They require sample preparation, are time-consuming, expensive and labor intensive to develop, and are often toxic to the cells. However, imaging fluorescence stains does not come without drawbacks. Labelling with fluorescent dyes is a well-established and effective method for identifying cellular components. Ī typical workflow in image cytometry utilizes fluorescent staining and imaging to extract relevant features from cells (such as morphology, count and intensity) and subsequently builds classifiers for various purposes based on these features. Such mRNA based vaccinations are also currently being developed for Covid-19. Furthermore, using nanoparticle delivery of mRNA to adipocytes, via subcutaneous injection, is a very promising next-generation approach for protein replacement therapies and vaccination. Therapies that modify adipocyte phenotypes can also be used to adjust metabolic profiles towards more healthy states by encouraging catabolic lipid processing. The metabolic demands of nanomedicine transfection can therefore cause physical remodeling of the lipid droplets as the cells respond to the increased energy demands and the resulting phenotypic signatures can be used to evaluate nanomedicine efficacy. Membrane surfaces of lipid droplets can contain hundreds of different proteins (such as perilipins, enzymes and trafficking proteins) that allow them to function as energy repositories and interact with other cellular components. They provide fuel for the organism and supply a safeguard for energy fluctuations. The lipid droplets within the adipocytes play a key role in metabolism and are implicated in several pathologies, including cancer, diabetes and obesity. Nanomedicine uptake and effect on fat cells (adipocytes) can be explored using microscopy imaging techniques applied to stem cell derived cell cultures. These grants were awarded to Carolina Wählby (the PhD supervisor of the five authors on this paper).Ĭompeting interests: No authors have competing interests. All of the code and trained models to accompany this manuscript are available on GitHub ( ).įunding: This project was financially supported by the Swedish Foundation for Strategic Research (, grants BD150008 and ARC19-0016). This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.ĭata Availability: A sample of the data is freely available at and access to the entire dataset can be requested from AI Sweden ( ). Received: Accepted: SeptemPublished: October 15, 2021Ĭopyright: © 2021 Wieslander et al. The former resulted in better morphological and count features and the latter resulted in more faithfully captured defects in the lipids, which are key features required for downstream analysis of these channels.Ĭitation: Wieslander H, Gupta A, Bergman E, Hallström E, Harrison PJ (2021) Learning to see colours: Biologically relevant virtual staining for adipocyte cell images. The solutions included utilizing privileged information for the nuclear channel, and using image gradient information and adversarial training for the lipids channel. The models were tailored for each imaging channel, paying particular attention to the various challenges in each case, and those with the highest fidelity in extracted cell-level features were selected. To tackle this problem deep learning models were explored to learn the mapping between bright-field and fluorescence images for adipocyte cell images. Generating the fluorescence images directly from bright-field images using virtual staining (also known as “label-free prediction” and “in-silico labeling”) can get the best of both worlds, but can be very challenging to do for poorly visible cellular structures in the bright-field images. Bright-field images lack these downsides but also lack the clear contrast of the cellular components and hence are difficult to use for downstream analysis. Unfortunately, fluorescence microscopy is time-consuming, expensive, labour intensive, and toxic to the cells. Together these features form phenotypes that can be used to determine effective drug therapies, such as those based on nanomedicines. From these images various cellular features can be extracted. Fluorescence microscopy, which visualizes cellular components with fluorescent stains, is an invaluable method in image cytometry.
0 Comments
Leave a Reply. |