Skip to main content

MIRIAM: A machine and deep learning single-cell segmentation and quantification pipeline for multi-dimensional tissue images


McKinley ETEliot T , Shao JJustin , Ellis STSamuel T , Heiser CNCody N , Roland JTJoseph T , Macedonia MCMary C , Vega PNPaige N , Shin SSusie , Coffey RJRobert J , Lau KSKen S . Cytometry. Part A : the journal of the International Society for Analytical Cytology. 2022 2 7; 101(6). 521-528


Increasingly, highly multiplexed tissue imaging methods are used to profile protein expression at the single-cell level. However, a critical limitation is the lack of robust cell segmentation tools for tissue sections. We present Multiplexed Image Resegmentation of Internal Aberrant Membranes (MIRIAM) that combines (a) a pipeline for cell segmentation and quantification that incorporates machine learning-based pixel classification to define cellular compartments, (b) a novel method for extending incomplete cell membranes, and (c) a deep learning-based cell shape descriptor. Using human colonic adenomas as an example, we show that MIRIAM is superior to widely utilized segmentation methods and provides a pipeline that is broadly applicable to different imaging platforms and tissue types.