astropathjhuastropathjhu
19

AstroPathPipeline

screenshot of AstroPathPipeline

The AstroPath Pipeline was developed to process whole slide multiplex immunofluorescence data from microscope to database at single cell resolution.

Github

Overview

The AstroPath Pipeline is an innovative tool designed to enhance the processing of whole slide multiplex immunofluorescence data, bridging the gap between microscopy and database management. With its automation capabilities, this pipeline streamlines what can often be a complex and tedious workflow. Developed specifically for use with Akoya Biosciences’ Vectra imaging platform, it efficiently processes histopathology images, ensuring accurate data analysis and integration.

This powerful pipeline meticulously organizes and processes images through multiple stages, ultimately linking clinical and image data for comprehensive sample evaluation. By automating the various steps of image processing and ensuring consistency across batches, the AstroPath Pipeline stands as a game-changer for researchers and medical professionals involved in histopathology.

Features

  • Automated Processing: Streamlines the workflow from image capture to database loading, minimizing manual labor and reducing the chance of human error.

  • High Powered Field (HPF) Processing: Individual images are reorganized, corrected for imaging effects, and segmented, ensuring high accuracy in data preparation.

  • Batch Stitching and Annotation: Whole slide images are stitched together and annotated by a pathologist, facilitating effective collaboration and review.

  • Comprehensive Data Linking: Connects cell, image, and annotation data with clinical information, providing a complete view of each sample.

  • Modular Code Structure: Organized into distinct folders and modules, allowing for easier navigation and access to documentation tailored to each processing stage.

  • Compatibility with Python and MATLAB: Works seamlessly with Windows 10, Python 3.6 or higher, and MATLAB 2020a, ensuring versatility in usage.

  • Support for GPU Computation: Leverages PyOpenCL to enable GPU acceleration in certain Python modules, enhancing computational efficiency.

  • Anaconda Integration: Recommended for dependency management, simplifying the installation of required libraries and avoiding common installation issues.