Shape-to-graph mapping method for efficient characterization and classification of complex geometries in biological images

• Type of Material: Article
• Authors: William Pilcher, Georgia Institute of Technology; Xingyu Yang, Georgia Institute of Technology; Anastasia Zhurikhina, Georgia Institute of Technology; Olga Chernaya, Georgia Institute of Technology; Yinghan Xu, Georgia Institute of Technology; Peng Qiu, Georgia Institute of Technology; Denis Tsygankov, Emory University
• Language: English
• Date: 2020-09-01
• Publisher: PUBLIC LIBRARY SCIENCE
• Publication Version: Final Published Version
• Copyright Statement: © 2020 Pilcher et al
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1371/journal.pcbi.1007758
• Title of Journal or Parent Work: PLOS COMPUTATIONAL BIOLOGY
• Volume: 16
• Issue: 9
• Start Page: e1007758
• End Page: e1007758
• Grant/Funding Information: This work was supported by the National Science Foundation grant CCF-1552784 and the ISAC Marylou Ingram Scholarship to P.Q. and by the U.S. Army Research Office (ARO) grant W911NF-17-1-0395 to D.T. and by funds from the Marcus Foundation, The Georgia Research Alliance, and the Georgia Tech Foundation through their support of the Marcus Center for Therapeutic Cell Characterization and Manufacturing (MC3M) at Georgia Tech. In all cases, the funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
• Keywords: Biochemical Research Methods; ANGIOGENESIS; Mathematical & Computational Biology; Biochemistry & Molecular Biology; Science & Technology; QUANTIFICATION; Life Sciences & Biomedicine; VORONOI DIAGRAMS
• Research Categories: Chemistry, Biochemistry; Biology, Molecular; Mathematics

Abstract

With the ever-increasing quality and quantity of imaging data in biomedical research comes the demand for computational methodologies that enable efficient and reliable automated extraction of the quantitative information contained within these images. One of the challenges in providing such methodology is the need for tailoring algorithms to the specifics of the data, limiting their areas of application. Here we present a broadly applicable approach to quantification and classification of complex shapes and patterns in biological or other multi-component formations. This approach integrates the mapping of all shape boundaries within an image onto a global information-rich graph and machine learning on the multidimensional measures of the graph. We demonstrated the power of this method by (1) extracting subtle structural differences from visually indistinguishable images in our phenotype rescue experiments using the endothelial tube formations assay, (2) training the algorithm to identify biophysical parameters underlying the formation of different multicellular networks in our simulation model of collective cell behavior, and (3) analyzing the response of U2OS cell cultures to a broad array of small molecule perturbations.