Actin Quantification Using the Filamentous Actin Segmentation Tool (FAST).

Studying actin-filament assembly into distinct subcellular structures can provide insights into both physiological cellular processes and the mechanisms of disease. However, there are a limited number of tools that can quantify the organization and abundance of different actin structures from confocal microscopy images of cells expressing Lifeact or fixed and stained with phalloidin. Filamentous actin segmentation tool (FAST) is a deep learning model trained with a unique approach of antibody-assisted annotation, resulting in accurate and efficient quantification of distinct classes of actin structures. Here, we detail the protocol for using antibody-assisted annotation to generate datasets that could be applied to train machine learning models. Additionally, we provide step-by-step instructions for applying FAST on phalloidin-stained or live-cell confocal imaging data using our pretrained model. FAST is open source and freely available, with user-friendly notebooks that enable quantification of different classes of actin structure, without the need for structure-specific antibodies. As such, FAST can be a practical tool for researchers investigating the role of cytoskeletal organization in a range of processes. Key features • This antibody-assisted labeling approach can be used for identifying different classes of actin structure and generating labeled datasets for training machine learning algorithms. • The trained FAST model then enables the detection of distinct classes of actin structure without the need for multiple structure-specific antibodies. • FAST generates segmentation masks that can be used to quantify the abundance and organization of detected classes. • This protocol provides a graphical user interface for fine-tuning custom phalloidin-stained images and provides instructions on using trained model on Ilastik interface.