SPACEc

SPACEc streamlines spatial imaging analysis by integrating image processing, cell segmentation, and data preprocessing into a scalable Python workflow with parallelization and GPU acceleration for efficient analysis of large multiplexed imaging datasets.

Key Features:

• Patch Proximity Analysis: This method more accurately maps local cellular neighborhoods and interactions.
• Deep-Learning Annotation: Advanced deep-learning approaches for annotation are incorporated into the workflow.
• Computational Performance: Parallelization and GPU acceleration improve efficiency for large datasets often comprising tens of gigabytes per image.

Scientific Applications:

• Tissue Architecture Analysis: Enables researchers to study tissue organization by capturing thousands of cells and molecules in their native context.
• Cellular Microenvironment Mapping: Supports investigation of local cellular neighborhoods and interactions within tissue samples.
• Multiplexed Imaging Analysis: Facilitates efficient and accurate processing of large multiplexed imaging datasets across diverse research backgrounds.

Methodology:

SPACEc integrates image processing, cell segmentation, and data preprocessing into a single workflow, with patch proximity analysis for mapping local cellular neighborhoods and interactions, and incorporates deep-learning annotation approaches.