseLand/cellpose (fetched 2026-08-28T04:06:37.752758+00:00, sha db8ad8c9a69e)
  - homepage: https://huggingface.co/spaces/mouseland/cellpose (fetched 2026-08-29T10:18:29.740560+00:00, sha 21938d4f8c62)
  - registry_pypi: https://pypi.org/pypi/cellpose/json (fetched 2026-08-29T10:18:29.749536+00:00, sha 4f50645724d7)
- Data as of 2026-08-30T08:39:29.467469+00:00.