A convex-hull based method with manifold projections for detecting cell protrusions.

Area of Science:

• Cell Biology
• Computational Biology
• Image Analysis

Background:

• Cell protrusions are crucial for various physiological processes.
• Accurate detection of these structures is vital for understanding cell behavior.

Purpose of the Study:

• To develop and validate a robust computational method for detecting cell protrusions.
• To quantify the performance of the proposed method on different cell protrusion types.

Main Methods:

• A convex-hull based approach combined with manifold projections was employed.
• A depth function was defined based on the distance between the cell surface and its convex hull.
• Spherical polar coordinates were used for efficient extreme point identification.

Main Results:

• The method achieved high average precision: 98.9% for blebs, 95.6% for filopodia, and 94.7% for lamellipodia.
• Experiments on three datasets demonstrated the method's robust performance across different cell protrusion types.

Conclusions:

• The proposed convex-hull based method is effective and robust for cell protrusion detection.
• This technique provides a valuable tool for quantitative cell biology and image analysis.