Reservoir Computing for Jurkat T-cell Segmentation in High Resolution Live Cell Ca2+ Fluorescence Microscopy

Author(s):  
Fatemeh Hadaeghi ◽  
Bjorn-Philipp Diercks ◽  
Insa M.A. Wolf ◽  
Rene Werner
2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Fatemeh Hadaeghi ◽  
Björn-Philipp Diercks ◽  
Daniel Schetelig ◽  
Fabrizio Damicelli ◽  
Insa M. A. Wolf ◽  
...  

AbstractAdvances in high-resolution live-cell $$\hbox {Ca}^{2+}$$ Ca 2 + imaging enabled subcellular localization of early $$\hbox {Ca}^{2+}$$ Ca 2 + signaling events in T-cells and paved the way to investigate the interplay between receptors and potential target channels in $$\hbox {Ca}^{2+}$$ Ca 2 + release events. The huge amount of acquired data requires efficient, ideally automated image processing pipelines, with cell localization/segmentation as central tasks. Automated segmentation in live-cell cytosolic $$\hbox {Ca}^{2+}$$ Ca 2 + imaging data is, however, challenging due to temporal image intensity fluctuations, low signal-to-noise ratio, and photo-bleaching. Here, we propose a reservoir computing (RC) framework for efficient and temporally consistent segmentation. Experiments were conducted with Jurkat T-cells and anti-CD3 coated beads used for T-cell activation. We compared the RC performance with a standard U-Net and a convolutional long short-term memory (LSTM) model. The RC-based models (1) perform on par in terms of segmentation accuracy with the deep learning models for cell-only segmentation, but show improved temporal segmentation consistency compared to the U-Net; (2) outperform the U-Net for two-emission wavelengths image segmentation and differentiation of T-cells and beads; and (3) perform on par with the convolutional LSTM for single-emission wavelength T-cell/bead segmentation and differentiation. In turn, RC models contain only a fraction of the parameters of the baseline models and reduce the training time considerably.


Author(s):  
Sven-Thomas Antoni ◽  
Omar M. F. Ismail ◽  
Daniel Schetelig ◽  
Björn-Philipp Diercks ◽  
René Werner ◽  
...  

Immunology ◽  
2012 ◽  
Vol 135 (3) ◽  
pp. 198-206 ◽  
Author(s):  
Joseph J. Illingworth ◽  
P. Anton van der Merwe

Author(s):  
Milan Lesko ◽  
Zoltan Kato ◽  
Antal Nagy ◽  
Imre Gombos ◽  
Zsolt Torok ◽  
...  

2012 ◽  
Vol 86 (18) ◽  
pp. 9802-9816 ◽  
Author(s):  
Melissa M. Norström ◽  
Marcus Buggert ◽  
Johanna Tauriainen ◽  
Wendy Hartogensis ◽  
Mattia C. Prosperi ◽  
...  

HLA-B*5701 is the host factor most strongly associated with slow HIV-1 disease progression, although rates can vary within this group. Underlying mechanisms are not fully understood but likely involve both immunological and virological dynamics. The present study investigated HIV-1in vivoevolution and epitope-specific CD8+T cell responses in six HLA-B*5701 patients who had not received antiretroviral treatment, monitored from early infection for up to 7 years. The subjects were classified as high-risk progressors (HRPs) or low-risk progressors (LRPs) based on baseline CD4+T cell counts. Dynamics of HIV-1 Gag p24 evolution and multifunctional CD8+T cell responses were evaluated by high-resolution phylogenetic analysis and polychromatic flow cytometry, respectively. In all subjects, substitutions occurred more frequently in flanking regions than in HLA-B*5701-restricted epitopes. In LRPs, p24 sequence diversity was significantly lower; sequences exhibited a higher degree of homoplasy and more constrained mutational patterns than HRPs. The HIV-1 intrahost evolutionary rate was also lower in LRPs and followed a strict molecular clock, suggesting neutral genetic drift rather than positive selection. Additionally, polyfunctional CD8+T cell responses, particularly to TW10 and QW9 epitopes, were more robust in LRPs, who also showed significantly higher interleukin-2 (IL-2) production in early infection. Overall, the findings indicate that HLA-B*5701 patients with higher CD4 counts at baseline have a lower risk of HIV-1 disease progression because of the interplay between specific HLA-linked immune responses and the rate and mode of viral evolution. The study highlights the power of a multidisciplinary approach, integrating high-resolution evolutionary and immunological data, to understand mechanisms underlying HIV-1 pathogenesis.


2014 ◽  
Vol 111 (48) ◽  
pp. 17164-17169 ◽  
Author(s):  
Jérôme Boulanger ◽  
Charles Gueudry ◽  
Daniel Münch ◽  
Bertrand Cinquin ◽  
Perrine Paul-Gilloteaux ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document