Graph-based description of tertiary lymphoid organs at single-cell level

• Published in: PLoS computational biology Vol. 16; no. 2; p. e1007385
• Main Authors: Schaadt, Nadine S, Schönmeyer, Ralf, Forestier, Germain, Brieu, Nicolas, Braubach, Peter, Nekolla, Katharina, Meyer-Hermann, Michael, Feuerhake, Friedrich
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 21-02-2020; PLOS; Public Library of Science (PLoS)
• Subjects: Allografts; Antigens; Artificial Intelligence; Biology and Life Sciences; Biopsy; Breast cancer; Breast Neoplasms - pathology; CD20 antigen; CD3 antigen; Classification; Cluster analysis; Clustering; Composition; Computer and Information Sciences; Computer Science; Cystic fibrosis; Delaunay triangulation; Female; Fibrosis; Funding; Graph theory; Health aspects; Homografts; Human health and pathology; Humans; Image detection; Immune system; Immunology; Inflammation; Life Sciences; Lung cancer; Lymphocytes; Lymphoid Tissue - anatomy & histology; Medical imaging; Medical imaging equipment; Medical prognosis; Medicine and Health Sciences; Microscopy; Neighborhoods; Organs; Pathology; People and Places; Single-Cell Analysis; Support Vector Machine; Support vector machines; Surgery; Tissues and Organs; Transplantation; Transplants & implants; Xenografts; Germany
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1007385

Our aim is to complement observer-dependent approaches of immune cell evaluation in microscopy images with reproducible measures for spatial composition of lymphocytic infiltrates. Analyzing such patterns of inflammation is becoming increasingly important for therapeutic decisions, for example in transplantation medicine or cancer immunology. We developed a graph-based assessment of lymphocyte clustering in full whole slide images. Based on cell coordinates detected in the full image, a Delaunay triangulation and distance criteria are used to build neighborhood graphs. The composition of nodes and edges are used for classification, e.g. using a support vector machine. We describe the variability of these infiltrates on CD3/CD20 duplex staining in renal biopsies of long-term functioning allografts, in breast cancer cases, and in lung tissue of cystic fibrosis patients. The assessment includes automated cell detection, identification of regions of interest, and classification of lymphocytic clusters according to their degree of organization. We propose a neighborhood feature which considers the occurrence of edges with a certain type in the graph to distinguish between phenotypically different immune infiltrates. Our work addresses a medical need and provides a scalable framework that can be easily adjusted to the requirements of different research questions.