Published March 18, 2022 | Version v1
Preprint Open

Unsupervised discovery of tissue architecture in multiplexed imaging

  • 1. Weill Cornell Medicine
  • 2. The University of North Carolina at Chapel Hill

Description

Multiplexed imaging and spatial transcriptomics enable highly resolved spatial characterization of cellular phenotypes, but still largely depend on laborious manual annotation to understand higher-order patterns of tissue organization. As a result, higher-order patterns of tissue organization are poorly understood and not systematically connected to disease pathology or clinical outcomes. To address this gap, we developed UTAG, a novel method to identify and quantify microanatomical tissue structures in multiplexed images without human intervention. Our method combines information on cellular phenotypes with the physical proximity of cells to accurately identify organ-specific microanatomical domains in healthy and diseased tissue. We apply our method to various types of images across physiological and disease states to show that it can consistently detect higher level architectures in human organs, quantify structural differences between healthy and diseased tissue, and reveal tissue organization patterns with relevance to clinical outcomes in cancer patients.

Files

BRCA_survival_utag_info.csv

Files (4.0 GB)

Name Size Download all
md5:fb0c7dc5548df7819f0a08792f20a7fc
590.2 MB Download
md5:498b3a0c756a4b25c2dffb7e00527c27
755.5 MB Download
md5:5d51b6be82c6174a6ce8e5115ebb8e20
635.0 MB Download
md5:9ed80ee4984175c9880dfe74d1621f47
29.7 kB Preview Download
md5:0d4d3a18d935dea55310b6e7d740ebeb
65.2 MB Download
md5:d5846d4d7f518745220d7a3bf7dc7006
48.8 MB Download
md5:db862b6b532554b7d6261db27315926f
428.2 MB Download
md5:d219ef00dca051e216bd46ef462bf847
598.3 MB Download
md5:150d4ef0111a6ec06d4561c84f319a49
202.2 MB Download
md5:d4b0a4e165798b964a853db7c0655111
217.5 MB Download
md5:17e9d53ddba0e1be809e2e436293cf86
198.7 MB Download
md5:1126d889b62412aefd57d25b8c4c6c88
11.5 MB Preview Download
md5:a5ef741109beb2faf04baf1b70e4d58d
208.7 MB Download