Development of a motion-based cell-counting system for Trypanosoma parasite using a pattern recognition approach.

Area of Science:

• Parasitology
• Microbiology
• Biotechnology

Background:

• Automated cell counters using still images are common but struggle with slender, aggregate-prone microorganisms.
• Trypanosoma cruzi presents challenges for traditional cell counting methods due to its morphology and aggregation tendencies.

Purpose of the Study:

• To develop a motion-based cell-counting system for improved accuracy with challenging microorganisms.
• To enhance the sensitivity of drug screening assays by detecting parasite activity loss.

Main Methods:

• Developed a motion-based cell-counting system utilizing image recognition with a cubic higher-order local auto-correlation feature.
• Employed motion pattern recognition to estimate cell density for dispersed, aggregated, and fluorescent parasites.

Main Results:

• Successfully estimated cell density for various parasite states (dispersed, aggregated, fluorescent).
• Detected loss of parasite activity due to drug treatment as reduced apparent cell count.
• Enabled parasite counting in co-cultures with host cells by distinguishing parasite motion from static background.

Conclusions:

• The motion-based system offers a robust solution for counting difficult microorganisms like Trypanosoma cruzi.
• This approach enhances drug screening sensitivity and allows for accurate cell counting in complex biological samples.