CellRake: a Python package for analyzing cells in fluorescent images

CellRake is an open-source bio-Python package designed to analyze cells in fluorescent images, providing robust tools for image segmentation, machine learning-based model training and prediction, and colocalization analysis. Built on Scikit-image and Scikit-learn, CellRake streamlines complex workflows involving multiple fluorescent markers, making it highly suitable for advanced biological image analysis. In this study, we applied CellRake to examine cellular composition and marker colocalization across various brain areas. Our results demonstrate the utility and flexibility of CellRake for quantitative analysis in biological research.

The motivation for choosing this topic originated from my experience during my PhD, where I noticed a lack of Python libraries that utilize shallow machine learning techniques for tissue image analysis. Most available tools depended on complex neural networks, which are difficult to train and deploy on standard computers. By developing and applying CellRake, I sought to provide a more accessible and efficient solution for analyzing tissue images, particularly in neuroscience research.

• Learn about CellRake, a user-friendly Python package for analyzing fluorescent tissue images.
• Viewers will see how CellRake was used to analyze cellular composition and marker distribution in various brain regions.
• Attendees will grasp the benefits of using open-source tools like CellRake, such as transparency, reproducibility, and community-driven enhancements.

Basic Python Programming and Introductory Machine Learning