Answers are grounded in this paper and cite their sources.
Biological image analysis is central to modern biology, yet many available platforms require technical expertise, code-based workflows, extensive setup, or paid access. Here, we introduce Mycol, an open-source, machine-learning-assisted image analysis platform designed to be accessible and run on standard laptops. Mycol supports end-to-end workflows incorporating automated segmentation and classification in a single interface. Users annotate biological images, fine-tune machine learning models, inspect and correct the predictions, and quantitatively compare morphological and class frequency descriptors. By combining machine-learning analysis with efficient quality control by humans, Mycol makes rapid, high-quality image quantification available to non-specialists. We demonstrate the utility of Mycol in three case studies spanning four species: colony forming unit counting in Staphylococcus aureus and Escherichia coli , spore germination in the crop pathogen Fusarium oxysporum , and larval development in the blue mussel Mytilus edulis . Through Mycol, curated training sets are generated and high-quality segmentation and classification models are obtained in each case. Deploying these models through Mycol decreases experimental time requirements, increases traceability of established cell counting workflows, and facilitates a quantitative comparison of morphological parameters that reveals new patterns in early M. edulis larval development.
No takes yet. Share an insight, caveat, or question.
Bradley et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: