Highly adaptable deep-learning platform for automated detection and analysis of vesicle exocytosis

Abstract

Vesicle exocytosis is a fundamental component of intercellular communication, in all organisms. It has been studied for decades, using various imaging tools. Nevertheless, exocytosis research is still limited by the lack of reliable automated analysis procedures. To address this, we developed the Intelligent Vesicle Exocytosis Analysis Platform (IVEA), a nearly universal solution for analyzing exocytosis acquired with live cell imaging. IVEA is applicable to a wide variety of experimental model systems, microscopes and reporter fluorophores. IVEA combines state-of-the-art deep-learning and computer vision regimes to enable fully automated analysis of large data. IVEA runs as a FIJI plugin and does not require prior training or human intervention. IVEA is 60 times faster than manual analysis and is able to detect rare events often missed by the human eye. Overall, IVEA represents a breakthrough in the analysis of cellular secretory mechanisms and has a transformative potential for the exocytosis imaging field.