Back to Search
Start Over
Learning to see colours: Biologically relevant virtual staining for adipocyte cell images
- Source :
- PLoS ONE, Vol 16, Iss 10 (2021), PLoS ONE, PLoS ONE, Vol 16, Iss 10, p e0258546 (2021)
- Publication Year :
- 2021
- Publisher :
- Public Library of Science (PLoS), 2021.
-
Abstract
- Fluorescence microscopy, which visualizes cellular components with fluorescent stains, is an invaluable method in image cytometry. From these images various cellular features can be extracted. Together these features form phenotypes that can be used to determine effective drug therapies, such as those based on nanomedicines. Unfortunately, fluorescence microscopy is time-consuming, expensive, labour intensive, and toxic to the cells. 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. 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. To tackle this problem deep learning models were explored to learn the mapping between bright-field and fluorescence images for adipocyte cell images. 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. The solutions included utilizing privileged information for the nuclear channel, and using image gradient information and adversarial training for the lipids channel. 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.
- Subjects :
- Fluorescence-lifetime imaging microscopy
Cytoplasm
Computer science
Biochemistry
Bright Field Microscopy
Fluorescence microscope
Adipocytes
Image Processing, Computer-Assisted
Electron Microscopy
Staining
Microscopy
Bioinformatics (Computational Biology)
Multidisciplinary
Medicinsk bildbehandling
Light Microscopy
Cell Staining
Lipids
Cytoplasmic staining
Image Cytometry
Medicine
Cellular Structures and Organelles
Research Article
Imaging Techniques
Science
Research and Analysis Methods
Models, Biological
Fluorescence Imaging
Humans
Cytoplasmic Staining
Image gradient
Cell Nucleus
Staining and Labeling
business.industry
Deep learning
Biology and Life Sciences
Pattern recognition
Cell Biology
Key features
Nuclear Staining
Medical Image Processing
Microscopy, Fluorescence
Specimen Preparation and Treatment
Bright Field Imaging
Bioinformatik (beräkningsbiologi)
Transmission Electron Microscopy
Artificial intelligence
business
Subjects
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 16
- Issue :
- 10
- Database :
- OpenAIRE
- Journal :
- PLoS ONE
- Accession number :
- edsair.doi.dedup.....aa29eb5e3991afeae863e96f2aac64f5