Fully automated OCT-based tissue screening system.

Area of Science:

• Biomedical Engineering
• Ophthalmology
• Drug Discovery

Background:

• High-throughput screening (HTS) is crucial for drug discovery and biological research.
• Existing HTS methods often lack the resolution or automation required for detailed tissue analysis.
• Optical Coherence Tomography (OCT) offers non-invasive, high-resolution imaging but requires adaptation for HTS.

Purpose of the Study:

• To develop and validate a fully automated OCT imaging system for high-throughput screening of ex vivo tissue cultures.
• To integrate advanced automation and deep learning for robust and efficient data acquisition and analysis.
• To demonstrate the system's capability in assessing tissue response to treatments in a disease model.

Main Methods:

• Development of a custom OCT system with a motorized platform for automated sample handling and successive imaging.
• Implementation of transformer-based deep learning algorithms for automated tissue segmentation and analysis.
• Validation using ex vivo retinal explant cultures from a mouse model of retinal degeneration.

Main Results:

• The automated OCT system successfully performed high-throughput, successive imaging of tissue samples.
• Deep learning segmentation provided robust, consistent, and efficient quantitative readouts.
• The system demonstrated rapid, reliable, and unbiased assessment of retinal explant responses to treatments.

Conclusions:

• The developed automated OCT system significantly advances capabilities for ex vivo tissue screening.
• This technology promises to accelerate drug discovery and other research fields requiring high-throughput tissue analysis.
• The system offers a powerful, non-invasive tool for comprehensive evaluation of tissue-based assays.