microbeSEG

microbeSEG performs deep-learning instance segmentation of single microbial cells from phase contrast and fluorescence microscopy images to enable quantitative analysis of microbial cultures.

Key Features:

• Python implementation: The software is implemented in Python.
• Deep learning instance segmentation: Employs deep learning for instance segmentation at single-cell resolution.
• Imaging modalities: Supports phase contrast and fluorescence microscopy and handles diverse cell morphologies.
• OMERO integration: Integrates with OMERO data management systems.
• Training workflow: Covers training data creation through application of trained segmentation models.
• Public datasets and pre-labeling: Supports the use of public segmentation datasets and pre-labeling techniques.

Scientific Applications:

• Microbial culture analysis: Enables characterization and analysis of cell growth dynamics in microbial cultures.
• Biotechnology research: Provides single-cell segmentation for studies of cellular development processes.

Methodology:

Deep learning-based instance segmentation using state-of-the-art algorithms; supports training data generation, use of public segmentation datasets, and pre-labeling techniques for model training and application.