Automated high-throughput image processing as part of the screening platform for personalized oncology

Area of Science:

• Oncology
• Bioinformatics
• Medical Imaging

Background:

• Cancer is a leading cause of death globally, with treatment hindered by therapy resistance.
• Personalized oncology requires integrating multi-omics data with in-vitro Drug Sensitivity and Resistance Tests (DSRT).
• High-throughput screening platforms are crucial for personalized cancer care.

Purpose of the Study:

• To develop an automated image processing platform for high-throughput DSRT in personalized oncology.
• To address the limitations of manual image analysis in processing large datasets from DSRT experiments.
• To integrate multi-omics data with DSRT profiling for improved cancer therapy selection.

Main Methods:

• Development of a platform incorporating DSRT profiling workflows using minute cellular material.
• Implementation of assisted image annotation and algorithms for processing grid-like high-throughput experimental images.
• Integration of automated image processing with high-performance computing and deployment of processing pipelines.

Main Results:

• Demonstration of a comprehensive concept for automated image processing in personalized oncology.
• Successful linking of automated image analysis for DSRT with high-performance computing resources.
• Validation of the proposed solution using image data from heterogeneous practical experiments.

Conclusions:

• Automated image processing is essential for enabling high-throughput screening platforms in personalized oncology.
• The developed platform facilitates efficient and reproducible analysis of DSRT data.
• This approach enhances the potential for determining optimal cancer therapies based on individual patient data.