Precise Quantitative Analysis of Cell Targeting by Particle-Based Agents Using Imaging Flow Cytometry and...

Area of Science:

• Biomedical Engineering
• Computational Biology
• Cell Biology

Background:

• Accurate particle-cell interaction analysis is crucial for advancing imaging, phototherapy, and drug/gene delivery.
• High-throughput methods like imaging flow cytometry (IFC) generate vast datasets but pose analytical challenges.
• Conventional IFC data analysis methods struggle with integral parameters and mask-based recognition, limiting precision.

Purpose of the Study:

• To develop and apply a convolutional neural network (CNN) for precise quantitative analysis of particle targeting on cells using IFC data.
• To overcome the limitations of conventional IFC data analysis, enabling more accurate interpretation of particle-cell interactions.
• To provide a high-throughput, objective method for quantifying cell-bound particles.

Main Methods:

• Application of a convolutional neural network (CNN) for object detection and analysis of IFC data.
• Utilizing IFC data to capture cell morphology, organelle localization, and fluorescence/scatter intensity.
• Implementing CNN for high-throughput, precise counting and discrimination of cell-bound particles.

Main Results:

• The CNN method achieved high-throughput object detection with near-human precision.
• Accurate counting of cell-bound particles was demonstrated with reliable discrimination from non-bound particles.
• The approach avoids subjective image processing parameter choices, enhancing data reliability.

Conclusions:

• The proposed CNN method offers a powerful tool for precise quantitative analysis of particle-cell interactions in IFC data.
• This technique significantly enhances capabilities for spot counting applications, including organelle counting and interaction quantification.
• The method is broadly applicable to high-throughput analysis of IFC and other imaging techniques, improving diagnostic and therapeutic efficiency.