SlideBook Union and Synergy

Interoperability Modules for Imaging and Analysis Pipelines

Give SlideBook Scripting Superpowers! Introducing two all-new modules for interoperability with external applications: Union for Analysis Pipelines & Synergy for Imaging Pipelines

  • Implement analysis and imaging pipelines best suited for your science including machine learning and deep learning
  • Union enables sending & receiving image data, masks and objects to/from external applications including MATLAB or Python
  • Synergy includes all Union functionality plus hardware control & 6D Capture commands
  • Synergy server allows external applications to directly control SlideBook via a socket interface
  • Consulting services available to assist with getting started or complex implementations

For more information on how Union and Synergy can superpower your SlideBook experience, read on below - or contact us!

Get Union and Synergy Now

Fill out the form below and an applications scientist will contact you:

Union Analysis Pipeline Module

SlideBook Union allows interoperability with new or existing analysis pipelines. Image, mask, and object data can be sent to MATLAB or Python for processing and returned seamlessly to SlideBook. This module empowers users to apply machine learning and deep learning analysis tools tailored to their scientific and experimental needs - all within the SlideBook environment. With its powerful 2D and 3D visualization capabilities, convenient SLD file formats, and comprehensive mask and object statistics export, SlideBook enables users to analyze, review, and share processed data with confidence and ease.

Example: StarDist and MATLAB

StarDist is an AI-based tool that uses deep learning to detect objects with star-convex shapes in 2D and 3D. SlideBook Union allows users to segment image data with StarDist without leaving SlideBook. The resulting segmented region data is imported into SlideBook for further analysis or imaging. In this example, MATLAB code was used to process segmented coordinates/objects into regions.
 
Example: Adaptive Histogram Equalization via Python
Adaptive Histogram Equalization (AHE) is an image enhancement technique that improves the contrast and visibility of features. Rather than adjust an entire image, small regions are analyzed individually for ideal brightness and contrast. This approach is particularly useful when regions have varying levels of brightness. SlideBook Union can be used to implement AHE by exporting a channel in the current image to Python code (already written to perform AHE) and seamlessly importing a new AHE channel back into SlideBook.
 

Synergy Imaging Pipeline Module

SlideBook Synergy includes all the functionality found in the Union Analysis Pipeline Module functionality as well as hardware control & 6D Capture commands. SlideBook Synergy also features a server mode that allows external applications to trigger data exchange, hardware control and 6D Capture commands directly via sockets. These mechanisms allow for the implementation of powerful imaging pipelines where machine learning and deep learning processes guide the discovery of regions of interest (ROI) and automate high-resolution capture of each ROI.  The flexibility of SlideBook Synergy allows users to select scientifically- and experimentally-specific algorithms rather than relying on general techniques with reduced accuracy.