An AI-based imaging flow cytometry approach to study erythrophagocytosis

Area of Science:

• Cell Biology
• Immunology
• Computational Biology

Background:

• Erythrophagocytosis, the engulfment of erythrocytes by phagocytes, is crucial for red blood cell homeostasis.
• Current methods like Imaging Flow Cytometry (IFC) for studying phagocytosis are effective but analysis-intensive.
• Understanding erythrophagocytosis dynamics is vital in various physiological and pathological conditions.

Purpose of the Study:

• To develop a novel, efficient, and accurate method for analyzing erythrophagocytosis.
• To combine Artificial Intelligence (AI) with Imaging Flow Cytometry (IFC) for automated analysis.
• To accurately categorize erythrocytes as internalized, bound, or non-bound by phagocytes.

Main Methods:

• Integration of Artificial Intelligence (AI) algorithms with Imaging Flow Cytometry (IFC) data.
• Development of a computational pipeline for automated analysis of phagocytosis.
• Validation of the AI-IFC pipeline through rigorous experiments.

Main Results:

• The AI-IFC approach successfully categorizes erythrocytes based on their interaction with phagocytes (internalized, bound, non-bound).
• The developed pipeline demonstrates high accuracy and reproducibility in analyzing erythrophagocytosis.
• This novel method significantly reduces the laborious analysis typically associated with IFC.

Conclusions:

• Combining AI with IFC offers a powerful and efficient tool for studying erythrophagocytosis.
• The validated pipeline provides a reliable method for quantitative analysis of phagocytosis dynamics.
• This approach has broad applicability for research involving cellular engulfment processes.