Cell shape characterization and classification with discrete Fourier transforms and self‐organizing maps

Kriegel, Fabian L.; Köhler, Ralf; Bayat-Sarmadi, Jannike; Bayerl, Simon; Hauser, Anja E.; Niesner, Raluca; Luch, Andreas; Cseresnyés, Zoltán

doi:10.1002/cyto.a.23279

Cited by 16 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By labeling the epithelium using an injection of the blue dye CMAC, we could observe myeloid cells sampling the epithelium by touching the bases of epithelial cells with their protrusions, and even reaching in between epithelial cells. When cell nuclei were labeled by injection of the nuclear dye Hoechst 33342, we could visualize the highly ordered cellular organization of the epithelial cells lining the villi, and motility was observed in a fraction of myeloid cells in the lamina propria, as described previously [ 30 ].…”

Section: Resultsmentioning

confidence: 99%

NAD(P)H Oxidase Activity in the Small Intestine Is Predominantly Found in Enterocytes, Not Professional Phagocytes

Lindquist

Bayat-Sarmadi

Leben

et al. 2018

IJMS

Self Cite

View full text Add to dashboard Cite

The balance between various cellular subsets of the innate and adaptive immune system and microbiota in the gastrointestinal tract is carefully regulated to maintain tolerance to the normal flora and dietary antigens, while protecting against pathogens. The intestinal epithelial cells and the network of dendritic cells and macrophages in the lamina propria are crucial lines of defense that regulate this balance. The complex relationship between the myeloid compartment (dendritic cells and macrophages) and lymphocyte compartment (T cells and innate lymphoid cells), as well as the impact of the epithelial cell layer have been studied in depth in recent years, revealing that the regulatory and effector functions of both innate and adaptive immune compartments exhibit more plasticity than had been previously appreciated. However, little is known about the metabolic activity of these cellular compartments, which is the basic function underlying all other additional tasks the cells perform. Here we perform intravital NAD(P)H fluorescence lifetime imaging in the small intestine of fluorescent reporter mice to monitor the NAD(P)H-dependent metabolism of epithelial and myeloid cells. The majority of myeloid cells which comprise the surveilling network in the lamina propria have a low metabolic activity and remain resting even upon stimulation. Only a few myeloid cells, typically localized at the tip of the villi, are metabolically active and are able to activate NADPH oxidases upon stimulation, leading to an oxidative burst. In contrast, the epithelial cells are metabolically highly active and, although not considered professional phagocytes, are also able to activate NADPH oxidases, leading to massive production of reactive oxygen species. Whereas the oxidative burst in myeloid cells is mainly catalyzed by the NOX2 isotype, in epithelial cells other isotypes of the NADPH oxidases family are involved, especially NOX4. They are constitutively expressed by the epithelial cells, but activated only on demand to ensure rapid defense against pathogens. This minimizes the potential for inadvertent damage from resting NOX activation, while maintaining the capacity to respond quickly if needed.

show abstract

Section: Resultsmentioning

confidence: 99%

NAD(P)H Oxidase Activity in the Small Intestine Is Predominantly Found in Enterocytes, Not Professional Phagocytes

Lindquist

Bayat-Sarmadi

Leben

et al. 2018

IJMS

Self Cite

View full text Add to dashboard Cite

show abstract

“…We evaluated how SPHARM-based descriptors perform in comparison to 2D shape descriptors. As SPHARM is a 3D extension of a Fourier analysis, we applied a method that is based on the classification of a set of Fourier components produced by Discrete Fourier Transform (DFT) after carrying out a 3D-to-2D projection of surface-rendered cells 35 . The advantage of the latter approach is two-fold: (i) the more complex 3D shape characterization by SPHARM is reduced to 2D DFT and (ii) the combination of various random 3D-to-2D projections allows a seamless transition from a pure 2D shape descriptor to a quasi-3D description of cell shapes.…”

Section: Resultsmentioning

confidence: 99%

“…This approach, however, is not restricted to SPHARM and SVM. We believe that adding dynamics to other shape descriptors, such as Fourier-based descriptors 35 or wavelets 36,37 , could also improve their classification accuracy. The performance of other classifiers -such as random forest or neural networks -should also be studied in the future.…”

