UMITIC: An unsupervised framework for the joint characterization of cellular phenotypes and spatial neighborhoods in multiplex and hyperplex immunofluorescence imaging data

UMITIC accurately characterizes cellular phenotypes and tissue neighborhoods across diverse multiplex imaging datasets, achieving high agreement with expert annotations and biological structures.

• Why it matters: Understanding tissue organization and cell interactions in high-dimensional imaging data is crucial for insights into immune responses and disease mechanisms, yet current methods struggle without annotations.
• What they did: The framework combines three modules—CellCut for cell delineation, CellMap for morphological feature extraction, and TissueNet for modeling spatial interactions—applied to datasets with up to 58 markers.
• The result: UMITIC reliably identifies immune cell types, tissue regions, and microanatomy, enabling detailed, interpretable analyses that support biological discovery and prognostic assessments without manual labeling.