S3-CIMA: Supervised spatial single-cell image analysis for identifying disease-associated cell-type compositions in tissue

The spatial organization of various cell types within the tissue microenvironment is a key element for the for-mation of physiological and pathological processes, including cancer and autoimmune diseases. Here, we present S3-CIMA, a weakly supervised convolutional neural network model that enables the detection of dis-ease-specific microenvironment compositions from high-dimensional proteomic imaging data. We demon-strate the utility of this approach by determining cancer outcome-and cellular-signaling-specific spatial cell -state compositions in highly multiplexed fluorescence microscopy data of the tumor microenvironment in colorectal cancer. Moreover, we use S3-CIMA to identify disease-onset-specific changes of the pancreatic tissue microenvironment in type 1 diabetes using imaging mass-cytometry data. We evaluated S3-CIMA as a powerful tool to discover novel disease-associated spatial cellular interactions from currently available and future spatial biology datasets.

Automated summary

This paper introduces a weakly supervised convolutional neural network model called S3-CIMA, which enables the detection of disease-specific microenvironment compositions from high-dimensional proteomic imaging data. By applying this approach in colorectal cancer and type 1 diabetes, the study demonstrates the potential of S3-CIMA in studying tumor microenvironments and disease onset.