Section: Discussionmentioning

confidence: 99%

Dynamic spherical harmonics approach for shape classification of migrating cells

Medyukhina

Blickensdorf

Cseresnyés

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Cell migration involves dynamic changes in cell shape. Intricate patterns of cell shape can be analyzed and classified using advanced shape descriptors, including spherical harmonics (SPHARM). Though SPHARM have been used to analyze and classify migrating cells, such classification did not exploit SPHARM spectra in their dynamics. Here, we examine whether additional information from dynamic SPHARM improves classification of cell migration patterns. We combine the static and dynamic SPHARM approach with a support-vector-machine classifier and compare their classification accuracies. We demonstrate that the dynamic SPHARM analysis classifies cell migration patterns more accurately than the static one for both synthetic and experimental data. Furthermore, by comparing the computed accuracies with that of a naive classifier, we can identify the experimental conditions and model parameters that significantly affect cell shape. This capability should-in the future-help to pinpoint factors that play an essential role in cell migration. A cell's migration behavior depends on the state of the cell, extracellular environment, and signals from other cells 1. We can study the mechanisms of cell migration by, e.g., knocking out a certain gene or altering the structure of the extracellular matrix (ECM) and testing whether these changes affect cell migration patterns, such as cell trajectory, shape, or shape dynamics (Fig. 1). To compare migration patterns in an objective and statistically sound way, they have to be automatically analyzed and quantified 2. Whereas both cell trajectories 3,4 and cell shape 5,6 can be quantified with a multitude of available methods, the analysis of shape dynamics-especially in 3D-received considerably less attention. When analyzing cell shape in a static fashion, we look at just one snapshot of the cell's migration history. Depending on how we choose this snapshot, we may either miss important differences in cell shape-e.g., if cells transiently appear similar but have different migration patterns-or detect spurious differences-e.g., if cells occur in different phases of the same migration pattern. Even averaging cell shape descriptors over time 7 may not always be sufficient to distinguish some migration patterns, for example when all cells evolve through similar phases of cell shape but different cells do this with different frequencies (Fig. S1) 8. To distinguish such details of migration behavior we need dynamic shape analysis that takes into account relative changes in cell shape between consecutive time points. While such dynamic shape analysis has been done in 2D 8-11 , 3D shape descriptors have not been applied to characterize and compare the full dynamic migration patterns of cells. The ultimate goal, however, is to understand how cells migrate in living organisms 12. Due to advances in intravital microscopy 13-15 , we have increasingly more 3D + time data of cells migrating in vivo and we should exploit the potential of 3D methods to analyze these data 16. Although there are many simpl...

show abstract

“…Those visual patterns provide information on the twodimensional and/or three-dimensional structure of the scene, shape and trajectory of objects and the activity that is going on. Therefore, this visual information of still and moving images is the key for tasks such as: video compression [1], object tracking [2], video segmentation [3], video surveillance [4], video and multitemporal image classification [5], cell shape classification [6].…”

Section: Introductionmentioning

confidence: 99%

FASTensor: A tensor framework for spatiotemporal description

Mota¹,

Santos²,

Araújo³

2019

Anais Estendidos Do XXXII Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2019)

View full text Add to dashboard Cite

Spatiotemporal description is a research field with applications in various areas such as video indexing, surveillance, human-computer interfaces, among others. Big Data problems in large databases are now being treated with Deep Learning tools, however we still have room for improvement in spatiotemporal handcraft description. Moreover, we still have problems that involve small data in which data augmentation and other techniques are not valid. The main contribution of this Ph.D. Thesis 1 is the development of a framework for spatiotemporal representation using orientation tensors enabling dimension reduction and invariance. This is a multipurpose framework called Features As Spatiotemporal Tensors (FASTensor). We evaluate this framework in three different applications: Human Action recognition, Video Pornography classification and Cancer Cell classification. The latter one is also a contribution of this work, since we introduce a new dataset called Melanoma Cancer Cell dataset (MCC). It is a small data that cannot be artificially augmented due the difficulty of extraction and the nature of motion. The results were competitive, while also being fast and simple to implement. Finally, our results in the MCC dataset can be used in other cancer cell treatment analysis.

show abstract

Cell shape characterization and classification with discrete Fourier transforms and self‐organizing maps

Cited by 16 publications

References 28 publications

NAD(P)H Oxidase Activity in the Small Intestine Is Predominantly Found in Enterocytes, Not Professional Phagocytes

NAD(P)H Oxidase Activity in the Small Intestine Is Predominantly Found in Enterocytes, Not Professional Phagocytes

Dynamic spherical harmonics approach for shape classification of migrating cells

FASTensor: A tensor framework for spatiotemporal description

Contact Info

Product

Resources

About