Evolution of Vesicle Shape Parameters Based on A Deep-Learning Based Image Analysis Framework Over Extended Time Periods

Deep-learning image analysis of phase-contrast microscopy enables high-temporal-resolution tracking of mother and daughter giant unilamellar vesicles, quantifying budding-linked morphometrics over extended periods.

• Why it matters: Shape instabilities in cell-sized membrane compartments require precise, long-term quantification of individual vesicle dynamics, including budding and curvature changes.
• What they did: Giant unilamellar membrane vesicles were imaged by phase-contrast microscopy in potato starch solution with and without cholesterol in 1-palmitoyl-2-oleoyl-sn-glycero-3-phosphocholine, and a deep-learning framework segmented mother and daughter compartments from micrographs.
• The result: The approach yields time-resolved measurements of vesicle area and local membrane curvature during budding, supporting computational modeling of curvature-driven membrane remodeling in complex soft materials.

AI summary of the abstract · may contain errors · not medical advice · read the paper.