ACME: Automatic feature extraction for cell migration examination through intravital microscopy imaging.

Area of Science:

• Biomedical imaging
• Cellular biology
• Computational biology

Background:

• In vivo fluorescence microscopy is crucial for studying 4D cellular processes.
• Current cell tracking methods require manual intervention, limiting large-scale data analysis.
• Automated analysis of cell migration is needed for deeper biological understanding.

Purpose of the Study:

• To develop a fully automated system for segmenting, tracking, and extracting features of migrating cells in 4D microscopy.
• To overcome limitations of traditional, time-consuming cell analysis methods.
• To enable comprehensive analysis of immune cell migration dynamics.

Main Methods:

• A 3D convolutional neural network (CNN) for joint segmentation of blood vessels and cells.
• A 3D tracking module incorporating collision handling.
• A novel feature extraction method considering cell-vessel geometry.

Main Results:

• The proposed system significantly outperforms existing state-of-the-art tools in cell segmentation and tracking.
• Achieved superior performance on a large 4D intravital microscopy dataset.
• Enabled automated analysis of hundreds of neutrophils across thousands of time instances.

Conclusions:

• The developed automated system provides a comprehensive solution for 4D cell migration analysis.
• The system's extracted features support biological hypotheses regarding leukocyte migration.
• This represents a significant advancement in the automated analysis of immune cell migration.