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

• Published in: Cytometry. Part A Vol. 101; no. 6; pp. 521 - 528
• Main Authors: McKinley, Eliot T., Shao, Justin, Ellis, Samuel T., Heiser, Cody N., Roland, Joseph T., Macedonia, Mary C., Vega, Paige N., Shin, Susie, Coffey, Robert J., Lau, Ken S.
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.06.2022; Wiley Subscription Services, Inc
• Subjects: Cell membranes; cell segmentation; Cell size; Deep learning; image processing; Image segmentation; Learning algorithms; Machine learning; multiplexed imaging; Multiplexing; single cell analysis; Tissues; image processing; cell segmentation; single cell analysis; multiplexed imaging
• ISSN: 1552-4922; 1552-4930
• DOI: 10.1002/cyto.a.24541

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.