Cellpose — Deep Learning Cell Segmentation

Overview

Cellpose uses a flow-based neural network to segment individual cells or nuclei in fluorescence microscopy images without manual parameter tuning. Pre-trained models (cyto3, nuclei, tissuenet) generalize across cell types, magnifications, and staining conditions — eliminating the need for manual threshold selection or watershed parameter optimization. Cellpose outputs integer label masks (each cell = unique integer) compatible with scikit-image regionprops for morphology measurement and with TrackPy for tracking. A built-in diameter estimator removes the need to specify cell size, though providing an approximate diameter improves accuracy.

When to Use

• Segmenting cells or nuclei in fluorescence microscopy images where rule-based thresholding fails due to varying intensity or cell touching
• Processing large microscopy datasets in batch without per-image parameter tuning
• Segmenting diverse cell types (adherent cells, blood cells, bacteria, organoids) with a single model
• Producing label masks for downstream region property measurement (area, intensity, shape) with scikit-image
• 3D volumetric segmentation of z-stack microscopy data with do_3D=True
• Use scikit-image watershed when cells are well-separated and rule-based thresholding is sufficient
• Use StarDist as an alternative deep learning segmenter optimized for star-convex cells (neurons, nuclei)

Prerequisites