New definitions of human lymphoid and follicular cell entities in lymphatic tissue by machine learning

Abstract

Histological sections of the lymphatic system are usually the basis of static (2D) morphological investigations. Here, we performed a dynamic (4D) analysis of human reactive lymphoid tissue using confocal fluorescent laser microscopy in combination with machine learning. Based on tracks for T-cells (CD3), B-cells (CD20), follicular T-helper cells (PD1) and optical flow of follicular dendritic cells (CD35), we put forward the first quantitative analysis of movement-related and morphological parameters within human lymphoid tissue. We identified correlations of follicular dendritic cell movement and the behavior of lymphocytes in the microenvironment. In addition, we investigated the value of movement and/or morphological parameters for a precise definition of cell types (CD clusters). CD-clusters could be determined based on movement and/or morphology. Differentiating between CD3- and CD20 positive cells is most challenging and long term-movement characteristics are indispensable. We propose morphological and movement-related prototypes of cell entities applying machine learning models. Finally, we define beyond CD clusters new subgroups within lymphocyte entities based on long term movement characteristics. In conclusion, we showed that the combination of 4D imaging and machine learning is able to define characteristics of lymphocytes not visible in 2D histology.

Holistic View on the Structure of Immune Response: Petri Net Model

“…Real-time imaging microscopy on human lymph nodes has recorded the velocities and 3D tracks of individual cells [72], while automated image analysis is able to measure the distribution of dimension of lymphatic compartments and the abundances of cells in the departments [57]. We plan to feed quantitative data into our PN model in order to develop a quantitative model.…”

Imaging bridges pathology and radiology

“…To understand the interrelation between cellular networks and phenotypic changes of organs, e.g., lymph nodes, it is indispensable to understand underlying cell dynamics. 28 Investigating large amounts of cells in time and space, machine learning turned out to be helpfull. 28 Cellular interactions in some organs, such as the brain, may be relatively stable and static.…”

“… 28 Investigating large amounts of cells in time and space, machine learning turned out to be helpfull. 28 Cellular interactions in some organs, such as the brain, may be relatively stable and static. In the immune system, the movements of most cells are fast, and interactions are highly dynamic.…”

Multidimensionale Charakterisierung reaktiver und neoplastischer menschlicher Lymphknoten unter Anwendung von Methoden aus dem Bereich Bioinformatik, digitale Pathologie, Datenanalyse und Graphentheorie

“…Im Rahmen der Arbeit konnte gezeigt werden, dass die Analyse zweidimensional gescannter Dünnschnitte und dreidimensional gescannter Dickschnitte unterschiedliche Einblicke in die Konstitution humaner, lymphoider Gewebeproben ermöglicht. Darüber hinaus entstand in den letzten Jahren die Möglichkeit der Visualisierung humaner Gewebeproben in Raum und Zeit [10,11,12,133].…”

“…Es lassen sich Aussagen über die Zellbewegung treffen, um beispielsweise so die zelluläre Fitness zu beurteilen. Abschließend ermöglicht die 4D-Histologie eine mögliche Definition neuer funktionelle Subgruppen, welche über die reine CD-Klassifikation hinausgeht [133]. Dies ist in der klinischen Routine zuweilen nicht darstellbar.…”