Phenotyping

AI-powered phenotyping of multiplexed images

An essential tool for investigation of the tumor microenvironment

The challenge with multiplexed technologies: Interpreting tissue images stained with high dimensional and multiplexed technologies represents a significant challenge to the unaided human cognitive system. As staining technologies such as imaging mass cytometry (IMC^™, Fluidigm) and high-plex fluorescent panels (Akoya PhenoCycler™) continue to stretch our abilities to interrogate the tumor microenvironment, finding meaningful differences in your data becomes an ever more data-heavy and daunting challenge.

Align it all

Combine all imaging channels to get a complete picture.

The full picture

The phenotyping module will analyze all the data and display a phenotype map of the tissue microenvironment.

Seeing spots

Apply heatmaps to quickly assess specific phenotypes.

Enter the matrix

Use the phenotype matrix to visualize the marker expression in each image.

Get to know the neighborhood

Neighborhood analysis compares cell phenotypes to get a better look at the cell populations in your data.

Compare and contrast

Use t-SNE plots to analyze expression and look for changes across study groups.

Find cell phenotypes using any number of biomarkers

Visiopharm’s AI-powered Phenotyping module streamlines and automates the analysis workflow of high dimensional image data. Discover individual cells types and populations, then use the comprehensive set of measurement and visualization tools to find differences between study groups.

What can you expect:

Intelligent software

Automatically clusters high dimensional data into easy to understand cell phenotypes that are based on marker expression.

Integrative workflows

Works with spectrally unmixed data from Akoya PhenoCycler™ or PhenoImager™ as well as images from Ultivue, IONPath (MIBI), Lunaphore Comet, Fluidigm Hyperion and many more.

Actionable results

Generates phenotypic matrices, profiles, neighborhood analysis and t-SNE plots to see phenotypic relationships and understand the spatial correlations in your data. Interactive t-SNE or box plots allow intuitive QC of your result data.

We are using these methods to determine the diversity of macrophage profiles that are present in liver biopsy samples from patients with different types of chronic liver disease, including viral hepatitis C, autoimmune hepatitis, and non-alcoholic steatohepatitis

Heather L. Stevenson M.D., PhD, Asst. Professor, Dept. of Pathology Liver & Transplantation Pathologist, The University of Texas Medical Branch